Compare commits

..

1 Commits

Author SHA1 Message Date
Dr-Noob
b02d3d6d11 [0.95][x86] Print output to a file instead of printing it to stdout 2021-03-15 19:58:52 +01:00
65 changed files with 1870 additions and 4322 deletions

View File

@@ -1,36 +0,0 @@
name: 'Disable PR in cpufetch'
on:
issues:
types: opened
pull_request_target:
types: opened
permissions:
issues: write
pull-requests: write
jobs:
action:
runs-on: ubuntu-latest
steps:
- uses: dessant/repo-lockdown@v2
with:
github-token: ${{ github.token }}
exclude-issue-created-before: ''
exclude-issue-labels: ''
issue-labels: ''
issue-comment: ''
skip-closed-issue-comment: false
close-issue: false
lock-issue: true
issue-lock-reason: ''
exclude-pr-created-before: ''
exclude-pr-labels: ''
pr-labels: ''
pr-comment: 'cpufetch does not accept pull requests, see [the contributing guidelines](https://github.com/Dr-Noob/cpufetch/blob/master/CONTRIBUTING.md) for details'
skip-closed-pr-comment: false
close-pr: true
lock-pr: false
pr-lock-reason: ''
process-only: 'prs'

1
.gitignore vendored
View File

@@ -1,2 +1 @@
cpufetch
*.o

View File

@@ -1,52 +0,0 @@
# cpufetch contributing guidelines
<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
- [1. cpufetch does not accept pull requests](#1-cpufetch-does-not-accept-pull-requests)
- [2. Creating an issue](#2-creating-an-issue)
- [2.1: I found a bug in cpufetch (the program provides incorrect / invalid information)](#21-i-found-a-bug-in-cpufetch-the-program-provides-incorrect--invalid-information)
- [2.2: I found a bug in cpufetch (the program crashes / does not work properly)](#22-i-found-a-bug-in-cpufetch-the-program-crashes--does-not-work-properly)
- [Stacktrace option 1 (best)](#stacktrace-option-1-best)
- [Stacktrace option 2 (use this option if option 1 does not work)](#stacktrace-option-2-use-this-option-if-option-1-does-not-work)
- [2.3: I have an idea for a new feature in cpufetch / I want to suggest a change in cpufetch](#23-i-have-an-idea-for-a-new-feature-in-cpufetch--i-want-to-suggest-a-change-in-cpufetch)
<!-- END doctoc generated TOC please keep comment here to allow auto update -->
Thanks for your interest in contributing to cpufetch! Please, read this page carefully to understand how to contribute to cpufetch.
## 1. cpufetch does not accept pull requests
cpufetch is a small project, and I enjoy developing it. There are for sure some bugs and exciting features to add, but I prefer to make these
changes myself. For that reason, you should always use the issues page to report anything related to cpufetch. In the rare case that there is
a concise bug or feature that I am unable to implement myself, I will enable pull requests for this.
## 2. Creating an issue
### 2.1: I found a bug in cpufetch (the program provides incorrect / invalid information)
In the github issue **you must include**:
- Exact CPU model.
- Operating system.
- The output of `cpufetch`.
- The output of `cpufetch --debug`.
### 2.2: I found a bug in cpufetch (the program crashes / does not work properly)
- Exact CPU model.
- Operating system.
- The output of `cpufetch`.
- The output of `cpufetch --debug`.
- A stacktrace (if program crashes):
#### Stacktrace option 1 (best)
1. Build cpufetch with debug symbols (`make clean; make debug`).
2. Install valgrind (if it is not already installed)
3. Run cpufetch with valgrind (`valgrind ./cpufetch`)
4. Paste the complete output (preferably on a platform like pastebin)
#### Stacktrace option 2 (use this option if option 1 does not work)
1. Build cpufetch with debug symbols (`make clean; make debug`).
2. Install gdb (if it is not already installed)
3. Debug cpufetch with gdb (`gdb cpufetch`)
3. Run cpufetch (just r inside gdb console)
4. Paste the complete output (preferably on a platform like pastebin)
### 2.3: I have an idea for a new feature in cpufetch / I want to suggest a change in cpufetch
Just explain the feature in the issue and include references (links) to relevant sources if appropriate.

View File

@@ -1,10 +1,8 @@
CC ?= gcc
CXX=gcc
CFLAGS+=-Wall -Wextra -pedantic
CXXFLAGS=-Wall -Wextra -Werror -pedantic -fstack-protector-all -pedantic -std=c99
SANITY_FLAGS=-Wfloat-equal -Wshadow -Wpointer-arith
PREFIX ?= /usr
SRC_COMMON=src/common/
COMMON_SRC = $(SRC_COMMON)main.c $(SRC_COMMON)cpu.c $(SRC_COMMON)udev.c $(SRC_COMMON)printer.c $(SRC_COMMON)args.c $(SRC_COMMON)global.c
@@ -12,39 +10,16 @@ COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_C
ifneq ($(OS),Windows_NT)
arch := $(shell uname -m)
ifeq ($(arch), $(filter $(arch), x86_64 amd64 i686))
ifeq ($(arch), x86_64)
SRC_DIR=src/x86/
SOURCE += $(COMMON_SRC) $(SRC_DIR)cpuid.c $(SRC_DIR)apic.c $(SRC_DIR)cpuid_asm.c $(SRC_DIR)uarch.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h $(SRC_DIR)freq/freq.h
os := $(shell uname -s)
ifeq ($(os), Linux)
SOURCE += $(SRC_DIR)freq/freq.c freq_nov.o freq_avx.o freq_avx512.o
HEADERS += $(SRC_DIR)freq/freq.h
CFLAGS += -pthread
endif
CFLAGS += -DARCH_X86 -std=c99 -fstack-protector-all
else ifeq ($(arch), $(filter $(arch), ppc64le ppc64 ppcle ppc))
SRC_DIR=src/ppc/
SOURCE += $(COMMON_SRC) $(SRC_DIR)ppc.c $(SRC_DIR)uarch.c $(SRC_DIR)udev.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)ppc.h $(SRC_DIR)uarch.h $(SRC_DIR)udev.c
CFLAGS += -DARCH_PPC -std=gnu99 -fstack-protector-all
else ifeq ($(arch), $(filter $(arch), arm aarch64_be aarch64 arm64 armv8b armv8l armv7l armv6l))
HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h
CXXFLAGS += -DARCH_X86
else
SRC_DIR=src/arm/
SOURCE += $(COMMON_SRC) $(SRC_DIR)midr.c $(SRC_DIR)uarch.c $(SRC_DIR)soc.c $(SRC_DIR)udev.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)midr.h $(SRC_DIR)uarch.h $(SRC_DIR)soc.h $(SRC_DIR)udev.c $(SRC_DIR)socs.h
CFLAGS += -DARCH_ARM -Wno-unused-parameter -std=c99 -fstack-protector-all
os := $(shell uname -s)
ifeq ($(os), Darwin)
SOURCE += $(SRC_DIR)sysctl.c
HEADERS += $(SRC_DIR)sysctl.h
endif
else
# Error lines should not be tabulated because Makefile complains about it
$(warning Unsupported arch detected: $(arch). See https://github.com/Dr-Noob/cpufetch#1-support)
$(warning If your architecture is supported but the compilation fails, please open an issue in https://github.com/Dr-Noob/cpufetch/issues)
$(error Aborting compilation)
CXXFLAGS += -DARCH_ARM -Wno-unused-parameter
endif
OUTPUT=cpufetch
@@ -53,47 +28,29 @@ else
SRC_DIR=src/x86/
SOURCE += $(COMMON_SRC) $(SRC_DIR)cpuid.c $(SRC_DIR)apic.c $(SRC_DIR)cpuid_asm.c $(SRC_DIR)uarch.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h
CFLAGS += -DARCH_X86 -std=c99
CXXFLAGS += -DARCH_X86
SANITY_FLAGS += -Wno-pedantic-ms-format
OUTPUT=cpufetch.exe
endif
all: CFLAGS += -O2
all: $(OUTPUT)
debug: CFLAGS += -g -O0
debug: CXXFLAGS += -g -O0
debug: $(OUTPUT)
static: CFLAGS += -static -O2
static: $(OUTPUT)
strict: CFLAGS += -O2 -Werror -fsanitize=undefined -D_FORTIFY_SOURCE=2
strict: $(OUTPUT)
freq_nov.o: Makefile $(SRC_DIR)freq/freq_nov.c $(SRC_DIR)freq/freq_nov.h
$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -pthread $(SRC_DIR)freq/freq_nov.c -o $@
freq_avx.o: Makefile $(SRC_DIR)freq/freq_avx.c $(SRC_DIR)freq/freq_avx.h
$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx -mfma -pthread $(SRC_DIR)freq/freq_avx.c -o $@
freq_avx512.o: Makefile $(SRC_DIR)freq/freq_avx512.c $(SRC_DIR)freq/freq_avx512.h
$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx512f -mfma -pthread $(SRC_DIR)freq/freq_avx512.c -o $@
release: CXXFLAGS += -static -O3
release: $(OUTPUT)
$(OUTPUT): Makefile $(SOURCE) $(HEADERS)
$(CC) $(CFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT)
$(CXX) $(CXXFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT)
run: $(OUTPUT)
./$(OUTPUT)
clean:
@rm -f $(OUTPUT) *.o
@rm $(OUTPUT)
install: $(OUTPUT)
install -Dm755 "cpufetch" "$(DESTDIR)$(PREFIX)/bin/cpufetch"
install -Dm644 "LICENSE" "$(DESTDIR)$(PREFIX)/share/licenses/cpufetch-git/LICENSE"
install -Dm644 "cpufetch.1" "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1.gz"
uninstall:
rm -f "$(DESTDIR)$(PREFIX)/bin/cpufetch"
rm -f "$(DESTDIR)$(PREFIX)/share/licenses/cpufetch-git/LICENSE"
rm -f "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1.gz"
install -Dm755 "cpufetch" "/usr/bin/cpufetch"
install -Dm644 "LICENSE" "/usr/share/licenses/cpufetch-git/LICENSE"
install -Dm644 "cpufetch.8" "/usr/share/man/man8/cpufetch.8.gz"

171
README.md
View File

@@ -1,84 +1,36 @@
<p align="center"><img width=50% src="./pictures/cpufetch.png"></p>
# cpufetch
<h4 align="center">Simple yet fancy CPU architecture fetching tool</h4>
Simplistic yet fancy CPU architecture fetching tool
![cpu1](pictures/i9.png)
<p align="center"> </p>
### Platforms
cpufetch currently supports x86_64 CPUs (both Intel and AMD) and ARM.
<div align="center">
<img height="22px" src="https://img.shields.io/github/v/tag/Dr-Noob/cpufetch?label=cpufetch&style=flat-square">
<a href="https://github.com/Dr-Noob/cpufetch/stargazers">
<img height="22px" src="https://img.shields.io/github/stars/Dr-Noob/cpufetch?color=4CC61F&style=flat-square">
</a>
<a href="https://github.com/Dr-Noob/cpufetch/issues">
<img height="22px" src="https://img.shields.io/github/issues/Dr-Noob/cpufetch?style=flat-square">
</a>
<a href="https://github.com/Dr-Noob/cpufetch/blob/master/README.md#1-support">
<img height="22px" src="pictures/os-shield.jpg">
</a>
<a href="https://github.com/Dr-Noob/cpufetch/blob/master/LICENSE">
<img height="22px" src="https://img.shields.io/github/license/Dr-Noob/cpufetch?color=orange&style=flat-square">
</a>
</div>
| Platform | x86_64 | ARM | Notes |
|:---------:|:------------------------:|:-------------------:|:-----------------:|
| Linux | :heavy_check_mark: | :heavy_check_mark: | Prefered platform. <br> Experimental ARM support |
| Windows | :heavy_check_mark: | :x: | Some information may be missing. <br> Colors will be used if supported |
| Android | :heavy_exclamation_mark: | :heavy_check_mark: | Experimental ARM support |
| macOS | :heavy_check_mark: | :x: | Some information may be missing |
<p align="center"> </p>
<p align="center">
cpufetch is a command-line tool written in C that displays the CPU information in a clean and beautiful way
</p>
<p align="center">
<img width=80% src="./pictures/examples.gif">
</p>
# Table of contents
<!-- UPDATE with: doctoc --notitle README.md -->
<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
| Emoji | Meaning |
|:-----------------------:|:-------------:|
|:heavy_check_mark: | Supported |
|:x: | Not supported |
|:heavy_exclamation_mark: | Not tested |
- [1. Support](#1-support)
- [2. Installation](#2-installation)
- [2.1 Installing from a package](#21-installing-from-a-package)
- [2.2 Building from source](#22-building-from-source)
- [2.3 Android](#23-android)
- [3. Examples](#3-examples)
- [3.1 x86_64](#31-x86_64)
- [3.2 ARM](#32-arm)
- [3.3 PowerPC](#33-powerpc)
- [4. Colors](#4-colors)
- [4.1 Specifying a name](#41-specifying-a-name)
- [4.2 Specifying the colors in RGB format](#42-specifying-the-colors-in-rgb-format)
- [5. Implementation](#5-implementation)
- [6. Bugs or improvements](#6-bugs-or-improvements)
- [7. Acknowledgements](#7-acknowledgements)
- [8. cpufetch for GPUs (gpufetch)](#8-cpufetch-for-gpus-gpufetch)
### Usage and installation
#### Linux
There is a cpufetch package available in Arch Linux ([cpufetch-git](https://aur.archlinux.org/packages/cpufetch-git)).
<!-- END doctoc generated TOC please keep comment here to allow auto update -->
If you are in another distro, you can build `cpufetch` from source (see below)
## 1. Support
#### Windows
In the [releases](https://github.com/Dr-Noob/cpufetch/releases) section you will find some cpufetch executables compiled for Windows. Just download and run it from Windows CMD.
| OS | x86_64 / x86 | ARM | PowerPC |
|:-----------:|:------------------:|:------------------:|:------------------:|
| GNU / Linux | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| Windows | :heavy_check_mark: | :x: | :x: |
| Android | :heavy_check_mark: | :heavy_check_mark: | :x: |
| macOS | :heavy_check_mark: | :heavy_check_mark: | :x: |
| FreeBSD | :heavy_check_mark: | :x: | :x: |
**NOTES:**
- Colors will be used in Windows only if the terminal supports it.
- Support in macOS ARM is limited to Apple M1 only
## 2. Installation
### 2.1 Installing from a package
Choose the right package for your operating system:
[![Packaging status](https://repology.org/badge/vertical-allrepos/cpufetch.svg)](https://repology.org/project/cpufetch/versions)
If there is no available package for your OS, you can download the cpufetch binary from [the releases page](https://github.com/Dr-Noob/cpufetch/releases), or [build cpufetch from source](#22-building-from-source-linuxwindowsmacos) (see below).
### 2.2 Building from source
You will need a C compiler (e.g, `gcc`) and `make` to compile `cpufetch`. Just clone the repo and run `make`:
#### Building from source
Just clone the repo and use `make` to compile it
```
git clone https://github.com/Dr-Noob/cpufetch
@@ -87,74 +39,41 @@ make
./cpufetch
```
### 2.3 Android
1. Install `termux` app (terminal emulator)
2. Run `pkg install -y git make clang` inside termux.
3. Build from source normally:
- git clone https://github.com/Dr-Noob/cpufetch
- cd cpufetch
- make
- ./cpufetch
The Makefile is designed to work on both Linux and Windows.
## 3. Examples
### 3.1 x86_64
### Examples
Here are more examples of how `cpufetch` looks on different CPUs.
<p align="center"><img width=90% src="pictures/epyc.png"></p>
<p align="center">AMD EPYC HPC server</p>
<p align="center"><img width=90% src="pictures/cascade_lake.jpg"></p>
<p align="center">Intel Xeon HPC server</p>
##### x86_64 CPUs
### 3.2 ARM
![cpu2](pictures/epyc.png)
<p align="center">
<img width=45% src="pictures/exynos.jpg">
&nbsp;
<img width=45% src="pictures/snapd.png">
</p>
<p align="center">Samsung Galaxy S8 (left) Xiaomi Redmi Note 7 (right)</p>
![cpu3](pictures/cascade_lake.png)
### 3.3 PowerPC
##### ARM CPUs
<p align="center"><img width=90% src="pictures/ibm.png"></p>
<p align="center">Talos II</p>
![cpu4](pictures/exynos.png)
## 4. Colors
By default, `cpufetch` will print the CPU logo with the system colorscheme. However, you can set a custom color scheme in two different ways:
![cpu5](pictures/snapdragon.png)
### 4.1 Specifying a name
By specifying a name, cpufetch will use the specific colors of each manufacture. Valid values are:
- intel
- intel-new
- amd
- ibm
- arm
### Colors and style
By default, `cpufetch` will print the CPU art with the system colorscheme. However, you can always set a custom color scheme, either
specifying Intel or AMD, or specifying the colors in RGB format:
```
./cpufetch --color intel (default color for Intel)
./cpufetch --color amd (default color for AND)
./cpufetch --color 239,90,45:210,200,200:100,200,45:0,200,200 (example)
```
### 4.2 Specifying the colors in RGB format
In the case of setting the colors using RGB, 4 colors must be given in with the format: ``[R,G,B:R,G,B:R,G,B:R,G,B]``. These colors correspond to CPU art color (2 colors) and for the text colors (following 2). Thus, you can customize all the colors.
5 colors must be given in RGB with the format: ``[R,G,B:R,G,B:R,G,B:R,G,B:R,G,B]``. These colors correspond to the CPU logo color (first 3 colors) and for the text colors (following 2).
### Implementation
```
./cpufetch --color 239,90,45:210,200,200:0,0,0:100,200,45:0,200,200
```
See [cpufetch programming documentation](https://github.com/Dr-Noob/cpufetch/blob/master/doc/README.md).
## 5. Implementation
See [cpufetch programming documentation](https://github.com/Dr-Noob/cpufetch/tree/master/doc).
### Bugs or improvements
There are many open issues in github (see [issues](https://github.com/Dr-Noob/cpufetch/issues)). Feel free to open a new one report an issue or propose any improvement in `cpufetch`
## 6. Bugs or improvements
See [cpufetch contributing guidelines](https://github.com/Dr-Noob/cpufetch/blob/master/CONTRIBUTING.md).
## 7. Acknowledgements
Thanks to the fellow contributors and interested people in the project. Special thanks to:
- [Gonzalocl](https://github.com/Gonzalocl), [OdnetninI](https://github.com/OdnetninI): Tested cpufetch in the earlier versions of the project in many different CPUs.
- [Kyngo](https://github.com/Kyngo): Tested cpufetch in the Apple M1 CPU.
- [avollmerhaus](https://github.com/avollmerhaus): Gave me ssh acess to a PowerPC machine, allowing me to develop the PowerPC port.
- [bbonev](https://github.com/bbonev), [stephan-cr](https://github.com/stephan-cr): Reviewed the source code.
## 8. cpufetch for GPUs (gpufetch)
See [gpufetch](https://github.com/Dr-Noob/gpufetch) project!
### Testing
I would like to thank [Gonzalocl](https://github.com/Gonzalocl) and [OdnetninI](https://github.com/OdnetninI) for their help, running `cpufetch` in many different CPUs they have access to, which makes it easier to debug and check the correctness of `cpufetch`.

View File

@@ -1,91 +0,0 @@
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.48.3. It was also manually adapted to look correctly
.\" help2man -N -n "Simple yet fancy CPU architecture fetching tool" ./cpufetch > cpufetch.1
.TH CPUFETCH "1" "September 2021" "cpufetch v1.00 (Linux x86_64 build)" "User Commands"
.SH NAME
cpufetch \- Simple yet fancy CPU architecture fetching tool
.SH SYNOPSIS
.B cpufetch
[\fI\,OPTION\/\fR]...
.SH DESCRIPTION
cpufetch is a command-line tool written in C that displays the CPU information in a clean and beautiful way
.SH OPTIONS
.TP
\fB\-c\fR, \fB\-\-color\fR
Set the color scheme (by default, cpufetch uses the system color scheme)
.TP
\fB\-s\fR, \fB\-\-style\fR
Set the style of CPU logo
.TP
\fB\-d\fR, \fB\-\-debug\fR
Print CPU model and cpuid levels (debug purposes)
.TP
\fB\-\-logo\-short\fR
Show the short version of the logo
.TP
\fB\-\-logo\-long\fR
Show the long version of the logo
.TP
\fB\-v\fR, \fB\-\-verbose\fR
Print extra information (if available) about how cpufetch tried fetching information
.TP
\fB\-\-logo\-intel\-old\fR
Show the old Intel logo
.TP
\fB\-\-logo\-intel\-new\fR
Show the new Intel logo
.TP
\fB\-F\fR, \fB\-\-full\-cpu\-name\fR
Show the full CPU name (do not abbreviate it)
.TP
\fB\-r\fR, \fB\-\-raw\fR
Print raw cpuid data (debug purposes)
.TP
\fB\-h\fR, \fB\-\-help\fR
Print this help and exit
.TP
\fB\-V\fR, \fB\-\-version\fR
Print cpufetch version and exit
.SH COLORS
.TP
* "intel":
Use Intel default color scheme
.TP
* "amd":
Use AMD default color scheme
.TP
* "ibm",
Use IBM default color scheme
.TP
* "arm":
Use ARM default color scheme
.TP
* custom:
If the argument of \fB\-\-color\fR does not match any of the previous strings, a custom scheme can be specified. 5 colors must be given in RGB with the format: R,G,B:R,G,B:...The first 3 colors are the CPU art color and the next 2 colors are the text colors
.SH STYLES
.TP
* "fancy":
Default style
.TP
* "retro":
Old cpufetch style
.TP
* "legacy":
Fallback style for terminals that do not support colors
.SH LOGOS
.TP
cpufetch will try to adapt the logo size and the text to the terminal width. When the output (logo and text) is wider than the terminal width, cpufetch will print a smaller version of the logo (if it exists). This behavior can be overridden by \fB\-\-logo\-short\fR and \fB\-\-logo\-long\fR, which always sets the logo size as specified by the user, even if it is too big. After the logo selection (either automatically or set by the user), cpufetch will check again if the output fits in the terminal. If not, it will use a shorter name for the fields (the left part of the text). If, after all of this, the output still does not fit, cpufetch will cut the text and will only print the text until there is no space left in each line
.SH EXAMPLES
.TP
Run cpufetch with Intel color scheme:
.IP
\&./cpufetch \fB\-\-color\fR intel
.TP
Run cpufetch with a custom color scheme:
.IP
\&./cpufetch \fB\-\-color\fR 239,90,45:210,200,200:0,0,0:100,200,45:0,200,200
.SH BUGS
.TP
Report bugs to https://github.com/Dr\-Noob/cpufetch/issues
.SH NOTE
.TP
Peak performance information is NOT accurate. cpufetch computes peak performance using the max frequency of the CPU. However, to compute the peak performance, you need to know the frequency of the CPU running AVX code. This value is not be fetched by cpufetch since it depends on each specific CPU. To correctly measure peak performance, see: https://github.com/Dr\-Noob/peakperf

57
cpufetch.8 Normal file
View File

@@ -0,0 +1,57 @@
.TH man 8 "1 Sep 2020" "0.7" "cpufetch man page"
.SH NAME
cpufetch \- Simplistic yet fancy CPU architecture fetching tool
.SH SYNOPSIS
cpufetch [--version] [--help] [--levels] [--style fancy|retro|legacy] [--color intel|amd|'R,G,B:R,G,B:R,G,B:R,G,B']
.SH DESCRIPTION
cpufetch will print CPU information, for which will query CPUID instructions and udev directories on Linux as a fallback method. Some of this features are:
.IP \[bu] 2
Name
.IP \[bu]
Frequency
.IP \[bu]
Number of cores (Physical and Logical)
.IP \[bu]
Cache sizes
.IP \[bu]
Theoretical peak performance in floating point operations per second (FLOP/s)
.SH OPTIONS
.TP
\fB\-\-style\fR \f[I][intel|amd|R,G,B:R,G,B:R,G,B:R,G,B]\f[]
Set the color scheme. By default, cpufetch uses the system color scheme. This option lets the user use different colors to print the CPU art:
.IP \[bu]
\fB"intel"\fR: Use intel color scheme
.IP \[bu]
\fB"amd"\fR: Use amd color scheme
.IP \[bu]
\fBcustom\fR: If color do not match "intel" or "amd", a custom scheme can be specified: 4 colors must be given in RGB with the format: R,G,B:R,G,B:...
These colors correspond to CPU art color (2 colors) and for the text colors (following 2)
.TP
\fB\-\-style\fR \f[I]STYLE\f[]
Specify the style of ascii logo:
.IP \[bu]
\fB"fancy"\fR: Default style
.IP \[bu]
\fB"retro"\fR: Old cpufetch style
.IP \[bu]
\fB"legacy"\fR: Fallback style for terminals that does not support colors
.TP
\fB\-\-levels\fR
Prints CPUID levels and CPU name
.TP
\fB\-\-verbose\fR
Prints extra information (if available) about how cpufetch tried fetching information
.TP
\fB\-\-help\fR
Prints help
.TP
\fB\-\-version\fR
Prints cpufetch version
.SH BUGS
Bugs should be posted on: https://github.com/Dr-Noob/cpufetch/issues
.SH NOTES
Peak performance information is NOT accurate. cpufetch computes peak performance using the max
frequency. However, to properly compute peak performance, you need to know the frequency of the
CPU running AVX code, which is not be fetched by cpufetch since it depends on each specific CPU.
.SH AUTHOR
Dr-Noob (https://github.com/Dr-Noob)

View File

@@ -11,7 +11,7 @@ Microarchitecture information is acquired from the Main ID Register (MIDR) [[2](
- `CPU part`
- `CPU revision`
The MIDR register can be built with this information. Another possible approach is to read MIDR directly from `/sys/devices/system/cpu/cpu*/regs/identification/midr_el1`
The MIDR register can be built with this information. Another posible approach is to read MIDR directly from `/sys/devices/system/cpu/cpu*/regs/identification/midr_el1`
With the MIDR available, the approach is the same as the one used in x86_64 architectures. cpufetch has a file that acts like a database that tries to match the MIDR register with the specific CPU microarchitecture.

View File

@@ -1,26 +0,0 @@
### 2. How to get CPU microarchitecture?
__Involved code: [get_uarch_from_pvr (uarch.c)](https://github.com/Dr-Noob/cpufetch/src/ppc/uarch.c)__
Microarchitecture is deduced from the PVR register, which is read using the `mfpvr` instruction. The correspondence between the PVR and the specific microarchitecture has been implemented using the values in `arch/powerpc/kernel/cputable.c` in the Linux kernel. Some of them have been removed. The manufacturing process has been queried by searching on the internet.
### 3. How to get CPU topology?
__Involved code: [get_topology_info (ppc.c)](https://github.com/Dr-Noob/cpufetch/src/ppc/ppc.c)__
The total number of cores is queried using `sysconf(_SC_NPROCESSORS_ONLN)`. Then, with the number of sockets and the number of physical cores, we can calculate the number of threads per core.
The number of sockets is queried using `/sys/devices/system/cpu/cpu*/topology/physical_package_id`. Once this file has been read for all of the cores, a simple custom algorithm is used to determine the number of sockets.
The number of physical cores is queried using `/sys/devices/system/cpu/cpu*/topology/core_id`. Again, a custom algorithm is used to determine the number of physical cores.
### 4. How to get the frequency?
Frequency is read directly from `/sys/devices/system/cpu/cpu*/cpufreq/cpuinfo_max_freq`
### 5. How to get cache size and topology?
Cache size is retrieved directly from Linux (using `/sys/devices/system/cpu/cpu0/cache/index*/size`).
To find the cache topology, the files `/sys/devices/system/cpu/cpu0/cache/index*/shared_cpu_map` are used, and a custom algorithm is used to determine how many caches are there at each level.
_NOTE_: To avoid Linux dependencies at this point, it looks like it is possible to derive the cache size and topology from the microarchitecture. For example, in the POWER9 architecture, wikichip assumes that all the POWER9 CPUs have the same cache size for each core and topology [[1](#references)].
#### References
- [1] [POWER9 - wikichip](https://en.wikichip.org/wiki/ibm/microarchitectures/power9)

View File

@@ -1,14 +1,13 @@
# cpufetch programming documentation (v0.98)
# cpufetch programming documentation (v0.94)
This documentation explains how cpufetch works internally and all the design decisions I made. This document intends to be useful for me in the future, for everyone interested in the project, and for anyone who is trying to obtain any specific information from the CPU. In this way, this can be used as a manual or a page that collects interesting material in this area.
### 1. Basics
cpufetch works for __x86_64__ (Intel and AMD), __ARM__ and __PowerPC__ CPUs. However, cpufetch is expected to work better on x86_64, because the codebase is older and has been tested much more than the ARM and PowerPC versions. Depending on the architecture, cpufetch choose certain files to be compiled. A summarized tree of the source code of cpufetch is shown below.
cpufetch works for __x86_64__ (Intel and AMD) and __ARM__ CPUs. However, cpufetch is expected to work better on x86_64, because the codebase is older and has been tested much more than the ARM version. Other kinds of x86_64 CPU are not supported (I don't think supporting other CPUs may pay off). Depending on the architecture, cpufetch choose certain files to be compiled. A summarized tree of the source code of cpufetch is shown below.
```
cpufetch/
├── doc
│   ├── DOCUMENTATION_ARM.md
| ├── DOCUMENTATION_PPC.md
│   ├── DOCUMENTATION_X86.md
│   └── README.md
├── Makefile
@@ -20,22 +19,17 @@ cpufetch/
│   └── other files ...
├── common/
│   └── common files ...
├── ppc/
| ├── ppc.c
| ├── ppc.h
| └── other files ...
└── x86/
├── cpuid.c
├── cpuid.h
└── other files ...
```
Source code is divided into four directories:
Source code is divided into three directories:
- `common/`: Source code shared between all architectures
- `arm/`: ARM source code
- `ppc/`: PowerPC source code
- `x86/`: x86 source code
- `common/`: Source code shared between x86 and ARM
- `arm/`: ARM dependant source code
- `x86/`: x86_64 dependant source code
##### 1.1 Basics (x86_64)
@@ -56,14 +50,10 @@ struct cpuInfo {
To use any CPUID leaf, cpufetch always needs to check that it is supported in the current CPU.
##### 1.2 Basics (ARM)
In ARM, __cpufetch works using the MIDR register and Linux filesystem__. MIDR (Main ID Register) is read from `/proc/cpuinfo`. It allows the detection of the microarchitecture of the cores. Furthermore, Linux filesystem `/sys/devices/system/cpu/` is used to fetch the number of cores and other information. This is the main reason to explain __why `cpufetch` for ARM only works on Linux systems.__
In ARM, __cpufetch works using the MIDR register and Linux filesystem__. MIDR (Main ID Register) is read from `/proc/cpuinfo`. It allows the detection of the microarchitecture of the cores. Furthermore, Linux filesystem `/sys/devices/system/cpu/` is used to fetch the number of cores and other information. This is the main reason to explain __why `cpufetch` only works on Linux kernel based systems.__
##### 1.3 Basics (PowerPC)
In PowerPC, __cpufetch works using the PVR register and Linux filesystem__. PVR (Processor Version Register) is read using assembly and it is used to identify the microarchitecture of the CPU. Linux is also used to query the rest of the information, like the CPU topology, frequency, etc. This is the main reason to explain __why `cpufetch` for PowerPC only works on Linux systems.__
##### 1.3 Documentation organization
The rest of the documentation is divided into x86 and ARM architectures since each one needs different implementations:
##### 1.4 Documentation organization
The rest of the documentation is divided in specific files for each architecture, since each one needs different implementations:
- [DOCUMENTATION_ARM.md](https://github.com/Dr-Noob/cpufetch/blob/master/doc/DOCUMENTATION_ARM.md)
- [DOCUMENTATION_PPC.md](https://github.com/Dr-Noob/cpufetch/blob/master/doc/DOCUMENTATION_PPC.md)
- [DOCUMENTATION_X86.md](https://github.com/Dr-Noob/cpufetch/blob/master/doc/DOCUMENTATION_X86.md)
- [DOCUMENTATION_ARM.md](https://github.com/Dr-Noob/cpufetch/blob/master/doc/DOCUMENTATION_ARM.md)

Binary file not shown.

Before

Width:  |  Height:  |  Size: 192 KiB

BIN
pictures/cascade_lake.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 42 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 76 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 62 KiB

After

Width:  |  Height:  |  Size: 33 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.7 MiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 268 KiB

BIN
pictures/exynos.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 44 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 32 KiB

After

Width:  |  Height:  |  Size: 34 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 47 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 162 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 107 KiB

View File

@@ -4,19 +4,8 @@
#include <assert.h>
#include <stdbool.h>
#include <errno.h>
#ifdef __linux__
#include <sys/auxv.h>
#include <asm/hwcap.h>
#elif defined __APPLE__ || __MACH__
#include "sysctl.h"
// From Linux kernel: arch/arm64/include/asm/cputype.h
#define MIDR_APPLE_M1_ICESTORM 0x610F0220
#define MIDR_APPLE_M1_FIRESTORM 0x610F0230
#ifndef CPUFAMILY_ARM_FIRESTORM_ICESTORM
#define CPUFAMILY_ARM_FIRESTORM_ICESTORM 0x1B588BB3
#endif
#endif
#include <sys/auxv.h>
#include <asm/hwcap.h>
#include "../common/global.h"
#include "udev.h"
@@ -24,12 +13,29 @@
#include "uarch.h"
#include "soc.h"
bool cores_are_equal(int c1pos, int c2pos, uint32_t* midr_array, int32_t* freq_array) {
return midr_array[c1pos] == midr_array[c2pos] && freq_array[c1pos] == freq_array[c2pos];
#define STRING_UNKNOWN "Unknown"
void init_cache_struct(struct cache* cach) {
cach->L1i = malloc(sizeof(struct cach));
cach->L1d = malloc(sizeof(struct cach));
cach->L2 = malloc(sizeof(struct cach));
cach->L3 = malloc(sizeof(struct cach));
cach->cach_arr = malloc(sizeof(struct cach*) * 4);
cach->cach_arr[0] = cach->L1i;
cach->cach_arr[1] = cach->L1d;
cach->cach_arr[2] = cach->L2;
cach->cach_arr[3] = cach->L3;
cach->max_cache_level = 0;
cach->L1i->exists = false;
cach->L1d->exists = false;
cach->L2->exists = false;
cach->L3->exists = false;
}
struct cache* get_cache_info(struct cpuInfo* cpu) {
struct cache* cach = emalloc(sizeof(struct cache));
struct cache* cach = malloc(sizeof(struct cache));
init_cache_struct(cach);
cach->max_cache_level = 2;
@@ -43,17 +49,19 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
}
struct frequency* get_frequency_info(uint32_t core) {
struct frequency* freq = emalloc(sizeof(struct frequency));
struct frequency* freq = malloc(sizeof(struct frequency));
freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(core);
freq->base = UNKNOWN_FREQ;
freq->max = get_max_freq_from_file(core, false);
return freq;
}
struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, uint32_t* midr_array, int32_t* freq_array, int socket_idx, int ncores) {
struct topology* topo = emalloc(sizeof(struct topology));
init_topology_struct(topo, cach);
struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, uint32_t* midr_array, int socket_idx, int ncores) {
struct topology* topo = malloc(sizeof(struct topology));
topo->cach = cach;
topo->total_cores = 0;
int sockets_seen = 0;
int first_core_idx = 0;
@@ -61,7 +69,7 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, uint
int cores_in_socket = 0;
while(socket_idx + 1 > sockets_seen) {
if(currrent_core_idx < ncores && cores_are_equal(first_core_idx, currrent_core_idx, midr_array, freq_array)) {
if(midr_array[first_core_idx] == midr_array[currrent_core_idx] && currrent_core_idx < ncores) {
currrent_core_idx++;
cores_in_socket++;
}
@@ -76,25 +84,8 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, uint
return topo;
}
int64_t get_peak_performance(struct cpuInfo* cpu) {
struct cpuInfo* ptr = cpu;
//First check we have consistent data
for(int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
if(get_freq(ptr->freq) == UNKNOWN_DATA) {
return -1;
}
}
int64_t flops = 0;
ptr = cpu;
for(int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
flops += ptr->topo->total_cores * (get_freq(ptr->freq) * 1000000);
}
if(cpu->feat->NEON) flops = flops * 4;
return flops;
bool cores_are_equal(int c1pos, int c2pos, uint32_t* midr_array, int32_t* freq_array) {
return midr_array[c1pos] == midr_array[c2pos] && freq_array[c1pos] == freq_array[c2pos];
}
uint32_t fill_ids_from_midr(uint32_t* midr_array, int32_t* freq_array, uint32_t* ids_array, int len) {
@@ -137,13 +128,12 @@ void init_cpu_info(struct cpuInfo* cpu) {
// ARM32 https://elixir.bootlin.com/linux/latest/source/arch/arm/include/uapi/asm/hwcap.h
// ARM64 https://elixir.bootlin.com/linux/latest/source/arch/arm64/include/uapi/asm/hwcap.h
struct features* get_features_info() {
struct features* feat = emalloc(sizeof(struct features));
struct features* feat = malloc(sizeof(struct features));
bool *ptr = &(feat->AES);
for(uint32_t i = 0; i < sizeof(struct features)/sizeof(bool); i++, ptr++) {
*ptr = false;
}
#ifdef __linux__
errno = 0;
long hwcaps = getauxval(AT_HWCAP);
@@ -173,27 +163,20 @@ struct features* get_features_info() {
feat->SHA1 = hwcaps & HWCAP2_SHA1;
feat->SHA2 = hwcaps & HWCAP2_SHA2;
}
#endif // ifdef __aarch64__
#elif defined __APPLE__ || __MACH__
// Must be M1
feat->AES = true;
feat->CRC32 = true;
feat->SHA1 = true;
feat->SHA2 = true;
feat->NEON = true;
#endif // ifdef __linux__
#endif
return feat;
}
#ifdef __linux__
struct cpuInfo* get_cpu_info_linux(struct cpuInfo* cpu) {
struct cpuInfo* get_cpu_info() {
struct cpuInfo* cpu = malloc(sizeof(struct cpuInfo));
init_cpu_info(cpu);
int ncores = get_ncores_from_cpuinfo();
bool success = false;
int32_t* freq_array = emalloc(sizeof(uint32_t) * ncores);
uint32_t* midr_array = emalloc(sizeof(uint32_t) * ncores);
uint32_t* ids_array = emalloc(sizeof(uint32_t) * ncores);
int32_t* freq_array = malloc(sizeof(uint32_t) * ncores);
uint32_t* midr_array = malloc(sizeof(uint32_t) * ncores);
uint32_t* ids_array = malloc(sizeof(uint32_t) * ncores);
for(int i=0; i < ncores; i++) {
midr_array[i] = get_midr_from_cpuinfo(i, &success);
@@ -203,8 +186,8 @@ struct cpuInfo* get_cpu_info_linux(struct cpuInfo* cpu) {
midr_array[i] = midr_array[0];
}
freq_array[i] = get_max_freq_from_file(i);
if(freq_array[i] == UNKNOWN_DATA) {
freq_array[i] = get_max_freq_from_file(i, false);
if(freq_array[i] == UNKNOWN_FREQ) {
printWarn("Unable to fetch max frequency for core %d. This is probably because the core is offline", i);
freq_array[i] = freq_array[0];
}
@@ -216,7 +199,7 @@ struct cpuInfo* get_cpu_info_linux(struct cpuInfo* cpu) {
int tmp_midr_idx = 0;
for(uint32_t i=0; i < sockets; i++) {
if(i > 0) {
ptr->next_cpu = emalloc(sizeof(struct cpuInfo));
ptr->next_cpu = malloc(sizeof(struct cpuInfo));
ptr = ptr->next_cpu;
init_cpu_info(ptr);
@@ -231,98 +214,62 @@ struct cpuInfo* get_cpu_info_linux(struct cpuInfo* cpu) {
ptr->feat = get_features_info();
ptr->freq = get_frequency_info(midr_idx);
ptr->cach = get_cache_info(ptr);
ptr->topo = get_topology_info(ptr, ptr->cach, midr_array, freq_array, i, ncores);
ptr->topo = get_topology_info(ptr, ptr->cach, midr_array, i, ncores);
}
cpu->num_cpus = sockets;
cpu->hv = emalloc(sizeof(struct hypervisor));
cpu->hv = malloc(sizeof(struct hypervisor));
cpu->hv->present = false;
cpu->soc = get_soc();
cpu->peak_performance = get_peak_performance(cpu);
return cpu;
}
#elif defined __APPLE__ || __MACH__
void fill_cpu_info_firestorm_icestorm(struct cpuInfo* cpu) {
// 1. Fill ICESTORM
struct cpuInfo* ice = cpu;
ice->midr = MIDR_APPLE_M1_ICESTORM;
ice->arch = get_uarch_from_midr(ice->midr, ice);
ice->cach = get_cache_info(ice);
ice->feat = get_features_info();
ice->topo = malloc(sizeof(struct topology));
ice->topo->cach = ice->cach;
ice->topo->total_cores = 4;
ice->freq = malloc(sizeof(struct frequency));
ice->freq->base = UNKNOWN_DATA;
ice->freq->max = 2064;
ice->hv = malloc(sizeof(struct hypervisor));
ice->hv->present = false;
ice->next_cpu = malloc(sizeof(struct cpuInfo));
// 2. Fill FIRESTORM
struct cpuInfo* fire = ice->next_cpu;
fire->midr = MIDR_APPLE_M1_FIRESTORM;
fire->arch = get_uarch_from_midr(fire->midr, fire);
fire->cach = get_cache_info(fire);
fire->feat = get_features_info();
fire->topo = malloc(sizeof(struct topology));
fire->topo->cach = fire->cach;
fire->topo->total_cores = 4;
fire->freq = malloc(sizeof(struct frequency));
fire->freq->base = UNKNOWN_DATA;
fire->freq->max = 3200;
fire->hv = malloc(sizeof(struct hypervisor));
fire->hv->present = false;
fire->next_cpu = NULL;
}
struct cpuInfo* get_cpu_info_mach(struct cpuInfo* cpu) {
uint32_t cpu_family = get_sys_info_by_name("hw.cpufamily");
// Manually fill the cpuInfo assuming that the CPU
// is a ARM_FIRESTORM_ICESTORM (Apple M1)
if(cpu_family == CPUFAMILY_ARM_FIRESTORM_ICESTORM) {
cpu->num_cpus = 2;
cpu->soc = get_soc();
fill_cpu_info_firestorm_icestorm(cpu);
cpu->peak_performance = get_peak_performance(cpu);
}
else {
printBug("Found invalid cpu_family: 0x%.8X", cpu_family);
return NULL;
}
return cpu;
}
#endif
struct cpuInfo* get_cpu_info() {
struct cpuInfo* cpu = malloc(sizeof(struct cpuInfo));
init_cpu_info(cpu);
#ifdef __linux__
return get_cpu_info_linux(cpu);
#elif defined __APPLE__ || __MACH__
return get_cpu_info_mach(cpu);
#endif
}
char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_socket) {
uint32_t size = 3+7+1;
char* string = emalloc(sizeof(char)*size);
char* string = malloc(sizeof(char)*size);
snprintf(string, size, "%d cores", topo->total_cores);
return string;
}
char* get_str_peak_performance(struct cpuInfo* cpu) {
//7 for GFLOP/s and 6 for digits,eg 412.14
uint32_t size = 7+6+1+1;
assert(strlen(STRING_UNKNOWN)+1 <= size);
char* string = malloc(sizeof(char)*size);
struct cpuInfo* ptr = cpu;
//First check we have consistent data
for(int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
if(get_freq(ptr->freq) == UNKNOWN_FREQ) {
snprintf(string, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
return string;
}
}
double flops = 0.0;
ptr = cpu;
for(int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
flops += ptr->topo->total_cores * (get_freq(ptr->freq) * 1000000);
}
if(cpu->feat->NEON) flops = flops * 4;
if(flops >= (double)1000000000000.0)
snprintf(string,size,"%.2f TFLOP/s",flops/1000000000000);
else if(flops >= 1000000000.0)
snprintf(string,size,"%.2f GFLOP/s",flops/1000000000);
else
snprintf(string,size,"%.2f MFLOP/s",flops/1000000);
return string;
}
char* get_str_features(struct cpuInfo* cpu) {
struct features* feat = cpu->feat;
uint32_t max_len = strlen("NEON,SHA1,SHA2,AES,CRC32,") + 1;
char* string = malloc(sizeof(char) * 25);
uint32_t len = 0;
char* string = ecalloc(max_len, sizeof(char));
if(feat->NEON) {
strcat(string, "NEON,");
@@ -359,7 +306,7 @@ void print_debug(struct cpuInfo* cpu) {
for(int i=0; i < ncores; i++) {
printf("[Core %d] ", i);
long freq = get_max_freq_from_file(i);
long freq = get_max_freq_from_file(i, false);
uint32_t midr = get_midr_from_cpuinfo(i, &success);
if(!success) {
printWarn("Unable to fetch MIDR for core %d. This is probably because the core is offline", i);
@@ -368,9 +315,9 @@ void print_debug(struct cpuInfo* cpu) {
else {
printf("0x%.8X ", midr);
}
if(freq == UNKNOWN_DATA) {
if(freq == UNKNOWN_FREQ) {
printWarn("Unable to fetch max frequency for core %d. This is probably because the core is offline", i);
printf("%ld MHz\n", get_max_freq_from_file(0));
printf("%ld MHz\n", get_max_freq_from_file(0, false));
}
else {
printf("%ld MHz\n", freq);

View File

@@ -7,6 +7,7 @@ struct cpuInfo* get_cpu_info();
uint32_t get_nsockets(struct topology* topo);
char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_socket);
char* get_str_peak_performance(struct cpuInfo* cpu);
char* get_str_features(struct cpuInfo* cpu);
void print_debug(struct cpuInfo* cpu);

View File

@@ -9,7 +9,7 @@
#include "../common/global.h"
#define min(a,b) (((a)<(b))?(a):(b))
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
#define STRING_UNKNOWN "Unknown"
static char* soc_trademark_string[] = {
[SOC_VENDOR_SNAPDRAGON] = "Snapdragon ",
@@ -17,14 +17,6 @@ static char* soc_trademark_string[] = {
[SOC_VENDOR_EXYNOS] = "Exynos ",
[SOC_VENDOR_KIRIN] = "Kirin ",
[SOC_VENDOR_BROADCOM] = "Broadcom BCM",
[SOC_VENDOR_APPLE] = "Apple "
};
static char* soc_rpi_string[] = {
"BCM2835",
"BCM2836",
"BCM2837",
"BCM2711"
};
void fill_soc(struct system_on_chip* soc, char* soc_name, SOC soc_model, int32_t process) {
@@ -32,7 +24,7 @@ void fill_soc(struct system_on_chip* soc, char* soc_name, SOC soc_model, int32_t
soc->soc_vendor = get_soc_vendor_from_soc(soc_model);
soc->process = process;
int len = strlen(soc_name) + strlen(soc_trademark_string[soc->soc_vendor]) + 1;
soc->soc_name = emalloc(sizeof(char) * len);
soc->soc_name = malloc(sizeof(char) * len);
memset(soc->soc_name, 0, sizeof(char) * len);
sprintf(soc->soc_name, "%s%s", soc_trademark_string[soc->soc_vendor], soc_name);
}
@@ -53,7 +45,7 @@ bool match_soc(struct system_on_chip* soc, char* raw_name, char* expected_name,
char* toupperstr(char* str) {
int len = strlen(str) + 1;
char* ret = emalloc(sizeof(char) * len);
char* ret = malloc(sizeof(char) * len);
memset(ret, 0, sizeof(char) * len);
for(int i=0; i < len; i++) {
@@ -67,12 +59,6 @@ char* toupperstr(char* str) {
#define SOC_EQ(raw_name, expected_name, soc_name, soc_model, soc, process) \
else if (match_soc(soc, raw_name, expected_name, soc_name, soc_model, process)) return true;
#define SOC_END else { return false; }
// Exynos special define
#define SOC_EXY_EQ(raw_name, tmpsoc, soc_name, soc_model, soc, process) \
sprintf(tmpsoc, "exynos%s", soc_name); \
if (match_soc(soc, raw_name, tmpsoc, soc_name, soc_model, process)) return true; \
sprintf(tmpsoc, "universal%s", soc_name); \
if (match_soc(soc, raw_name, tmpsoc, soc_name, soc_model, process)) return true;
// https://en.wikipedia.org/wiki/Raspberry_Pi
// http://phonedb.net/index.php?m=processor&id=562&c=broadcom_bcm21663
@@ -144,68 +130,56 @@ bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
bool match_exynos(char* soc_name, struct system_on_chip* soc) {
char* tmp;
if((tmp = strstr(soc_name, "universal")) != NULL);
else if((tmp = strstr(soc_name, "exynos")) != NULL);
else return false;
// Because exynos are recently using "exynosXXXX" instead
// of "universalXXXX" as codenames, SOC_EXY_EQ will check for
// both cases, since it seems that there are some SoCs that
// can appear with both codenames
// Used by SOC_EXY_EQ
char tmpsoc[14];
if((tmp = strstr(soc_name, "universal")) == NULL)
return false;
SOC_START
SOC_EXY_EQ(tmp, tmpsoc, "3475", SOC_EXYNOS_3475, soc, 28)
SOC_EXY_EQ(tmp, tmpsoc, "4210", SOC_EXYNOS_4210, soc, 45)
SOC_EXY_EQ(tmp, tmpsoc, "4212", SOC_EXYNOS_4212, soc, 32)
SOC_EXY_EQ(tmp, tmpsoc, "4412", SOC_EXYNOS_4412, soc, 32)
SOC_EXY_EQ(tmp, tmpsoc, "5250", SOC_EXYNOS_5250, soc, 32)
SOC_EXY_EQ(tmp, tmpsoc, "5410", SOC_EXYNOS_5410, soc, 28)
SOC_EXY_EQ(tmp, tmpsoc, "5420", SOC_EXYNOS_5420, soc, 28)
SOC_EXY_EQ(tmp, tmpsoc, "5422", SOC_EXYNOS_5422, soc, 28)
SOC_EXY_EQ(tmp, tmpsoc, "5430", SOC_EXYNOS_5430, soc, 20)
SOC_EXY_EQ(tmp, tmpsoc, "5433", SOC_EXYNOS_5433, soc, 20)
SOC_EXY_EQ(tmp, tmpsoc, "5260", SOC_EXYNOS_5260, soc, 28)
SOC_EXY_EQ(tmp, tmpsoc, "7270", SOC_EXYNOS_7270, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7420", SOC_EXYNOS_7420, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7570", SOC_EXYNOS_7570, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7570", SOC_EXYNOS_7570, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7870", SOC_EXYNOS_7870, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7870", SOC_EXYNOS_7870, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7872", SOC_EXYNOS_7872, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7880", SOC_EXYNOS_7880, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7884", SOC_EXYNOS_7884, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7885", SOC_EXYNOS_7885, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "7904", SOC_EXYNOS_7904, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "8890", SOC_EXYNOS_8890, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "8895", SOC_EXYNOS_8895, soc, 10)
SOC_EXY_EQ(tmp, tmpsoc, "9110", SOC_EXYNOS_9110, soc, 14)
SOC_EXY_EQ(tmp, tmpsoc, "9609", SOC_EXYNOS_9609, soc, 10)
SOC_EXY_EQ(tmp, tmpsoc, "9610", SOC_EXYNOS_9610, soc, 10)
SOC_EXY_EQ(tmp, tmpsoc, "9611", SOC_EXYNOS_9611, soc, 10)
SOC_EXY_EQ(tmp, tmpsoc, "9810", SOC_EXYNOS_9810, soc, 10)
SOC_EXY_EQ(tmp, tmpsoc, "9820", SOC_EXYNOS_9820, soc, 8)
SOC_EXY_EQ(tmp, tmpsoc, "9825", SOC_EXYNOS_9825, soc, 7)
SOC_EXY_EQ(tmp, tmpsoc, "1080", SOC_EXYNOS_1080, soc, 5)
SOC_EXY_EQ(tmp, tmpsoc, "990", SOC_EXYNOS_990, soc, 7)
SOC_EXY_EQ(tmp, tmpsoc, "980", SOC_EXYNOS_980, soc, 8)
SOC_EXY_EQ(tmp, tmpsoc, "880", SOC_EXYNOS_880, soc, 8)
// universalXXXX //
SOC_EQ(tmp, "universal3475", "3475", SOC_EXYNOS_3475, soc, 28)
SOC_EQ(tmp, "universal4210", "4210", SOC_EXYNOS_4210, soc, 45)
SOC_EQ(tmp, "universal4212", "4212", SOC_EXYNOS_4212, soc, 32)
SOC_EQ(tmp, "universal4412", "4412", SOC_EXYNOS_4412, soc, 32)
SOC_EQ(tmp, "universal5250", "5250", SOC_EXYNOS_5250, soc, 32)
SOC_EQ(tmp, "universal5410", "5410", SOC_EXYNOS_5410, soc, 28)
SOC_EQ(tmp, "universal5420", "5420", SOC_EXYNOS_5420, soc, 28)
SOC_EQ(tmp, "universal5422", "5422", SOC_EXYNOS_5422, soc, 28)
SOC_EQ(tmp, "universal5430", "5430", SOC_EXYNOS_5430, soc, 20)
SOC_EQ(tmp, "universal5433", "5433", SOC_EXYNOS_5433, soc, 20)
SOC_EQ(tmp, "universal5260", "5260", SOC_EXYNOS_5260, soc, 28)
SOC_EQ(tmp, "universal7270", "7270", SOC_EXYNOS_7270, soc, 14)
SOC_EQ(tmp, "universal7420", "7420", SOC_EXYNOS_7420, soc, 14)
SOC_EQ(tmp, "universal7570", "7570", SOC_EXYNOS_7570, soc, 14)
SOC_EQ(tmp, "universal7870", "7870", SOC_EXYNOS_7870, soc, 14)
SOC_EQ(tmp, "universal7872", "7872", SOC_EXYNOS_7872, soc, 14)
SOC_EQ(tmp, "universal7880", "7880", SOC_EXYNOS_7880, soc, 14)
SOC_EQ(tmp, "universal7884", "7884", SOC_EXYNOS_7884, soc, 14)
SOC_EQ(tmp, "universal7885", "7885", SOC_EXYNOS_7885, soc, 14)
SOC_EQ(tmp, "universal7904", "7904", SOC_EXYNOS_7904, soc, 14)
SOC_EQ(tmp, "universal8890", "8890", SOC_EXYNOS_8890, soc, 14)
SOC_EQ(tmp, "universal8895", "8895", SOC_EXYNOS_8895, soc, 10)
SOC_EQ(tmp, "universal9110", "9110", SOC_EXYNOS_9110, soc, 14)
SOC_EQ(tmp, "universal9609", "9609", SOC_EXYNOS_9609, soc, 10)
SOC_EQ(tmp, "universal9610", "9610", SOC_EXYNOS_9610, soc, 10)
SOC_EQ(tmp, "universal9611", "9611", SOC_EXYNOS_9611, soc, 10)
SOC_EQ(tmp, "universal9810", "9810", SOC_EXYNOS_9810, soc, 10)
SOC_EQ(tmp, "universal9820", "9820", SOC_EXYNOS_9820, soc, 8)
SOC_EQ(tmp, "universal9825", "9825", SOC_EXYNOS_9825, soc, 7)
// New exynos. Dont know if they will work //
SOC_EQ(tmp, "universal1080", "1080", SOC_EXYNOS_1080, soc, 5)
SOC_EQ(tmp, "universal990", "990", SOC_EXYNOS_990, soc, 7)
SOC_EQ(tmp, "universal980", "980", SOC_EXYNOS_980, soc, 8)
SOC_EQ(tmp, "universal880", "880", SOC_EXYNOS_880, soc, 8)
SOC_END
}
bool match_mediatek(char* soc_name, struct system_on_chip* soc) {
char* tmp;
char* soc_name_upper = toupperstr(soc_name);
if((tmp = strstr(soc_name_upper, "MT")) == NULL)
if((tmp = strstr(soc_name, "MT")) == NULL)
return false;
SOC_START
// Dimensity //
SOC_EQ(tmp, "MT6893", "Dimensity 1200", SOC_MTK_MT6893, soc, 6)
SOC_EQ(tmp, "MT6891", "Dimensity 1100", SOC_MTK_MT6891, soc, 6)
SOC_EQ(tmp, "MT6889", "Dimensity 1000", SOC_MTK_MT6889, soc, 7)
SOC_EQ(tmp, "MT6885Z", "Dimensity 1000L", SOC_MTK_MT6885Z, soc, 7)
//SOC_EQ(tmp, "?", "Dimensity 700", SOC_MTK_, soc, 7)
@@ -373,7 +347,7 @@ bool match_qualcomm(char* soc_name, struct system_on_chip* soc) {
SOC_EQ(tmp, "MSM8625Q", "200", SOC_SNAPD_MSM8625Q, soc, 45)
SOC_EQ(tmp, "MSM8208", "208", SOC_SNAPD_MSM8208, soc, 28)
SOC_EQ(tmp, "MSM8905", "205", SOC_SNAPD_MSM8905, soc, 28)
SOC_EQ(tmp, "MSM8909", "210 / 212", SOC_SNAPD_MSM8909, soc, 28) // In the future, we can differentiate them using frequency
SOC_EQ(tmp, "MSM8909", "210 / 212", SOC_SNAPD_MSM8909, soc, 28) // In the future, we can differenciate them using frequency
SOC_EQ(tmp, "QM215", "215", SOC_SNAPD_QM215, soc, 28)
// Snapdragon 4XX //
SOC_EQ(tmp, "APQ8028", "400", SOC_SNAPD_APQ8028, soc, 28)
@@ -450,7 +424,6 @@ bool match_qualcomm(char* soc_name, struct system_on_chip* soc) {
SOC_EQ(tmp, "SM8250", "865", SOC_SNAPD_SM8250, soc, 7)
SOC_EQ(tmp, "SM8250-AB", "865+", SOC_SNAPD_SM8250_AB, soc, 7)
SOC_EQ(tmp, "SM8350", "888", SOC_SNAPD_SM8350, soc, 5)
SOC_EQ(tmp, "SM8350-AC", "888+", SOC_SNAPD_SM8350, soc, 5)
SOC_END
}
@@ -463,21 +436,12 @@ bool match_special(char* soc_name, struct system_on_chip* soc) {
return true;
}
// Snapdragon 730 reported as "Qualcomm Technologies, Inc. SDMMAGPIE"
if((tmp = strstr(soc_name, "SDMMAGPIE")) != NULL) {
fill_soc(soc, "730", SOC_SNAPD_SM7150_AA, 8);
return true;
}
return false;
}
struct system_on_chip* parse_soc_from_string(struct system_on_chip* soc) {
char* raw_name = soc->raw_name;
if(match_special(raw_name, soc))
return soc;
if (match_qualcomm(raw_name, soc))
return soc;
@@ -490,7 +454,11 @@ struct system_on_chip* parse_soc_from_string(struct system_on_chip* soc) {
if(match_hisilicon(raw_name, soc))
return soc;
match_broadcom(raw_name, soc);
if(match_broadcom(raw_name, soc))
return soc;
match_special(raw_name, soc);
return soc;
}
@@ -501,37 +469,26 @@ static inline int android_property_get(const char* key, char* value) {
return __system_property_get(key, value);
}
void try_parse_soc_from_string(struct system_on_chip* soc, int soc_len, char* soc_str) {
soc->raw_name = emalloc(sizeof(char) * (soc_len + 1));
strncpy(soc->raw_name, soc_str, soc_len + 1);
soc->raw_name[soc_len] = '\0';
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
parse_soc_from_string(soc);
}
struct system_on_chip* guess_soc_from_android(struct system_on_chip* soc) {
char tmp[100];
int property_len = 0;
property_len = android_property_get("ro.mediatek.platform", (char *) &tmp);
if(property_len > 0) {
try_parse_soc_from_string(soc, property_len, tmp);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property ro.mediatek.platform: %s", tmp);
else return soc;
soc->raw_name = malloc(sizeof(char) * (property_len + 1));
strncpy(soc->raw_name, tmp, property_len + 1);
soc->raw_name[property_len] = '\0';
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
return parse_soc_from_string(soc);
}
property_len = android_property_get("ro.product.board", (char *) &tmp);
if(property_len > 0) {
try_parse_soc_from_string(soc, property_len, tmp);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property ro.product.board: %s", tmp);
else return soc;
}
property_len = android_property_get("ro.board.platform", (char *) &tmp);
if(property_len > 0) {
try_parse_soc_from_string(soc, property_len, tmp);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property ro.board.platform: %s", tmp);
else return soc;
soc->raw_name = malloc(sizeof(char) * (property_len + 1));
strncpy(soc->raw_name, tmp, property_len + 1);
soc->raw_name[property_len] = '\0';
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
return parse_soc_from_string(soc);
}
return soc;
@@ -539,7 +496,7 @@ struct system_on_chip* guess_soc_from_android(struct system_on_chip* soc) {
#endif
struct system_on_chip* guess_soc_from_cpuinfo(struct system_on_chip* soc) {
char* tmp = get_hardware_from_cpuinfo();
char* tmp = get_hardware_from_cpuinfo(&strlen);
if(tmp != NULL) {
soc->raw_name = tmp;
@@ -549,70 +506,12 @@ struct system_on_chip* guess_soc_from_cpuinfo(struct system_on_chip* soc) {
return soc;
}
int hex2int(char c) {
if (c >= '0' && c <= '9')
return c - '0';
if (c >= 'A' && c <= 'F')
return c - 'A' + 10;
if (c >= 'a' && c <= 'f')
return c - 'a' + 10;
return -1;
}
// https://www.raspberrypi.org/documentation/hardware/raspberrypi/revision-codes/README.md
struct system_on_chip* guess_soc_raspbery_pi(struct system_on_chip* soc) {
char* revision = get_revision_from_cpuinfo();
if(revision == NULL) {
printWarn("[RPi] Couldn't find revision field in cpuinfo");
return soc;
}
if(strlen(revision) != 6) {
printWarn("[RPi] Found invalid RPi revision code: '%s'", revision);
return soc;
}
int arr_size = ARRAY_SIZE(soc_rpi_string);
int pppp = hex2int(revision[2]);
if(pppp == -1) {
printErr("[RPi] Found invalid RPi PPPP code: %s", revision[2]);
return soc;
}
if(pppp > arr_size) {
printErr("[RPi] Found invalid RPi PPPP code: %d while max is %d", pppp, arr_size);
return soc;
}
char* soc_raw_name = soc_rpi_string[pppp];
/*int soc_len = strlen(soc_raw_name);
soc->raw_name = emalloc(sizeof(char) * (soc_len + 1));
strncpy(soc->raw_name, soc_raw_name, soc_len + 1);*/
match_broadcom(soc_raw_name, soc);
return soc;
}
struct system_on_chip* get_soc() {
struct system_on_chip* soc = emalloc(sizeof(struct system_on_chip));
struct system_on_chip* soc = malloc(sizeof(struct system_on_chip));
soc->raw_name = NULL;
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->process = UNKNOWN;
#ifdef __linux__
bool isRPi = is_raspberry_pi();
if(isRPi) {
soc = guess_soc_raspbery_pi(soc);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
printWarn("SoC detection failed using revision code");
}
else {
return soc;
}
}
soc = guess_soc_from_cpuinfo(soc);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
if(soc->raw_name != NULL)
@@ -625,14 +524,11 @@ struct system_on_chip* get_soc() {
printWarn("SoC detection failed using Android: No string found");
else if(soc->soc_vendor == SOC_VENDOR_UNKNOWN)
printWarn("SoC detection failed using Android: Found '%s' string", soc->raw_name);
#endif // ifdef __ANDROID__
#endif
}
#elif defined __APPLE__ || __MACH__
fill_soc(soc, "M1", SOC_APPLE_M1, 5);
#endif // ifdef __linux__
if(soc->raw_name == NULL) {
soc->raw_name = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
soc->raw_name = malloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
snprintf(soc->raw_name, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
@@ -653,13 +549,14 @@ char* get_str_process(struct system_on_chip* soc) {
char* str;
if(soc->process == UNKNOWN) {
str = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
str = malloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
else {
str = emalloc(sizeof(char) * 5);
str = malloc(sizeof(char) * 5);
memset(str, 0, sizeof(char) * 5);
snprintf(str, 5, "%dnm", soc->process);
}
return str;
}

View File

@@ -12,8 +12,7 @@ enum {
SOC_VENDOR_MEDIATEK,
SOC_VENDOR_EXYNOS,
SOC_VENDOR_KIRIN,
SOC_VENDOR_BROADCOM,
SOC_VENDOR_APPLE
SOC_VENDOR_BROADCOM
};
struct system_on_chip {

View File

@@ -63,8 +63,6 @@ enum {
SOC_EXYNOS_980,
SOC_EXYNOS_880,
// Mediatek //
SOC_MTK_MT6893,
SOC_MTK_MT6891,
SOC_MTK_MT6889,
SOC_MTK_MT6885Z,
SOC_MTK_MT6853,
@@ -252,17 +250,14 @@ enum {
SOC_SNAPD_SM8250,
SOC_SNAPD_SM8250_AB,
SOC_SNAPD_SM8350,
// APPLE
SOC_APPLE_M1
};
inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
if(soc >= SOC_BCM_2835 && soc <= SOC_BCM_21654) return SOC_VENDOR_BROADCOM;
else if(soc >= SOC_HISILICON_3620 && soc <= SOC_HISILICON_3690) return SOC_VENDOR_KIRIN;
else if(soc >= SOC_EXYNOS_3475 && soc <= SOC_EXYNOS_880) return SOC_VENDOR_EXYNOS;
else if(soc >= SOC_MTK_MT6893 && soc <= SOC_MTK_MT8783) return SOC_VENDOR_MEDIATEK;
else if(soc >= SOC_MTK_MT6889 && soc <= SOC_MTK_MT8783) return SOC_VENDOR_MEDIATEK;
else if(soc >= SOC_SNAPD_QSD8650 && soc <= SOC_SNAPD_SM8350) return SOC_VENDOR_SNAPDRAGON;
else if(soc >= SOC_APPLE_M1 && soc <= SOC_APPLE_M1) return SOC_VENDOR_APPLE;
return SOC_VENDOR_UNKNOWN;
}

View File

@@ -1,25 +0,0 @@
#include <sys/types.h>
#include <sys/sysctl.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include "../common/global.h"
#include "../common/cpu.h"
uint32_t get_sys_info_by_name(char* name) {
size_t size = 0;
uint32_t ret = 0;
if (sysctlbyname(name, NULL, &size, NULL, 0) != 0) {
printWarn("sysctlbyname(%s) failed: %s", name, strerror(errno));
}
else if (size == sizeof(uint32_t)) {
sysctlbyname(name, &ret, &size, NULL, 0);
}
else {
printWarn("sysctl does not support non-integer lookup for '%s'", name);
}
return ret;
}

View File

@@ -1,6 +0,0 @@
#ifndef __SYSCTL__
#define __SYSCTL__
uint32_t get_sys_info_by_name(char* name);
#endif

View File

@@ -7,6 +7,8 @@
#include "uarch.h"
#include "../common/global.h"
#define STRING_UNKNOWN "Unknown"
// Data not available
#define NA -1
@@ -22,17 +24,12 @@ struct uarch {
};
enum {
ISA_ARMv6,
ISA_ARMv6_T2,
ISA_ARMv6_KZ,
ISA_ARMv6_K,
ISA_ARMv7_A,
ISA_ARMv8_A,
ISA_ARMv8_A_AArch32,
ISA_ARMv8_1_A,
ISA_ARMv8_2_A,
ISA_ARMv8_3_A,
ISA_ARMv8_4_A,
};
enum {
@@ -40,10 +37,7 @@ enum {
// ARM
UARCH_ARM7,
UARCH_ARM9,
UARCH_ARM1136,
UARCH_ARM1156,
UARCH_ARM1176,
UARCH_ARM11MPCORE,
UARCH_ARM11, // ARM 1136, ARM 1156, ARM 1176, or ARM 11MPCore.
UARCH_CORTEX_A5,
UARCH_CORTEX_A7,
UARCH_CORTEX_A8,
@@ -64,7 +58,6 @@ enum {
UARCH_CORTEX_A76,
UARCH_CORTEX_A77,
UARCH_CORTEX_A78,
UARCH_CORTEX_X1,
UARCH_NEOVERSE_N1,
UARCH_NEOVERSE_E1,
UARCH_SCORPION,
@@ -93,8 +86,6 @@ enum {
UARCH_TEMPEST, // Apple A12 processor (big cores).
UARCH_LIGHTNING, // Apple A13 processor (big cores).
UARCH_THUNDER, // Apple A13 processor (little cores).
UARCH_ICESTORM, // Apple M1 processor (little cores).
UARCH_FIRESTORM, // Apple M1 processor (big cores).
// CAVIUM
UARCH_THUNDERX, // Cavium ThunderX
UARCH_THUNDERX2, // Cavium ThunderX2 (originally Broadcom Vulkan).
@@ -107,10 +98,6 @@ enum {
};
static const ISA isas_uarch[] = {
[UARCH_ARM1136] = ISA_ARMv6,
[UARCH_ARM1156] = ISA_ARMv6_T2,
[UARCH_ARM1176] = ISA_ARMv6_KZ,
[UARCH_ARM11MPCORE] = ISA_ARMv6_K,
[UARCH_CORTEX_A5] = ISA_ARMv7_A,
[UARCH_CORTEX_A7] = ISA_ARMv7_A,
[UARCH_CORTEX_A8] = ISA_ARMv7_A,
@@ -131,7 +118,6 @@ static const ISA isas_uarch[] = {
[UARCH_CORTEX_A76] = ISA_ARMv8_2_A,
[UARCH_CORTEX_A77] = ISA_ARMv8_2_A,
[UARCH_CORTEX_A78] = ISA_ARMv8_2_A,
[UARCH_CORTEX_X1] = ISA_ARMv8_2_A,
[UARCH_NEOVERSE_N1] = ISA_ARMv8_2_A,
[UARCH_NEOVERSE_E1] = ISA_ARMv8_2_A,
[UARCH_BRAHMA_B15] = ISA_ARMv7_A, // Same as Cortex-A15
@@ -153,23 +139,16 @@ static const ISA isas_uarch[] = {
[UARCH_EXYNOS_M3] = ISA_ARMv8_A,
[UARCH_EXYNOS_M4] = ISA_ARMv8_2_A,
[UARCH_EXYNOS_M5] = ISA_ARMv8_2_A,
[UARCH_ICESTORM] = ISA_ARMv8_4_A,
[UARCH_FIRESTORM] = ISA_ARMv8_4_A,
[UARCH_PJ4] = ISA_ARMv7_A,
};
static char* isas_string[] = {
[ISA_ARMv6] = "ARMv6",
[ISA_ARMv6_T2] = "ARMv6T2",
[ISA_ARMv6_KZ] = "ARMv6KZ",
[ISA_ARMv6_K] = "ARMv6K",
[ISA_ARMv7_A] = "ARMv7",
[ISA_ARMv8_A] = "ARMv8",
[ISA_ARMv8_A_AArch32] = "ARMv8 AArch32",
[ISA_ARMv8_1_A] = "ARMv8.1",
[ISA_ARMv8_2_A] = "ARMv8.2",
[ISA_ARMv8_3_A] = "ARMv8.3",
[ISA_ARMv8_4_A] = "ARMv8.4"
};
#define UARCH_START if (false) {}
@@ -182,10 +161,10 @@ void fill_uarch(struct uarch* arch, struct cpuInfo* cpu, char* str, MICROARCH u,
arch->isa = isas_uarch[arch->uarch];
cpu->cpu_vendor = vendor;
arch->uarch_str = emalloc(sizeof(char) * (strlen(str)+1));
arch->uarch_str = malloc(sizeof(char) * (strlen(str)+1));
strcpy(arch->uarch_str, str);
arch->isa_str = emalloc(sizeof(char) * (strlen(isas_string[arch->isa])+1));
arch->isa_str = malloc(sizeof(char) * (strlen(isas_string[arch->isa])+1));
strcpy(arch->isa_str, isas_string[arch->isa]);
}
@@ -197,7 +176,7 @@ void fill_uarch(struct uarch* arch, struct cpuInfo* cpu, char* str, MICROARCH u,
* - https://elixir.bootlin.com/linux/latest/source/arch/arm/include/asm/cputype.h
*/
struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
struct uarch* arch = emalloc(sizeof(struct uarch));
struct uarch* arch = malloc(sizeof(struct uarch));
uint32_t im = midr_get_implementer(midr);
uint32_t p = midr_get_part(midr);
uint32_t v = midr_get_variant(midr);
@@ -211,10 +190,6 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
// ----------------------------------------------------------------------- //
// IM P V R //
UARCH_START
CHECK_UARCH(arch, cpu, 'A', 0xB36, NA, NA, "ARM1136", UARCH_ARM1136, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xB56, NA, NA, "ARM1156", UARCH_ARM1156, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xB76, NA, NA, "ARM1176", UARCH_ARM1176, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xB02, NA, NA, "ARM11 MPCore", UARCH_ARM11MPCORE, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xC05, NA, NA, "Cortex-A5", UARCH_CORTEX_A5, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xC07, NA, NA, "Cortex-A7", UARCH_CORTEX_A7, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xC08, NA, NA, "Cortex-A8", UARCH_CORTEX_A8, CPU_VENDOR_ARM)
@@ -238,7 +213,6 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
CHECK_UARCH(arch, cpu, 'A', 0xD0D, NA, NA, "Cortex-A77", UARCH_CORTEX_A77, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD0E, NA, NA, "Cortex-A76", UARCH_CORTEX_A76, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD41, NA, NA, "Cortex-A78", UARCH_CORTEX_A78, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD44, NA, NA, "Cortex-X1", UARCH_CORTEX_X1, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4A, NA, NA, "Neoverse E1", UARCH_NEOVERSE_E1, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'B', 0x00F, NA, NA, "Brahma B15", UARCH_BRAHMA_B15, CPU_VENDOR_BROADCOM)
@@ -289,9 +263,6 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
CHECK_UARCH(arch, cpu, 'S', 0x003, 1, NA, "Exynos M4", UARCH_EXYNOS_M4, CPU_VENDOR_SAMSUNG) // Exynos 9820
CHECK_UARCH(arch, cpu, 'S', 0x004, 1, NA, "Exynos M5", UARCH_EXYNOS_M5, CPU_VENDOR_SAMSUNG) // Exynos 9820 (this one looks wrong at uarch.c ...)
CHECK_UARCH(arch, cpu, 'a', 0x022, NA, NA, "Icestorm", UARCH_ICESTORM, CPU_VENDOR_APPLE)
CHECK_UARCH(arch, cpu, 'a', 0x023, NA, NA, "Firestorm", UARCH_FIRESTORM, CPU_VENDOR_APPLE)
CHECK_UARCH(arch, cpu, 'V', 0x581, NA, NA, "PJ4", UARCH_PJ4, CPU_VENDOR_MARVELL)
CHECK_UARCH(arch, cpu, 'V', 0x584, NA, NA, "PJ4B-MP", UARCH_PJ4, CPU_VENDOR_MARVELL)
@@ -308,3 +279,4 @@ void free_uarch_struct(struct uarch* arch) {
free(arch->uarch_str);
free(arch);
}

View File

@@ -1,8 +1,7 @@
#include "../common/global.h"
#include "udev.h"
#include "midr.h"
#define _PATH_DEVICETREE_MODEL "/sys/firmware/devicetree/base/model"
#define _PATH_CPUS_PRESENT _PATH_SYS_SYSTEM _PATH_SYS_CPU "/present"
#define _PATH_CPUINFO "/proc/cpuinfo"
//#define _PATH_CPUINFO "cpuinfo_debug"
@@ -12,10 +11,42 @@
#define CPUINFO_CPU_PART_STR "CPU part\t: "
#define CPUINFO_CPU_REVISION_STR "CPU revision\t: "
#define CPUINFO_HARDWARE_STR "Hardware\t: "
#define CPUINFO_REVISION_STR "Revision\t: "
#define CPUINFO_CPU_STRING "processor"
// https://www.kernel.org/doc/html/latest/core-api/cpu_hotplug.html
int get_ncores_from_cpuinfo() {
// Examples:
// 0-271
// 0-5
// 0-7
int filelen;
char* buf;
if((buf = read_file(_PATH_CPUS_PRESENT, &filelen)) == NULL) {
perror("open");
return UNKNOWN;
}
int ncores = 0;
char* tmp1 = strstr(buf, "-") + 1;
char* tmp2 = strstr(buf, "\n");
char ncores_str[filelen];
memset(ncores_str, 0, sizeof(char) * filelen);
memcpy(ncores_str, tmp1, tmp2-tmp1);
char* end;
errno = 0;
ncores = strtol(ncores_str, &end, 10) + 1;
if(errno != 0) {
perror("strtol");
return UNKNOWN;
}
free(buf);
return ncores;
}
long parse_cpuinfo_field(char* buf, char* field_str, int field_base) {
char* tmp = strstr(buf, field_str);
if(tmp == NULL) return -1;
@@ -25,7 +56,7 @@ long parse_cpuinfo_field(char* buf, char* field_str, int field_base) {
errno = 0;
long ret = strtol(tmp, &end, field_base);
if(errno != 0) {
printWarn("strtol: %s:\n", strerror(errno));
perror("strtol");
return -1;
}
@@ -38,7 +69,7 @@ uint32_t get_midr_from_cpuinfo(uint32_t core, bool* success) {
char* buf;
*success = true;
if((buf = read_file(_PATH_CPUINFO, &filelen)) == NULL) {
printWarn("read_file: %s: %s\n", _PATH_CPUINFO, strerror(errno));
perror("open");
*success = false;
return 0;
}
@@ -65,35 +96,35 @@ uint32_t get_midr_from_cpuinfo(uint32_t core, bool* success) {
long ret;
if ((ret = parse_cpuinfo_field(tmp, CPUINFO_CPU_IMPLEMENTER_STR, 16)) < 0) {
printBug("get_midr_from_cpuinfo: Failed parsing cpu_implementer\n");
printf("Failed parsing cpu_implementer\n");
*success = false;
return 0;
}
cpu_implementer = (uint32_t) ret;
if ((ret = parse_cpuinfo_field(tmp, CPUINFO_CPU_ARCHITECTURE_STR, 10)) < 0) {
printBug("get_midr_from_cpuinfo: Failed parsing cpu_architecture\n");
printf("Failed parsing cpu_architecture\n");
*success = false;
return 0;
}
cpu_architecture = (uint32_t) 0xF; // Why?
if ((ret = parse_cpuinfo_field(tmp, CPUINFO_CPU_VARIANT_STR, 16)) < 0) {
printBug("get_midr_from_cpuinfo: Failed parsing cpu_variant\n");
printf("Failed parsing cpu_variant\n");
*success = false;
return 0;
}
cpu_variant = (uint32_t) ret;
if ((ret = parse_cpuinfo_field(tmp, CPUINFO_CPU_PART_STR, 16)) < 0) {
printBug("get_midr_from_cpuinfo: Failed parsing cpu_part\n");
printf("Failed parsing cpu_part\n");
*success = false;
return 0;
}
cpu_part = (uint32_t) ret;
if ((ret = parse_cpuinfo_field(tmp, CPUINFO_CPU_REVISION_STR, 10)) < 0) {
printBug("get_midr_from_cpuinfo: Failed parsing cpu_revision\n");
printf("Failed parsing cpu_revision\n");
*success = false;
return 0;
}
@@ -108,45 +139,24 @@ uint32_t get_midr_from_cpuinfo(uint32_t core, bool* success) {
return midr;
}
char* get_field_from_cpuinfo(char* CPUINFO_FIELD) {
char* get_hardware_from_cpuinfo() {
int filelen;
char* buf;
if((buf = read_file(_PATH_CPUINFO, &filelen)) == NULL) {
printWarn("read_file: %s: %s:\n", _PATH_CPUINFO, strerror(errno));
perror("open");
return NULL;
}
char* tmp1 = strstr(buf, CPUINFO_FIELD);
char* tmp1 = strstr(buf, CPUINFO_HARDWARE_STR);
if(tmp1 == NULL) return NULL;
tmp1 = tmp1 + strlen(CPUINFO_FIELD);
tmp1 = tmp1 + strlen(CPUINFO_HARDWARE_STR);
char* tmp2 = strstr(tmp1, "\n");
int strlen = (1 + (tmp2-tmp1));
char* hardware = emalloc(sizeof(char) * strlen);
char* hardware = malloc(sizeof(char) * strlen);
memset(hardware, 0, sizeof(char) * strlen);
strncpy(hardware, tmp1, tmp2-tmp1);
return hardware;
}
char* get_hardware_from_cpuinfo() {
return get_field_from_cpuinfo(CPUINFO_HARDWARE_STR);
}
char* get_revision_from_cpuinfo() {
return get_field_from_cpuinfo(CPUINFO_REVISION_STR);
}
bool is_raspberry_pi() {
int filelen;
char* buf;
if((buf = read_file(_PATH_DEVICETREE_MODEL, &filelen)) == NULL) {
return false;
}
char* tmp;
if((tmp = strstr(buf, "Raspberry Pi")) == NULL) {
return false;
}
return true;
}

View File

@@ -7,8 +7,6 @@
int get_ncores_from_cpuinfo();
uint32_t get_midr_from_cpuinfo(uint32_t core, bool* success);
char* get_hardware_from_cpuinfo();
char* get_revision_from_cpuinfo();
bool is_raspberry_pi();
#endif

View File

@@ -5,12 +5,8 @@
#include "args.h"
#include "global.h"
#define NUM_COLORS 5
#define COLOR_STR_INTEL "intel"
#define COLOR_STR_INTEL_NEW "intel-new"
#define COLOR_STR_AMD "amd"
#define COLOR_STR_IBM "ibm"
#define COLOR_STR_ARM "arm"
static const char *SYTLES_STR_LIST[] = {
@@ -21,52 +17,22 @@ static const char *SYTLES_STR_LIST[] = {
[STYLE_INVALID] = NULL
};
enum {
ARG_CHAR_STYLE,
ARG_CHAR_COLOR,
ARG_CHAR_HELP,
ARG_CHAR_DEBUG,
ARG_CHAR_VERBOSE,
ARG_CHAR_VERSION
};
struct args_struct {
bool debug_flag;
bool help_flag;
bool raw_flag;
bool accurate_pp;
bool full_cpu_name_flag;
bool logo_long;
bool logo_short;
bool logo_intel_new;
bool logo_intel_old;
bool verbose_flag;
bool version_flag;
STYLE style;
struct color** colors;
};
const char args_chr[] = {
/* [ARG_STYLE] = */ 's',
/* [ARG_COLOR] = */ 'c',
/* [ARG_HELP] = */ 'h',
/* [ARG_RAW] = */ 'r',
/* [ARG_FULLCPUNAME] = */ 'F',
/* [ARG_LOGO_LONG] = */ 1,
/* [ARG_LOGO_SHORT] = */ 2,
/* [ARG_LOGO_INTEL_NEW] = */ 3,
/* [ARG_LOGO_INTEL_OLD] = */ 4,
/* [ARG_ACCURATE_PP] = */ 5,
/* [ARG_DEBUG] = */ 'd',
/* [ARG_VERBOSE] = */ 'v',
/* [ARG_VERSION] = */ 'V',
};
const char *args_str[] = {
/* [ARG_STYLE] = */ "style",
/* [ARG_COLOR] = */ "color",
/* [ARG_HELP] = */ "help",
/* [ARG_RAW] = */ "raw",
/* [ARG_FULLCPUNAME] = */ "full-cpu-name",
/* [ARG_LOGO_LONG] = */ "logo-long",
/* [ARG_LOGO_SHORT] = */ "logo-short",
/* [ARG_LOGO_INTEL_NEW] = */ "logo-intel-new",
/* [ARG_LOGO_INTEL_OLD] = */ "logo-intel-old",
/* [ARG_ACCURATE_PP] = */ "accurate-pp",
/* [ARG_DEBUG] = */ "debug",
/* [ARG_VERBOSE] = */ "verbose",
/* [ARG_VERSION] = */ "version",
struct colors* colors;
};
static struct args_struct args;
@@ -75,7 +41,7 @@ STYLE get_style() {
return args.style;
}
struct color** get_colors() {
struct colors* get_colors() {
return args.colors;
}
@@ -91,47 +57,10 @@ bool show_debug() {
return args.debug_flag;
}
bool show_raw() {
return args.raw_flag;
}
bool accurate_pp() {
return args.accurate_pp;
}
bool show_full_cpu_name() {
return args.full_cpu_name_flag;
}
bool show_logo_long() {
return args.logo_long;
}
bool show_logo_short() {
return args.logo_short;
}
bool show_logo_intel_new() {
return args.logo_intel_new;
}
bool show_logo_intel_old() {
return args.logo_intel_old;
}
bool verbose_enabled() {
return args.verbose_flag;
}
int max_arg_str_length() {
int max_len = -1;
int len = sizeof(args_str) / sizeof(args_str[0]);
for(int i=0; i < len; i++) {
max_len = max(max_len, (int) strlen(args_str[i]));
}
return max_len;
}
STYLE parse_style(char* style) {
uint8_t i = 0;
uint8_t styles_count = sizeof(SYTLES_STR_LIST) / sizeof(SYTLES_STR_LIST[0]);
@@ -145,65 +74,83 @@ STYLE parse_style(char* style) {
return i;
}
void free_colors_struct(struct color** cs) {
for(int i=0; i < NUM_COLORS; i++) {
free(cs[i]);
}
void free_colors_struct(struct colors* cs) {
free(cs->c1);
free(cs->c2);
free(cs->c3);
free(cs->c4);
free(cs);
}
bool parse_color(char* optarg_str, struct color*** cs) {
for(int i=0; i < NUM_COLORS; i++) {
(*cs)[i] = emalloc(sizeof(struct color));
}
struct color** c = *cs;
bool parse_color(char* optarg_str, struct colors** cs) {
*cs = malloc(sizeof(struct colors));
(*cs)->c1 = malloc(sizeof(struct color));
(*cs)->c2 = malloc(sizeof(struct color));
(*cs)->c3 = malloc(sizeof(struct color));
(*cs)->c4 = malloc(sizeof(struct color));
struct color** c1 = &((*cs)->c1);
struct color** c2 = &((*cs)->c2);
struct color** c3 = &((*cs)->c3);
struct color** c4 = &((*cs)->c4);
int32_t ret;
char* str_to_parse = NULL;
char* color_to_copy = NULL;
bool free_ptr = true;
bool free_ptr;
if(strcmp(optarg_str, COLOR_STR_INTEL) == 0) color_to_copy = COLOR_DEFAULT_INTEL;
else if(strcmp(optarg_str, COLOR_STR_INTEL_NEW) == 0) color_to_copy = COLOR_DEFAULT_INTEL_NEW;
else if(strcmp(optarg_str, COLOR_STR_AMD) == 0) color_to_copy = COLOR_DEFAULT_AMD;
else if(strcmp(optarg_str, COLOR_STR_IBM) == 0) color_to_copy = COLOR_DEFAULT_IBM;
else if(strcmp(optarg_str, COLOR_STR_ARM) == 0) color_to_copy = COLOR_DEFAULT_ARM;
if(strcmp(optarg_str, COLOR_STR_INTEL) == 0) {
str_to_parse = malloc(sizeof(char) * 46);
strcpy(str_to_parse, COLOR_DEFAULT_INTEL);
free_ptr = true;
}
else if(strcmp(optarg_str, COLOR_STR_AMD) == 0) {
str_to_parse = malloc(sizeof(char) * 44);
strcpy(str_to_parse, COLOR_DEFAULT_AMD);
free_ptr = true;
}
else if(strcmp(optarg_str, COLOR_STR_ARM) == 0) {
str_to_parse = malloc(sizeof(char) * 46);
strcpy(str_to_parse, COLOR_DEFAULT_ARM);
free_ptr = true;
}
else {
str_to_parse = optarg_str;
free_ptr = false;
}
if(str_to_parse == NULL) {
str_to_parse = emalloc(sizeof(char) * (strlen(color_to_copy) + 1));
strcpy(str_to_parse, color_to_copy);
}
ret = sscanf(str_to_parse, "%d,%d,%d:%d,%d,%d:%d,%d,%d:%d,%d,%d",
&(*c1)->R, &(*c1)->G, &(*c1)->B,
&(*c2)->R, &(*c2)->G, &(*c2)->B,
&(*c3)->R, &(*c3)->G, &(*c3)->B,
&(*c4)->R, &(*c4)->G, &(*c4)->B);
ret = sscanf(str_to_parse, "%d,%d,%d:%d,%d,%d:%d,%d,%d:%d,%d,%d:%d,%d,%d",
&c[0]->R, &c[0]->G, &c[0]->B,
&c[1]->R, &c[1]->G, &c[1]->B,
&c[2]->R, &c[2]->G, &c[2]->B,
&c[3]->R, &c[3]->G, &c[3]->B,
&c[4]->R, &c[4]->G, &c[4]->B);
int expected_colors = 3 * NUM_COLORS;
if(ret != expected_colors) {
printErr("Expected to read %d values for color but read %d", expected_colors, ret);
if(ret != 12) {
printErr("Expected to read 12 values for color but read %d", ret);
return false;
}
for(int i=0; i < NUM_COLORS; i++) {
if(c[i]->R < 0 || c[i]->R > 255) {
printErr("Red in color %d is invalid: %d; must be in range (0, 255)", i+1, c[i]->R);
//TODO: Refactor c1->R c2->R ... to c[i]->R
if((*c1)->R < 0 || (*c1)->R > 255) {
printErr("Red in color 1 is invalid. Must be in range (0, 255)");
return false;
}
if(c[i]->G < 0 || c[i]->G > 255) {
printErr("Green in color %d is invalid: %d; must be in range (0, 255)", i+1, c[i]->G);
if((*c1)->G < 0 || (*c1)->G > 255) {
printErr("Green in color 1 is invalid. Must be in range (0, 255)");
return false;
}
if(c[i]->B < 0 || c[i]->B > 255) {
printErr("Blue in color %d is invalid: %d; must be in range (0, 255)", i+1, c[i]->B);
if((*c1)->B < 0 || (*c1)->B > 255) {
printErr("Blue in color 1 is invalid. Must be in range (0, 255)");
return false;
}
if((*c2)->R < 0 || (*c2)->R > 255) {
printErr("Red in color 2 is invalid. Must be in range (0, 255)");
return false;
}
if((*c2)->G < 0 || (*c2)->G > 255) {
printErr("Green in color 2 is invalid. Must be in range (0, 255)");
return false;
}
if((*c2)->B < 0 || (*c2)->B > 255) {
printErr("Blue in color 2 is invalid. Must be in range (0, 255)");
return false;
}
if(free_ptr) free (str_to_parse);
@@ -211,88 +158,43 @@ bool parse_color(char* optarg_str, struct color*** cs) {
return true;
}
char* build_short_options() {
const char *c = args_chr;
int len = sizeof(args_chr) / sizeof(args_chr[0]);
char* str = (char *) emalloc(sizeof(char) * (len*2 + 1));
memset(str, 0, sizeof(char) * (len*2 + 1));
#ifdef ARCH_X86
sprintf(str, "%c:%c:%c%c%c%c%c%c%c%c%c%c%c",
c[ARG_STYLE], c[ARG_COLOR], c[ARG_HELP],
c[ARG_RAW], c[ARG_FULLCPUNAME],
c[ARG_LOGO_SHORT], c[ARG_LOGO_LONG],
c[ARG_LOGO_INTEL_NEW], c[ARG_LOGO_INTEL_OLD],
c[ARG_ACCURATE_PP], c[ARG_DEBUG], c[ARG_VERBOSE],
c[ARG_VERSION]);
#else
sprintf(str, "%c:%c:%c%c%c%c%c%c",
c[ARG_STYLE], c[ARG_COLOR], c[ARG_HELP],
c[ARG_LOGO_SHORT], c[ARG_LOGO_LONG],
c[ARG_DEBUG], c[ARG_VERBOSE],
c[ARG_VERSION]);
#endif
return str;
}
bool parse_args(int argc, char* argv[]) {
int opt;
int c;
int option_index = 0;
opterr = 0;
bool color_flag = false;
args.debug_flag = false;
args.accurate_pp = false;
args.full_cpu_name_flag = false;
args.raw_flag = false;
args.verbose_flag = false;
args.logo_long = false;
args.logo_short = false;
args.logo_intel_new = false;
args.logo_intel_old = false;
args.help_flag = false;
args.style = STYLE_EMPTY;
args.colors = NULL;
// Temporary enable verbose level to allow printing warnings inside parse_args
set_log_level(true);
const struct option long_options[] = {
{args_str[ARG_STYLE], required_argument, 0, args_chr[ARG_STYLE] },
{args_str[ARG_COLOR], required_argument, 0, args_chr[ARG_COLOR] },
{args_str[ARG_HELP], no_argument, 0, args_chr[ARG_HELP] },
#ifdef ARCH_X86
{args_str[ARG_LOGO_INTEL_NEW], no_argument, 0, args_chr[ARG_LOGO_INTEL_NEW] },
{args_str[ARG_LOGO_INTEL_OLD], no_argument, 0, args_chr[ARG_LOGO_INTEL_OLD] },
{args_str[ARG_ACCURATE_PP], no_argument, 0, args_chr[ARG_ACCURATE_PP] },
{args_str[ARG_FULLCPUNAME], no_argument, 0, args_chr[ARG_FULLCPUNAME] },
{args_str[ARG_RAW], no_argument, 0, args_chr[ARG_RAW] },
#endif
{args_str[ARG_LOGO_SHORT], no_argument, 0, args_chr[ARG_LOGO_SHORT] },
{args_str[ARG_LOGO_LONG], no_argument, 0, args_chr[ARG_LOGO_LONG] },
{args_str[ARG_DEBUG], no_argument, 0, args_chr[ARG_DEBUG] },
{args_str[ARG_VERBOSE], no_argument, 0, args_chr[ARG_VERBOSE] },
{args_str[ARG_VERSION], no_argument, 0, args_chr[ARG_VERSION] },
static struct option long_options[] = {
{"style", required_argument, 0, ARG_CHAR_STYLE },
{"color", required_argument, 0, ARG_CHAR_COLOR },
{"help", no_argument, 0, ARG_CHAR_HELP },
{"debug", no_argument, 0, ARG_CHAR_DEBUG },
{"verbose", no_argument, 0, ARG_CHAR_VERBOSE },
{"version", no_argument, 0, ARG_CHAR_VERSION },
{0, 0, 0, 0}
};
char* short_options = build_short_options();
opt = getopt_long(argc, argv, short_options, long_options, &option_index);
c = getopt_long(argc, argv, "", long_options, &option_index);
while (!args.help_flag && !args.debug_flag && !args.version_flag && opt != -1) {
if(opt == args_chr[ARG_COLOR]) {
while (c != -1) {
if(c == ARG_CHAR_COLOR) {
if(color_flag) {
printErr("Color option specified more than once");
return false;
}
color_flag = true;
args.colors = emalloc(sizeof(struct color *) * NUM_COLORS);
if(!parse_color(optarg, &args.colors)) {
printErr("Color parsing failed");
return false;
}
}
else if(opt == args_chr[ARG_STYLE]) {
else if(c == ARG_CHAR_STYLE) {
if(args.style != STYLE_EMPTY) {
printErr("Style option specified more than once");
return false;
@@ -303,74 +205,55 @@ bool parse_args(int argc, char* argv[]) {
return false;
}
}
else if(opt == args_chr[ARG_HELP]) {
else if(c == ARG_CHAR_HELP) {
if(args.help_flag) {
printErr("Help option specified more than once");
return false;
}
args.help_flag = true;
}
else if(opt == args_chr[ARG_ACCURATE_PP]) {
args.accurate_pp = true;
else if(c == ARG_CHAR_VERBOSE) {
if(args.verbose_flag) {
printErr("Verbose option specified more than once");
return false;
}
else if(opt == args_chr[ARG_FULLCPUNAME]) {
args.full_cpu_name_flag = true;
}
else if(opt == args_chr[ARG_LOGO_SHORT]) {
args.logo_short = true;
}
else if(opt == args_chr[ARG_LOGO_LONG]) {
args.logo_long = true;
}
else if(opt == args_chr[ARG_LOGO_INTEL_NEW]) {
args.logo_intel_new = true;
}
else if(opt == args_chr[ARG_LOGO_INTEL_OLD]) {
args.logo_intel_old = true;
}
else if(opt == args_chr[ARG_RAW]) {
args.raw_flag = true;
}
else if(opt == args_chr[ARG_VERBOSE]) {
args.verbose_flag = true;
}
else if(opt == args_chr[ARG_DEBUG]) {
else if(c == ARG_CHAR_DEBUG) {
if(args.debug_flag) {
printErr("Debug option specified more than once");
return false;
}
args.debug_flag = true;
}
else if(opt == args_chr[ARG_VERSION]) {
else if (c == ARG_CHAR_VERSION) {
if(args.version_flag) {
printErr("Version option specified more than once");
return false;
}
args.version_flag = true;
}
else {
else if(c == '?') {
printWarn("Invalid options");
args.help_flag = true;
break;
}
else
printBug("Bug at line number %d in file %s", __LINE__, __FILE__);
option_index = 0;
opt = getopt_long(argc, argv, short_options, long_options, &option_index);
c = getopt_long(argc, argv,"",long_options, &option_index);
}
if(optind < argc) {
if (optind < argc) {
printWarn("Invalid options");
args.help_flag = true;
}
if(args.logo_intel_new && args.logo_intel_old) {
printWarn("%s and %s cannot be specified together", args_str[ARG_LOGO_INTEL_NEW], args_str[ARG_LOGO_INTEL_OLD]);
args.logo_intel_new = false;
args.logo_intel_old = false;
}
if(args.logo_short && args.logo_long) {
printWarn("%s and %s cannot be specified together", args_str[ARG_LOGO_SHORT], args_str[ARG_LOGO_LONG]);
args.logo_short = false;
args.logo_long = false;
}
#if defined(ARCH_X86) && ! defined(__linux__)
if(args.accurate_pp) {
printWarn("%s option is valid only in Linux x86_64", args_str[ARG_ACCURATE_PP]);
if((args.help_flag + args.version_flag + color_flag) > 1) {
printWarn("You should specify just one option");
args.help_flag = true;
}
#endif
// Leave log level untouched after returning
set_log_level(false);
return true;
}

View File

@@ -10,50 +10,31 @@ struct color {
int32_t B;
};
struct colors {
struct color* c1;
struct color* c2;
struct color* c3;
struct color* c4;
};
enum {
STYLE_EMPTY,
STYLE_FANCY,
STYLE_WILD,
STYLE_RETRO,
STYLE_LEGACY,
STYLE_INVALID
};
enum {
ARG_STYLE,
ARG_COLOR,
ARG_HELP,
ARG_RAW,
ARG_FULLCPUNAME,
ARG_LOGO_LONG,
ARG_LOGO_SHORT,
ARG_LOGO_INTEL_NEW,
ARG_LOGO_INTEL_OLD,
ARG_ACCURATE_PP,
ARG_DEBUG,
ARG_VERBOSE,
ARG_VERSION
};
extern const char args_chr[];
extern const char *args_str[];
#include "printer.h"
int max_arg_str_length();
bool parse_args(int argc, char* argv[]);
bool show_help();
bool accurate_pp();
bool show_full_cpu_name();
bool show_logo_long();
bool show_logo_short();
bool show_logo_intel_new();
bool show_logo_intel_old();
bool show_raw();
bool show_debug();
bool show_version();
bool verbose_enabled();
void free_colors_struct(struct color** cs);
struct color** get_colors();
void free_colors_struct(struct colors* cs);
struct colors* get_colors();
STYLE get_style();
#endif

View File

@@ -1,329 +1,208 @@
#ifndef __ASCII__
#define __ASCII__
#define COLOR_NONE ""
#define C_FG_BLACK "\x1b[30;1m"
#define C_FG_RED "\x1b[31;1m"
#define C_FG_GREEN "\x1b[32;1m"
#define C_FG_YELLOW "\x1b[33;1m"
#define C_FG_BLUE "\x1b[34;1m"
#define C_FG_MAGENTA "\x1b[35;1m"
#define C_FG_CYAN "\x1b[36;1m"
#define C_FG_WHITE "\x1b[37;1m"
#define C_BG_BLACK "\x1b[40;1m"
#define C_BG_RED "\x1b[41;1m"
#define C_BG_GREEN "\x1b[42;1m"
#define C_BG_YELLOW "\x1b[43;1m"
#define C_BG_BLUE "\x1b[44;1m"
#define C_BG_MAGENTA "\x1b[45;1m"
#define C_BG_CYAN "\x1b[46;1m"
#define C_BG_WHITE "\x1b[47;1m"
#define C_FG_B_BLACK "\x1b[90;1m"
#define C_FG_B_RED "\x1b[91;1m"
#define C_FG_B_GREEN "\x1b[92;1m"
#define C_FG_B_YELLOW "\x1b[93;1m"
#define C_FG_B_BLUE "\x1b[94;1m"
#define C_FG_B_MAGENTA "\x1b[95;1m"
#define C_FG_B_CYAN "\x1b[96;1m"
#define C_FG_B_WHITE "\x1b[97;1m"
#define COLOR_RESET "\x1b[m"
#define NUMBER_OF_LINES 19
#define LINE_SIZE 62
struct ascii_logo {
char* art;
uint32_t width;
uint32_t height;
bool replace_blocks;
char color_ascii[3][100];
char color_text[2][100];
#define AMD_ASCII \
" \
\
\
\
\
\
@@@@ @@@ @@@ @@@@@@@@ ############ \
@@@@@@ @@@@@ @@@@ @@@ @@@@ ########## \
@@@ @@@ @@@@@@@@@@@@@ @@@ @@ # #### \
@@@ @@@ @@@ @@@ @@@ @@@ @@@ ### #### \
@@@@@@@@@@@@ @@@ @@@ @@@ @@@ #### ## ### \
@@@ @@@ @@@ @@@ @@@@@@@@@ ######## ## \
\
\
\
\
\
\
"
#define INTEL_ASCII \
" ################ \
####### ####### \
#### #### \
### #### \
### ### \
### ### \
# ### ### ### \
## ### ######### ###### ###### ### ### \
## ### ### ### ### #### #### ### ### \
## ### ### ### ### ### ### ### ### \
## ### ### ### ### ########## ### #### \
## ### ### ### ### ### ### ##### \
## ## ### ### ##### ######### ## ### \
### \
### \
#### #### \
##### ########## \
########## ################ \
############################### "
#define SNAPDRAGON_ASCII \
" \
@@######## \
@@@@@########### \
@@ @@@@@################# \
@@@@@@@@@@#################### \
@@@@@@@@@@@@##################### \
@@@@@@@@@@@@@@@#################### \
@@@@@@@@@@@@@@@@@################### \
@@@@@@@@@@@@@@@@@@@@################ \
@@@@@@@@@@@@@@@@@@@@############# \
@@@@@@@@@@@@@@@@@@############ \
@ @@@@@@@@@@@@@@@########### \
@@@@@ @@@@@@@@@@@@@########## \
@@@@@@@@@ @@@@@@@@@@@@######## \
@@@@@@@@@ @@@@@@@@@@####### \
@@@@@@@@@@@@@@@@####### \
@@@@########### \
\
"
#define MEDIATEK_ASCII \
" \
\
\
\
\
\
## ## ###### ###### # ### @@@@@@ @@@@@@ @@ @@ \
### ### # # # # #### @@ @ @@ @@ \
######## # ### # # # ## ## @@ @ @@@ @@@@ \
## ### ## # # # # ## ## @@ @ @@ @@ \
## ## ## ###### ##### # ## ## @@ @@@@@@ @@ @@ \
\
\
\
\
\
\
\
"
#define EXYNOS_ASCII \
" \
\
\
\
\
\
## ## ## \
## ## \
## \
## ## \
## ## ## \
\
SAMSUNG \
Exynos \
\
\
\
\
"
#define KIRIN_ASCII \
" \
\
\
\
\
####### \
##### #################### \
###################################### \
####################################### \
####################################### \
############################## \
########################## \
######################### \
######################## \
######################## \
######################### \
######################### \
\
"
#define BROADCOM_ASCII \
" \
################ \
######################### \
############################### \
################@@@@################ \
################@@@@@@################ \
#################@@@@@@################ \
#################@@@@@@@@################# \
#################@@@@@@@@################# \
#################@@@@##@@@@################ \
################@@@@##@@@@################ \
###############@@@@####@@@@############### \
@@@@@@@@@@####@@@@####@@@@####@@@@@@@@@@ \
######@@@@@@@@@@######@@@@@@@@@@###### \
################################## \
############################## \
######################## \
############### \
"
#define ARM_ASCII \
" \
\
\
\
\
\
############ ########## #### ###### ######## \
############### ######### ####################### \
#### #### #### ##### ####### ##### \
#### #### #### #### ##### #### \
#### #### #### #### #### #### \
#### ##### #### #### #### #### \
############### #### #### #### #### \
######## #### #### #### #### #### \
\
\
\
\
"
#define UNKNOWN_ASCII \
" \
\
\
\
\
\
\
\
\
\
\
\
\
\
\
\
\
\
"
static const char* ASCII_ARRAY [] = {
AMD_ASCII,
INTEL_ASCII,
ARM_ASCII,
SNAPDRAGON_ASCII,
MEDIATEK_ASCII,
EXYNOS_ASCII,
KIRIN_ASCII,
BROADCOM_ASCII,
UNKNOWN_ASCII
};
/*
* ASCII logos brief documentation
* ----------------------------------------------------
* C1, C2, ...: ColorN, gets replaced by printer.c with
* the color in ascii_logo->color_ascii[N]
* CR: Color reset, gets replaced by the reset
* color by printer.c
*
* Logos with replace_blocks=true are replaced by character
* blocks (actually, spaces with background color), so
* the color in the structure must be C_BG_XXX. When
* replace_blocks is true, the characters '#' are replaced
* by spaces printed with color_ascii[0], and '@' are
* printed with color_ascii[1]. If replace_blocks=true,
* color format specified in ASCIIs ($C1, $C2) are ignored.
*
* In any case, '$' is a illegal character to be used in
* the ascii logos because it is used to parse colors
*
* LONG_LOGOS will be printed only if the fit in the screen,
* otherwise SHORT_LOGOS will be used
*/
// SHORT LOGOS //
#define ASCII_AMD \
"$C2 '############### \
$C2 ,############# \
$C2 .#### \
$C2 #. .#### \
$C2 :##. .#### \
$C2 :###. .#### \
$C2 #########. :## \
$C2 #######. ; \
$C1 \
$C1 ### ### ### ####### \
$C1 ## ## ##### ##### ## ## \
$C1 ## ## ### #### ### ## ## \
$C1 ######### ### ## ### ## ## \
$C1## ## ### ### ## ## \
$C1## ## ### ### ####### "
#define ASCII_INTEL \
"$C1 .#################. \
$C1 .#### ####. \
$C1 .## ### \
$C1 ## :## ### \
$C1 # ## :## ## \
$C1 ## ## ######. #### ###### :## ## \
$C1 ## ## ##: ##: ## ## ### :## ### \
$C1## ## ##: ##: ## :######## :## ## \
$C1## ## ##: ##: ## ##. . :## #### \
$C1## # ##: ##: #### #####: ## \
$C1 ## \
$C1 ###. ..o####. \
$C1 ######oo... ..oo####### \
$C1 o###############o "
#define ASCII_INTEL_NEW \
"$C1 MMM oddl MMN \
$C1 MMM dMMN MMN \
$C1 ... .... ... dMMM.. .cc. NMN \
$C1 MMM :MMMdWMMMMMX. dMMMMM, .XMMMMMMNo MMN \
$C1 MMM :MMMp dMMM dMMX .NMW WMN. MMN \
$C1 MMM :MMM WMM dMMK kMMXooooooNMMx MMN \
$C1 MMM :MMM NMM dMMK dMMX MMN \
$C1 MMM :MMM NMM dMMMoo OMM0....:Nx. MMN \
$C1 MMM :WWW XWW lONMM 'xXMMMMNOc MMN "
#define ASCII_SNAPD \
" $C1@@$C2######## \
$C1@@@@@$C2########### \
$C1@@ @@@@@$C2################# \
$C1@@@@@@@@@@$C2#################### \
$C1@@@@@@@@@@@@$C2##################### \
$C1@@@@@@@@@@@@@@@$C2#################### \
$C1@@@@@@@@@@@@@@@@@$C2################### \
$C1@@@@@@@@@@@@@@@@@@@@$C2################ \
$C1@@@@@@@@@@@@@@@@@@@@$C2############# \
$C1@@@@@@@@@@@@@@@@@@$C2############ \
$C1@ @@@@@@@@@@@@@@@$C2########### \
$C1@@@@@ @@@@@@@@@@@@@$C2########## \
$C1@@@@@@@@@ @@@@@@@@@@@@$C2######## \
$C1@@@@@@@@@ @@@@@@@@@@$C2####### \
$C1@@@@@@@@@@@@@@@@$C2####### \
$C1@@@@$C2########### "
#define ASCII_MTK \
"$C1 ## ## ###### ###### # ### $C2@@@@@@ @@@@@@ @@ @@ \
$C1 ### ### # # # # #### $C2@@ @ @@ @@ \
$C1 ######## # ### # # # ## ## $C2@@ @ @@@ @@@@ \
$C1 ## ### ## # # # # ## ## $C2@@ @ @@ @@ \
$C1## ## ## ###### ##### # ## ## $C2@@ @@@@@@ @@ @@ "
#define ASCII_EXYNOS \
"$C2 \
$C2 \
$C2 \
$C1##$CR $C1##$CR $C1##$CR \
$C1##$CR $C1##$CR \
$C1##$CR \
$C1##$CR $C1##$CR \
$C1##$CR $C1##$CR $C1##$CR \
$C2 \
$C2 SAMSUNG \
$C2 Exynos \
$C2 \
$C2 "
#define ASCII_KIRIN \
"$C1 ####### \
$C1 ##### #################### \
$C1 ###################################### \
$C1 ####################################### \
$C1 ####################################### \
$C1 ############################## \
$C1 ########################## \
$C1 ######################### \
$C1 ######################## \
$C1 ######################## \
$C1 ######################### \
$C1######################### "
#define ASCII_BROADCOM \
"$C2 \
$C2 ################ \
$C2 ########################## \
$C2 ################################ \
$C2 ################$C1@@@@$C2################ \
$C2 ################$C1@@@@@@$C2################ \
$C2 #################$C1@@@@@@$C2################# \
$C2#################$C1@@@@@@@@$C2################# \
$C2#################$C1@@@@@@@@$C2################# \
$C2################$C1@@@@$C2##$C1@@@@$C2################ \
$C2################$C1@@@@$C2##$C1@@@@$C2################ \
$C2###############$C1@@@@$C2####$C1@@@@$C2############### \
$C1 @@@@@@@@@@$C2####$C1@@@@$C2####$C1@@@@$C2####$C1@@@@@@@@@@ \
$C2 ######$C1@@@@@@@@@@$C2######$C1@@@@@@@@@@$C2###### \
$C2 ################################## \
$C2 ############################## \
$C2 ######################## \
$C2 ############### \
$C2 "
#define ASCII_ARM \
"$C1 ##### ## # ##### ## #### ###### \
$C1 ### #### ### #### ### ### \
$C1### ## ### ### ## ### \
$C1 ### #### ### ### ## ### \
$C1 ###### ## ### ### ## ### "
#define ASCII_IBM \
"$C1######## ########## ###### ###### \
$C1######## ########### ####### ####### \
$C1 #### ### #### ###### ###### \
$C1 #### ### ### ####### ####### \
$C1 #### ######## ############### \
$C1 #### ### ### #### ##### #### \
$C1 #### ### #### #### ### #### \
$C1######## ########### ###### # ###### \
$C1######## ########## ###### ###### "
// inspired by the neofetch mac logo
#define ASCII_APPLE \
"$C1 .\"c. \
$C1 ,xNMM. \
$C1 .lMM\" \
$C1 MM* \
$C1 .;loddo;:. olloddol;. \
$C1 cKMMMMMMMMMMNWMMMMMMMMMMM0: \
$C1 .KMMMMMMMMMMMMMMMMMMMMMMMW* \
$C1 XMMMMMMMMMMMMMMMMMMMMMMMX. \
$C1;MMMMMMMMMMMMMMMMMMMMMMMM: \
$C1:MMMMMMMMMMMMMMMMMMMMMMMM: \
$C1.MMMMMMMMMMMMMMMMMMMMMMMMX. \
$C1 kMMMMMMMMMMMMMMMMMMMMMMMMWd. \
$C1 'XMMMMMMMMMMMMMMMMMMMMMMMMMMk \
$C1 'XMMMMMMMMMMMMMMMMMMMMMMMMK. \
$C1 kMMMMMMMMMMMMMMMMMMMMMMd \
$C1 'KMMMMMMMWXXWMMMMMMMk. \
$C1 \"cooc\"* \"*coo'\" "
// --------------------- LONG LOGOS ------------------------- //
#define ASCII_AMD_L \
"$C1 \
$C1 \
$C1 \
$C1 \
$C1 \
$C1 \
$C1 @@@@ @@@ @@@ @@@@@@@@ $C2 ############ \
$C1 @@@@@@ @@@@@ @@@@@ @@@ @@@ $C2 ########## \
$C1 @@@ @@@ @@@@@@@@@@@@@ @@@ @@ $C2 # ##### \
$C1 @@@ @@@ @@@ @@@ @@@ @@@ @@ $C2 ### ##### \
$C1 @@@@@@@@@@@@ @@@ @@@ @@@ @@@ $C2######### ### \
$C1 @@@ @@@ @@@ @@@ @@@@@@@@@ $C2######## ## \
$C1 \
$C1 \
$C1 \
$C1 \
$C1 \
$C1 \
$C1 "
#define ASCII_INTEL_L \
"$C1 ###############@ \
$C1 ######@ ######@ \
$C1 ###@ ###@ \
$C1 ##@ ###@ \
$C1 ##@ ##@ \
$C1 ##@ ##@ \
$C1 @ ##@ ##@ ##@ \
$C1 #@ ##@ ########@ #####@ #####@ ##@ ##@ \
$C1 #@ ##@ ##@ ##@ ##@ ###@ ###@ ##@ ##@ \
$C1 #@ ##@ ##@ ##@ ##@ ##@ ##@ ##@ ##@ \
$C1 #@ ##@ ##@ ##@ ##@ #########@ ##@ ###@ \
$C1 #@ ##@ ##@ ##@ ##@ ##@ ##@ ####@ \
$C1 #@ #@ ##@ ##@ ####@ ########@ #@ ##@ \
$C1 ##@ \
$C1 ##@ \
$C1 ###@ ###@ \
$C1 ####@ #########@ \
$C1 #########@ ###############@ \
$C1 ##############################@ "
#define ASCII_INTEL_L_NEW \
" ####################################################### \
####################################################### \
####%%%#################@@@#####################@@@#### \
####%%%#################@@@#####################@@@#### \
########################@@@#####################@@@#### \
####@@@##@@@#@@@@@@@####@@@@@@####@@@@@@@@@#####@@@#### \
####@@@##@@@@@@@@@@@@###@@@@@@##@@@@#####@@@@###@@@#### \
####@@@##@@@@#####@@@@##@@@####@@@@#######@@@@##@@@#### \
####@@@##@@@#######@@@##@@@####@@@@@@@@@@@@@@@##@@@#### \
####@@@##@@@#######@@@##@@@####@@@@#############@@@#### \
####@@@##@@@#######@@@##@@@@@@##@@@@#####@@@@###@@@#### \
####@@@##@@@#######@@@###@@@@@####@@@@@@@@@#####@@@#### \
####################################################### \
####################################################### "
#define ASCII_ARM_L \
"$C1 ############ ########## #### ####### ######## \
$C1 ############### ######### ######################## \
$C1 #### #### #### ##### ######## ##### \
$C1#### #### #### #### ###### #### \
$C1#### #### #### #### #### #### \
$C1 #### ##### #### #### #### #### \
$C1 ############### #### #### #### #### \
$C1 ######## #### #### #### #### #### "
#define ASCII_IBM_L \
"$C1 ############ ################ ########## ########## \
$C1 \
$C1 ############ ################## ############ ############ \
$C1 \
$C1 ###### ###### ###### #################### \
$C1 \
$C1 ###### ############## #################### \
$C1 \
$C1 ###### ###### ###### ##### ###### ##### \
$C1 \
$C1 ############ ################## ######### #### ######### \
$C1 \
$C1 ############ ################ ######### ## ######### "
typedef struct ascii_logo asciiL;
// ------------------------------------------------------------------------------------------------------+
// | LOGO | W | H | REPLACE | COLORS LOGO (>0 && <10) | COLORS TEXT (=2) |
// ------------------------------------------------------------------------------------------------------+
asciiL logo_amd = { ASCII_AMD, 39, 15, false, {C_FG_WHITE, C_FG_GREEN}, {C_FG_WHITE, C_FG_GREEN} };
asciiL logo_intel = { ASCII_INTEL, 48, 14, false, {C_FG_CYAN}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_intel_new = { ASCII_INTEL_NEW, 51, 9, false, {C_FG_CYAN}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_snapd = { ASCII_SNAPD, 39, 16, false, {C_FG_RED, C_FG_WHITE}, {C_FG_RED, C_FG_WHITE} };
asciiL logo_mtk = { ASCII_MTK, 59, 5, false, {C_FG_BLUE, C_FG_YELLOW}, {C_FG_BLUE, C_FG_YELLOW} };
asciiL logo_exynos = { ASCII_EXYNOS, 22, 13, true, {C_BG_BLUE, C_FG_WHITE}, {C_FG_BLUE, C_FG_WHITE} };
asciiL logo_kirin = { ASCII_KIRIN, 53, 12, false, {C_FG_RED}, {C_FG_WHITE, C_FG_RED} };
asciiL logo_broadcom = { ASCII_BROADCOM, 44, 19, false, {C_FG_WHITE, C_FG_RED}, {C_FG_WHITE, C_FG_RED} };
asciiL logo_arm = { ASCII_ARM, 42, 5, false, {C_FG_CYAN}, {C_FG_WHITE, C_FG_CYAN} };
asciiL logo_ibm = { ASCII_IBM, 42, 9, false, {C_FG_CYAN, C_FG_WHITE}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_apple = { ASCII_APPLE, 32, 17, false, {C_FG_WHITE}, {C_FG_B_BLACK, C_FG_B_WHITE} };
// Long variants | ----------------------------------------------------------------------------------------------------|
asciiL logo_amd_l = { ASCII_AMD_L, 62, 19, true, {C_BG_WHITE, C_BG_GREEN}, {C_FG_WHITE, C_FG_GREEN} };
asciiL logo_intel_l = { ASCII_INTEL_L, 62, 19, true, {C_BG_CYAN, C_BG_WHITE}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_intel_l_new = { ASCII_INTEL_L_NEW, 57, 14, true, {C_BG_CYAN, C_BG_WHITE, C_BG_BLUE}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_arm_l = { ASCII_ARM_L, 60, 8, true, {C_BG_CYAN}, {C_FG_WHITE, C_FG_CYAN} };
asciiL logo_ibm_l = { ASCII_IBM_L, 62, 13, true, {C_BG_CYAN, C_FG_WHITE}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_unknown = { NULL, 0, 0, false, {COLOR_NONE}, {COLOR_NONE, COLOR_NONE} };
#endif

138
src/common/cpu.c Normal file → Executable file
View File

@@ -9,15 +9,11 @@
#ifdef ARCH_X86
#include "../x86/uarch.h"
#include "../x86/apic.h"
#elif ARCH_PPC
#include "../ppc/uarch.h"
#elif ARCH_ARM
#include "../arm/uarch.h"
#endif
#define UNUSED(x) (void)(x)
#define STRING_UNKNOWN "Unknown"
#define STRING_YES "Yes"
#define STRING_NO "No"
#define STRING_NONE "None"
@@ -34,20 +30,13 @@ int64_t get_freq(struct frequency* freq) {
return freq->max;
}
#if defined(ARCH_X86) || defined(ARCH_PPC)
char* get_str_cpu_name(struct cpuInfo* cpu, bool fcpuname) {
#ifdef ARCH_X86
if(!fcpuname) {
return get_str_cpu_name_abbreviated(cpu);
}
#elif ARCH_PPC
UNUSED(fcpuname);
#endif
#ifdef ARCH_X86
char* get_str_cpu_name(struct cpuInfo* cpu) {
return cpu->cpu_name;
}
char* get_str_sockets(struct topology* topo) {
char* string = emalloc(sizeof(char) * 2);
char* string = malloc(sizeof(char) * 2);
int32_t sanity_ret = snprintf(string, 2, "%d", topo->sockets);
if(sanity_ret < 0) {
printBug("get_str_sockets: snprintf returned a negative value for input: '%d'", topo->sockets);
@@ -62,58 +51,71 @@ uint32_t get_nsockets(struct topology* topo) {
#endif
int32_t get_value_as_smallest_unit(char ** str, uint32_t value) {
int32_t ret;
int max_len = 10; // Max is 8 for digits, 2 for units
*str = emalloc(sizeof(char)* (max_len + 1));
int32_t sanity_ret;
*str = malloc(sizeof(char)* 11); //8 for digits, 2 for units
if(value/1024 >= 1024)
ret = snprintf(*str, max_len, "%.4g"STRING_MEGABYTES, (double)value/(1<<20));
sanity_ret = snprintf(*str, 10,"%.4g"STRING_MEGABYTES, (double)value/(1<<20));
else
ret = snprintf(*str, max_len, "%.4g"STRING_KILOBYTES, (double)value/(1<<10));
sanity_ret = snprintf(*str, 10,"%.4g"STRING_KILOBYTES, (double)value/(1<<10));
return ret;
return sanity_ret;
}
// String functions
char* get_str_cache_two(int32_t cache_size, uint32_t physical_cores) {
// 4 for digits, 2 for units, 2 for ' (', 3 digits, 2 for units and 7 for ' Total)'
uint32_t max_size = 4+2 + 2 + 4+2 + 7 + 1;
int32_t sanity_ret;
char* string = malloc(sizeof(char) * max_size);
char* tmp1;
char* tmp2;
int32_t tmp1_len = get_value_as_smallest_unit(&tmp1, cache_size);
int32_t tmp2_len = get_value_as_smallest_unit(&tmp2, cache_size * physical_cores);
// tmp1_len for first output, 2 for ' (', tmp2_len for second output and 7 for ' Total)'
uint32_t size = tmp1_len + 2 + tmp2_len + 7 + 1;
char* string = emalloc(sizeof(char) * size);
if(tmp1_len < 0) {
printBug("get_value_as_smallest_unit: snprintf failed for input: %d\n", cache_size);
printBug("get_value_as_smallest_unit: snprintf returned a negative value for input: %d\n", cache_size);
return NULL;
}
if(tmp2_len < 0) {
printBug("get_value_as_smallest_unit: snprintf failed for input: %d\n", cache_size * physical_cores);
printBug("get_value_as_smallest_unit: snprintf returned a negative value for input: %d\n", cache_size * physical_cores);
return NULL;
}
if(snprintf(string, size, "%s (%s Total)", tmp1, tmp2) < 0) {
printBug("get_str_cache_two: snprintf failed for input: '%s' and '%s'\n", tmp1, tmp2);
uint32_t size = tmp1_len + 2 + tmp2_len + 7 + 1;
sanity_ret = snprintf(string, size, "%s (%s Total)", tmp1, tmp2);
if(sanity_ret < 0) {
printBug("get_str_cache_two: snprintf returned a negative value for input: '%s' and '%s'\n", tmp1, tmp2);
return NULL;
}
free(tmp1);
free(tmp2);
return string;
}
char* get_str_cache_one(int32_t cache_size) {
char* string;
int32_t str_len = get_value_as_smallest_unit(&string, cache_size);
// 4 for digits, 2 for units, 2 for ' (', 3 digits, 2 for units and 7 for ' Total)'
uint32_t max_size = 4+2 + 1;
int32_t sanity_ret;
char* string = malloc(sizeof(char) * max_size);
char* tmp;
int32_t tmp_len = get_value_as_smallest_unit(&tmp, cache_size);
if(str_len < 0) {
printBug("get_value_as_smallest_unit: snprintf failed for input: %d", cache_size);
if(tmp_len < 0) {
printBug("get_value_as_smallest_unit: snprintf returned a negative value for input: %d", cache_size);
return NULL;
}
uint32_t size = tmp_len + 1;
sanity_ret = snprintf(string, size, "%s", tmp);
if(sanity_ret < 0) {
printBug("get_str_cache_one: snprintf returned a negative value for input: '%s'", tmp);
return NULL;
}
free(tmp);
return string;
}
@@ -145,79 +147,21 @@ char* get_str_l3(struct cache* cach) {
char* get_str_freq(struct frequency* freq) {
//Max 3 digits and 3 for '(M/G)Hz' plus 1 for '\0'
uint32_t size = (5+1+3+1);
uint32_t size = (4+3+1);
assert(strlen(STRING_UNKNOWN)+1 <= size);
char* string = emalloc(sizeof(char)*size);
char* string = malloc(sizeof(char)*size);
memset(string, 0, sizeof(char)*size);
if(freq->max == UNKNOWN_DATA || freq->max < 0)
if(freq->max == UNKNOWN_FREQ || freq->max < 0)
snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN);
else if(freq->max >= 1000)
snprintf(string,size,"%.3f "STRING_GIGAHERZ,(float)(freq->max)/1000);
snprintf(string,size,"%.2f"STRING_GIGAHERZ,(float)(freq->max)/1000);
else
snprintf(string,size,"%d "STRING_MEGAHERZ,freq->max);
snprintf(string,size,"%d"STRING_MEGAHERZ,freq->max);
return string;
}
char* get_str_peak_performance(int64_t flops) {
char* str;
if(flops == -1) {
str = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1));
strncpy(str, STRING_UNKNOWN, strlen(STRING_UNKNOWN) + 1);
return str;
}
// 7 for digits (e.g, XXXX.XX), 7 for XFLOP/s
double flopsd = (double) flops;
uint32_t max_size = 7+1+7+1;
str = ecalloc(max_size, sizeof(char));
if(flopsd >= (double)1000000000000.0)
snprintf(str, max_size, "%.2f TFLOP/s", flopsd/1000000000000);
else if(flopsd >= 1000000000.0)
snprintf(str, max_size, "%.2f GFLOP/s", flopsd/1000000000);
else
snprintf(str, max_size, "%.2f MFLOP/s", flopsd/1000000);
return str;
}
void init_topology_struct(struct topology* topo, struct cache* cach) {
topo->total_cores = 0;
topo->cach = cach;
#if defined(ARCH_X86) || defined(ARCH_PPC)
topo->physical_cores = 0;
topo->logical_cores = 0;
topo->smt_supported = 0;
topo->sockets = 0;
#ifdef ARCH_X86
topo->smt_available = 0;
topo->apic = emalloc(sizeof(struct apic));
#endif
#endif
}
void init_cache_struct(struct cache* cach) {
cach->L1i = emalloc(sizeof(struct cach));
cach->L1d = emalloc(sizeof(struct cach));
cach->L2 = emalloc(sizeof(struct cach));
cach->L3 = emalloc(sizeof(struct cach));
cach->cach_arr = emalloc(sizeof(struct cach*) * 4);
cach->cach_arr[0] = cach->L1i;
cach->cach_arr[1] = cach->L1d;
cach->cach_arr[2] = cach->L2;
cach->cach_arr[3] = cach->L3;
cach->max_cache_level = 0;
cach->L1i->exists = false;
cach->L1d->exists = false;
cach->L2->exists = false;
cach->L3->exists = false;
}
void free_cache_struct(struct cache* cach) {
for(int i=0; i < 4; i++) free(cach->cach_arr[i]);
free(cach->cach_arr);

View File

@@ -10,7 +10,6 @@ enum {
CPU_VENDOR_AMD,
// ARCH_ARM
CPU_VENDOR_ARM,
CPU_VENDOR_APPLE,
CPU_VENDOR_BROADCOM,
CPU_VENDOR_CAVIUM,
CPU_VENDOR_NVIDIA,
@@ -34,7 +33,7 @@ enum {
HV_VENDOR_INVALID
};
#define UNKNOWN_DATA -1
#define UNKNOWN_FREQ -1
#define CPU_NAME_MAX_LENGTH 64
typedef int32_t VENDOR;
@@ -70,16 +69,14 @@ struct cache {
struct topology {
int32_t total_cores;
struct cache* cach;
#if defined(ARCH_X86) || defined(ARCH_PPC)
int32_t physical_cores;
int32_t logical_cores;
uint32_t sockets;
uint32_t smt_supported; // Number of SMT that CPU supports (equal to smt_available if SMT is enabled)
#ifdef ARCH_X86
uint32_t physical_cores;
uint32_t logical_cores;
uint32_t smt_available; // Number of SMT that is currently enabled
uint32_t smt_supported; // Number of SMT that CPU supports (equal to smt_available if SMT is enabled)
uint32_t sockets;
struct apic* apic;
#endif
#endif
};
struct features {
@@ -98,8 +95,6 @@ struct features {
bool FMA3;
bool FMA4;
bool SHA;
#elif ARCH_PPC
bool altivec;
#elif ARCH_ARM
bool NEON;
bool SHA1;
@@ -116,22 +111,14 @@ struct cpuInfo {
struct cache* cach;
struct topology* topo;
struct features* feat;
int64_t peak_performance;
#if defined(ARCH_X86) || defined(ARCH_PPC)
// CPU name from model
char* cpu_name;
#endif
#ifdef ARCH_X86
// CPU name from model
char* cpu_name;
// Max cpuids levels
uint32_t maxLevels;
// Max cpuids extended levels
uint32_t maxExtendedLevels;
// Topology Extensions (AMD only)
bool topology_extensions;
#elif ARCH_PPC
uint32_t pvr;
#elif ARCH_ARM
// Main ID register
uint32_t midr;
@@ -147,8 +134,8 @@ struct cpuInfo {
#endif
};
#if defined(ARCH_X86) || defined(ARCH_PPC)
char* get_str_cpu_name(struct cpuInfo* cpu, bool fcpuname);
#ifdef ARCH_X86
char* get_str_cpu_name(struct cpuInfo* cpu);
char* get_str_sockets(struct topology* topo);
uint32_t get_nsockets(struct topology* topo);
#endif
@@ -163,10 +150,6 @@ char* get_str_l1d(struct cache* cach);
char* get_str_l2(struct cache* cach);
char* get_str_l3(struct cache* cach);
char* get_str_freq(struct frequency* freq);
char* get_str_peak_performance(int64_t flops);
void init_topology_struct(struct topology* topo, struct cache* cach);
void init_cache_struct(struct cache* cach);
void free_cache_struct(struct cache* cach);
void free_freq_struct(struct frequency* freq);

View File

@@ -1,9 +1,5 @@
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include "global.h"
#ifdef _WIN32
@@ -57,10 +53,10 @@ void printBug(const char *fmt, ...) {
vsnprintf(buffer,buffer_size, fmt, args);
va_end(args);
fprintf(stderr,RED "[ERROR]: "RESET "%s\n",buffer);
#if defined(ARCH_X86) || defined(ARCH_PPC)
fprintf(stderr, "Please, create a new issue with this error message, the output of 'cpufetch' and 'cpufetch --debug' on https://github.com/Dr-Noob/cpufetch/issues\n");
#ifdef ARCH_X86
fprintf(stderr,"Please, create a new issue with this error message and the output of 'cpufetch --debug' in https://github.com/Dr-Noob/cpufetch/issues\n");
#elif ARCH_ARM
fprintf(stderr, "Please, create a new issue with this error message, your smartphone/computer model, the output of 'cpufetch' and 'cpufetch --debug' on https://github.com/Dr-Noob/cpufetch/issues\n");
fprintf(stderr,"Please, create a new issue with this error message, your smartphone/computer model and the output of 'cpufetch --debug' in https://github.com/Dr-Noob/cpufetch/issues\n");
#endif
}
@@ -68,46 +64,3 @@ void set_log_level(bool verbose) {
if(verbose) LOG_LEVEL = LOG_LEVEL_VERBOSE;
else LOG_LEVEL = LOG_LEVEL_NORMAL;
}
int max(int a, int b) {
return a > b ? a : b;
}
int min(int a, int b) {
return a < b ? a : b;
}
char *strremove(char *str, const char *sub) {
char *p, *q, *r;
if (*sub && (q = r = strstr(str, sub)) != NULL) {
size_t len = strlen(sub);
while ((r = strstr(p = r + len, sub)) != NULL) {
memmove(q, p, r - p);
q += r - p;
}
memmove(q, p, strlen(p) + 1);
}
return str;
}
void* emalloc(size_t size) {
void* ptr = malloc(size);
if(ptr == NULL) {
printErr("malloc failed: %s", strerror(errno));
exit(1);
}
return ptr;
}
void* ecalloc(size_t nmemb, size_t size) {
void* ptr = calloc(nmemb, size);
if(ptr == NULL) {
printErr("calloc failed: %s", strerror(errno));
exit(1);
}
return ptr;
}

View File

@@ -2,18 +2,10 @@
#define __GLOBAL__
#include <stdbool.h>
#include <stddef.h>
#define STRING_UNKNOWN "Unknown"
void set_log_level(bool verbose);
void printWarn(const char *fmt, ...);
void printErr(const char *fmt, ...);
void printBug(const char *fmt, ...);
int min(int a, int b);
int max(int a, int b);
char *strremove(char *str, const char *sub);
void* emalloc(size_t size);
void* ecalloc(size_t nmemb, size_t size);
#endif

View File

@@ -1,6 +1,5 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "args.h"
#include "printer.h"
@@ -9,105 +8,50 @@
#ifdef ARCH_X86
static const char* ARCH_STR = "x86_64 build";
#include "../x86/cpuid.h"
#elif ARCH_PPC
static const char* ARCH_STR = "PowerPC build";
#include "../ppc/ppc.h"
#elif ARCH_ARM
static const char* ARCH_STR = "ARM build";
#include "../arm/midr.h"
#endif
#ifdef __linux__
#ifdef __ANDROID__
static const char* OS_STR = "Android";
#else
static const char* OS_STR = "Linux";
#endif
#elif __FreeBSD__
static const char* OS_STR = "FreeBSD";
#elif _WIN32
static const char* OS_STR = "Windows";
#elif defined __APPLE__ || __MACH__
static const char* OS_STR = "macOS";
#else
static const char* OS_STR = "Unknown OS";
#endif
static const char* VERSION = "1.01";
static const char* VERSION = "0.95";
void print_help(char *argv[]) {
const char **t = args_str;
const char *c = args_chr;
int max_len = max_arg_str_length();
printf("Usage: %s [--version] [--help] [--debug] [--style \"fancy\"|\"retro\"|\"legacy\"] [--color \"intel\"|\"amd\"|'R,G,B:R,G,B:R,G,B:R,G,B']\n\n", argv[0]);
printf("Usage: %s [OPTION]...\n", argv[0]);
printf("Simple yet fancy CPU architecture fetching tool\n\n");
printf("Options: \n\
--color Set the color scheme. By default, cpufetch uses the system color scheme. This option \n\
lets the user use different colors to print the CPU art: \n\
* \"intel\": Use Intel default color scheme \n\
* \"amd\": Use AMD default color scheme \n\
* \"arm\": Use ARM default color scheme \n\
* custom: If color argument do not match \"Intel\", \"AMD\" or \"ARM\", a custom scheme can be specified: \n\
4 colors must be given in RGB with the format: R,G,B:R,G,B:... \n\
These colors correspond to CPU art color (2 colors) and for the text colors (following 2) \n\
For example: --color 239,90,45:210,200,200:100,200,45:0,200,200 \n\n\
--style Set the style of CPU art: \n\
* \"fancy\": Default style \n\
* \"retro\": Old cpufetch style \n\
* \"legacy\": Fallback style for terminals that does not support colors \n\n");
printf("OPTIONS: \n");
printf(" -%c, --%s %*s Set the color scheme (by default, cpufetch uses the system color scheme)\n", c[ARG_COLOR], t[ARG_COLOR], (int) (max_len-strlen(t[ARG_COLOR])), "");
printf(" -%c, --%s %*s Set the style of CPU logo\n", c[ARG_STYLE], t[ARG_STYLE], (int) (max_len-strlen(t[ARG_STYLE])), "");
#ifdef ARCH_X86
printf(" -%c, --%s %*s Print CPU model and cpuid levels (debug purposes)\n", c[ARG_DEBUG], t[ARG_DEBUG], (int) (max_len-strlen(t[ARG_DEBUG])), "");
#elif ARCH_PPC
printf(" -%c, --%s %*s Print PVR register (debug purposes)\n", c[ARG_DEBUG], t[ARG_DEBUG], (int) (max_len-strlen(t[ARG_DEBUG])), "");
printf(" --debug Prints CPU model and cpuid levels (debug purposes)\n\n");
#elif ARCH_ARM
printf(" -%c, --%s %*s Print main ID register values (debug purposes)\n", c[ARG_DEBUG], t[ARG_DEBUG], (int) (max_len-strlen(t[ARG_DEBUG])), "");
printf(" --debug Prints main ID register values for all cores (debug purposes)\n\n");
#endif
printf(" --%s %*s Show the short version of the logo\n", t[ARG_LOGO_SHORT], (int) (max_len-strlen(t[ARG_LOGO_SHORT])), "");
printf(" --%s %*s Show the long version of the logo\n", t[ARG_LOGO_LONG], (int) (max_len-strlen(t[ARG_LOGO_LONG])), "");
printf(" -%c, --%s %*s Print extra information (if available) about how cpufetch tried fetching information\n", c[ARG_VERBOSE], t[ARG_VERBOSE], (int) (max_len-strlen(t[ARG_VERBOSE])), "");
#ifdef ARCH_X86
#ifdef __linux__
printf(" --%s %*s Compute the peak performance accurately (measure the CPU frequency instead of using the maximum)\n", t[ARG_ACCURATE_PP], (int) (max_len-strlen(t[ARG_ACCURATE_PP])), "");
#endif
printf(" --%s %*s Show the old Intel logo\n", t[ARG_LOGO_INTEL_OLD], (int) (max_len-strlen(t[ARG_LOGO_INTEL_OLD])), "");
printf(" --%s %*s Show the new Intel logo\n", t[ARG_LOGO_INTEL_NEW], (int) (max_len-strlen(t[ARG_LOGO_INTEL_NEW])), "");
printf(" -%c, --%s %*s Show the full CPU name (do not abbreviate it)\n", c[ARG_FULLCPUNAME], t[ARG_FULLCPUNAME], (int) (max_len-strlen(t[ARG_FULLCPUNAME])), "");
printf(" -%c, --%s %*s Print raw cpuid data (debug purposes)\n", c[ARG_RAW], t[ARG_RAW], (int) (max_len-strlen(t[ARG_RAW])), "");
#endif
printf(" -%c, --%s %*s Print this help and exit\n", c[ARG_HELP], t[ARG_HELP], (int) (max_len-strlen(t[ARG_HELP])), "");
printf(" -%c, --%s %*s Print cpufetch version and exit\n", c[ARG_VERSION], t[ARG_VERSION], (int) (max_len-strlen(t[ARG_VERSION])), "");
printf("\nCOLORS: \n");
printf(" * \"intel\": Use Intel default color scheme \n");
printf(" * \"amd\": Use AMD default color scheme \n");
printf(" * \"ibm\", Use IBM default color scheme \n");
printf(" * \"arm\": Use ARM default color scheme \n");
printf(" * custom: If the argument of --color does not match any of the previous strings, a custom scheme can be specified.\n");
printf(" 5 colors must be given in RGB with the format: R,G,B:R,G,B:...\n");
printf(" The first 3 colors are the CPU art color and the next 2 colors are the text colors\n");
printf("\nSTYLES: \n");
printf(" * \"fancy\": Default style\n");
printf(" * \"retro\": Old cpufetch style\n");
printf(" * \"legacy\": Fallback style for terminals that do not support colors\n");
printf("\nLOGOS: \n");
printf(" cpufetch will try to adapt the logo size and the text to the terminal width. When the output (logo and text) is wider than\n");
printf(" the terminal width, cpufetch will print a smaller version of the logo (if it exists). This behavior can be overridden by\n");
printf(" --logo-short and --logo-long, which always sets the logo size as specified by the user, even if it is too big. After the\n");
printf(" logo selection (either automatically or set by the user), cpufetch will check again if the output fits in the terminal.\n");
printf(" If not, it will use a shorter name for the fields (the left part of the text). If, after all of this, the output still does\n");
printf(" not fit, cpufetch will cut the text and will only print the text until there is no space left in each line\n");
printf("\nEXAMPLES: \n");
printf(" Run cpufetch with Intel color scheme:\n");
printf(" ./cpufetch --color intel\n");
printf(" Run cpufetch with a custom color scheme:\n");
printf(" ./cpufetch --color 239,90,45:210,200,200:0,0,0:100,200,45:0,200,200\n");
printf("\nBUGS: \n");
printf(" Report bugs to https://github.com/Dr-Noob/cpufetch/issues\n");
printf("\nNOTE: \n");
printf(" Peak performance information is NOT accurate. cpufetch computes peak performance using the max\n");
printf(" frequency of the CPU. However, to compute the peak performance, you need to know the frequency of the\n");
printf(" CPU running AVX code. This value is not be fetched by cpufetch since it depends on each specific CPU.\n");
printf(" To correctly measure peak performance, see: https://github.com/Dr-Noob/peakperf\n");
printf(" --verbose Prints extra information (if available) about how cpufetch tried fetching information\n\n\
--help Prints this help and exit\n\n\
--version Prints cpufetch version and exit\n\n\
\n\
NOTES: \n\
- Bugs or improvements should be submitted to: github.com/Dr-Noob/cpufetch/issues \n\
- Peak performance information is NOT accurate. cpufetch computes peak performance using the max \n\
frequency. However, to properly compute peak performance, you need to know the frequency of the \n\
CPU running AVX code, which is not be fetched by cpufetch since it depends on each specific CPU. \n");
}
void print_version() {
printf("cpufetch v%s (%s %s)\n",VERSION, OS_STR, ARCH_STR);
printf("cpufetch v%s (%s) [outfile branch]\n",VERSION, ARCH_STR);
}
int main(int argc, char* argv[]) {
@@ -115,6 +59,7 @@ int main(int argc, char* argv[]) {
return EXIT_FAILURE;
if(show_help()) {
print_version();
print_help(argv);
return EXIT_SUCCESS;
}
@@ -136,19 +81,7 @@ int main(int argc, char* argv[]) {
return EXIT_SUCCESS;
}
// TODO: This should be moved to the end of args.c
if(show_raw()) {
#ifdef ARCH_X86
print_version();
print_raw(cpu);
return EXIT_SUCCESS;
#else
printErr("raw option is valid only in x86_64");
return EXIT_FAILURE;
#endif
}
if(print_cpufetch(cpu, get_style(), get_colors(), show_full_cpu_name()))
if(print_cpufetch(cpu, get_style(), get_colors()))
return EXIT_SUCCESS;
else
return EXIT_FAILURE;

File diff suppressed because it is too large Load Diff

View File

@@ -7,25 +7,18 @@ typedef int STYLE;
#ifdef ARCH_X86
#include "../x86/cpuid.h"
#elif ARCH_PPC
#include "../ppc/ppc.h"
#elif ARCH_ARM
#else
#include "../arm/midr.h"
#endif
// +-----------------------------------+-----------------------+
// | Color logo | Color text |
// | Color 1 | Color 2 | Color 3 | Color 1 | Color 2 |
#define COLOR_DEFAULT_INTEL "015,125,194:230,230,230:000,000,000:040,150,220:230,230,230"
#define COLOR_DEFAULT_INTEL_NEW "030,204,251:250,250,250:000,104,181:230,230,230:030,204,251"
#define COLOR_DEFAULT_AMD "250,250,250:000,154,102:000,000,000:250,250,250:000,154,102"
#define COLOR_DEFAULT_IBM "092,119,172:092,119,172:000,000,000:240,240,240:092,119,172"
#define COLOR_DEFAULT_ARM "000,145,189:000,145,189:000,000,000:240,240,240:000,145,189"
#define COLOR_DEFAULT_INTEL "15,125,194:230,230,230:40,150,220:230,230,230"
#define COLOR_DEFAULT_AMD "250,250,250:0,154,102:250,250,250:0,154,102"
#define COLOR_DEFAULT_ARM "0,145,189:0,145,189:240,240,240:0,145,189"
#ifdef ARCH_X86
void print_levels(struct cpuInfo* cpu);
#endif
bool print_cpufetch(struct cpuInfo* cpu, STYLE s, struct color** cs, bool fcpuname);
bool print_cpufetch(struct cpuInfo* cpu, STYLE s, struct colors* cs);
#endif

View File

@@ -2,48 +2,6 @@
#include "global.h"
#include "cpu.h"
// https://www.kernel.org/doc/html/latest/core-api/cpu_hotplug.html
int get_ncores_from_cpuinfo() {
// Examples:
// 0-271
// 0-7
// 0
int filelen;
char* buf;
if((buf = read_file(_PATH_CPUS_PRESENT, &filelen)) == NULL) {
printWarn("read_file: %s: %s\n", _PATH_CPUS_PRESENT, strerror(errno));
return -1;
}
int ncores;
char* tmp1;
if((tmp1 = strstr(buf, "-")) == NULL) {
// file contains no - character, we assume that it contains 0,
// which means that the CPU contains only one core
return 1;
}
else {
tmp1++;
}
char* tmp2 = strstr(buf, "\n");
char ncores_str[filelen];
memset(ncores_str, 0, sizeof(char) * filelen);
memcpy(ncores_str, tmp1, tmp2-tmp1);
char* end;
errno = 0;
ncores = strtol(ncores_str, &end, 10) + 1;
if(errno != 0) {
printWarn("strtol: %s:\n", strerror(errno));
return -1;
}
free(buf);
return ncores;
}
char* read_file(char* path, int* len) {
int fd = open(path, O_RDONLY);
@@ -55,7 +13,7 @@ char* read_file(char* path, int* len) {
int bytes_read = 0;
int offset = 0;
int block = 128;
char* buf = emalloc(sizeof(char)*DEFAULT_FILE_SIZE);
char* buf = malloc(sizeof(char)*DEFAULT_FILE_SIZE);
memset(buf, 0, sizeof(char)*DEFAULT_FILE_SIZE);
while ( (bytes_read = read(fd, buf+offset, block)) > 0 ) {
@@ -70,21 +28,32 @@ char* read_file(char* path, int* len) {
return buf;
}
long get_freq_from_file(char* path) {
long get_freq_from_file(char* path, bool hv_present) {
int filelen;
char* buf;
if((buf = read_file(path, &filelen)) == NULL) {
#ifdef ARCH_X86
if(hv_present) {
printWarn("Could not open '%s'", path);
return UNKNOWN_DATA;
}
else {
perror("open");
printBug("Could not open '%s'", path);
}
#elif ARCH_ARM
printWarn("Could not open '%s'", path);
#endif
return UNKNOWN_FREQ;
}
char* end;
errno = 0;
long ret = strtol(buf, &end, 10);
if(errno != 0) {
printBug("strtol: %s", strerror(errno));
perror("strtol");
printBug("Failed parsing '%s' file. Read data was: '%s'", path, buf);
free(buf);
return UNKNOWN_DATA;
return UNKNOWN_FREQ;
}
// We will be getting the frequency in KHz
@@ -92,7 +61,7 @@ long get_freq_from_file(char* path) {
// greater than 10 GHz or less than 100 MHz
if(ret > 10000 * 1000 || ret < 100 * 1000) {
printBug("Invalid data was read from file '%s': %ld\n", path, ret);
return UNKNOWN_DATA;
return UNKNOWN_FREQ;
}
free(buf);
@@ -100,139 +69,14 @@ long get_freq_from_file(char* path) {
return ret/1000;
}
long get_cache_size_from_file(char* path) {
int filelen;
char* buf;
if((buf = read_file(path, &filelen)) == NULL) {
printWarn("Could not open '%s'", path);
return -1;
}
buf[filelen] = '\0'; // remove the K at the end
char* end;
errno = 0;
long ret = strtol(buf, &end, 10);
if(errno != 0) {
printBug("strtol: %s", strerror(errno));
free(buf);
return -1;
}
free(buf);
return ret * 1024;
}
long get_max_freq_from_file(uint32_t core) {
long get_max_freq_from_file(uint32_t core, bool hv_present) {
char path[_PATH_FREQUENCY_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_FREQUENCY, _PATH_FREQUENCY_MAX);
return get_freq_from_file(path);
return get_freq_from_file(path, hv_present);
}
long get_min_freq_from_file(uint32_t core) {
long get_min_freq_from_file(uint32_t core, bool hv_present) {
char path[_PATH_FREQUENCY_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_FREQUENCY, _PATH_FREQUENCY_MIN);
return get_freq_from_file(path);
}
long get_l1i_cache_size(uint32_t core) {
char path[_PATH_CACHE_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_CACHE_L1I, _PATH_CACHE_SIZE);
return get_cache_size_from_file(path);
}
long get_l1d_cache_size(uint32_t core) {
char path[_PATH_CACHE_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_CACHE_L1D, _PATH_CACHE_SIZE);
return get_cache_size_from_file(path);
}
long get_l2_cache_size(uint32_t core) {
char path[_PATH_CACHE_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_CACHE_L2, _PATH_CACHE_SIZE);
return get_cache_size_from_file(path);
}
long get_l3_cache_size(uint32_t core) {
char path[_PATH_CACHE_MAX_LEN];
sprintf(path, "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, core, _PATH_CACHE_L3, _PATH_CACHE_SIZE);
return get_cache_size_from_file(path);
}
int get_num_caches_from_files(char** paths, int num_paths) {
int SHARED_MAP_MAX_LEN = 8 + 1;
int filelen;
char* buf;
uint32_t* shared_maps = emalloc(sizeof(uint32_t *) * num_paths);
// 1. Read cpu_shared_map from every core
for(int i=0; i < num_paths; i++) {
if((buf = read_file(paths[i], &filelen)) == NULL) {
printWarn("Could not open '%s'", paths[i]);
return -1;
}
if(filelen > SHARED_MAP_MAX_LEN) {
printBug("Shared map length is %d while the max is be %d", filelen, SHARED_MAP_MAX_LEN);
return -1;
}
char* end;
errno = 0;
long ret = strtol(buf, &end, 16);
if(errno != 0) {
printBug("strtol: %s", strerror(errno));
free(buf);
return -1;
}
shared_maps[i] = (uint32_t) ret;
}
// 2. Count number of different masks; this is the number of caches
int num_caches = 0;
bool found = false;
uint32_t* unique_shared_maps = emalloc(sizeof(uint32_t *) * num_paths);
for(int i=0; i < num_paths; i++) unique_shared_maps[i] = 0;
for(int i=0; i < num_paths; i++) {
for(int j=0; j < num_paths && !found; j++) {
if(shared_maps[i] == unique_shared_maps[j]) found = true;
}
if(!found) {
unique_shared_maps[num_caches] = shared_maps[i];
num_caches++;
}
found = false;
}
return num_caches;
}
int get_num_caches_by_level(struct cpuInfo* cpu, uint32_t level) {
char** paths = emalloc(sizeof(char *) * cpu->topo->total_cores);
char* cache_path = NULL;
if(level == 0) cache_path = _PATH_CACHE_L1I;
else if(level == 1) cache_path = _PATH_CACHE_L1D;
else if(level == 2) cache_path = _PATH_CACHE_L2;
else if(level == 3) cache_path = _PATH_CACHE_L3;
else {
printBug("Found invalid cache level to inspect: %d\n", level);
return -1;
}
for(int i=0; i < cpu->topo->total_cores; i++) {
paths[i] = emalloc(sizeof(char) * _PATH_CACHE_MAX_LEN);
sprintf(paths[i], "%s%s/cpu%d%s%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, i, cache_path, _PATH_CACHE_SHARED_MAP);
}
int ret = get_num_caches_from_files(paths, cpu->topo->total_cores);
for(int i=0; i < cpu->topo->total_cores; i++)
free(paths[i]);
free(paths);
return ret;
return get_freq_from_file(path, hv_present);
}

View File

@@ -17,26 +17,12 @@
#define _PATH_FREQUENCY "/cpufreq"
#define _PATH_FREQUENCY_MAX "/cpuinfo_max_freq"
#define _PATH_FREQUENCY_MIN "/cpuinfo_min_freq"
#define _PATH_CACHE_L1D "/cache/index0"
#define _PATH_CACHE_L1I "/cache/index1"
#define _PATH_CACHE_L2 "/cache/index2"
#define _PATH_CACHE_L3 "/cache/index3"
#define _PATH_CACHE_SIZE "/size"
#define _PATH_CACHE_SHARED_MAP "/shared_cpu_map"
#define _PATH_CPUS_PRESENT _PATH_SYS_SYSTEM _PATH_SYS_CPU "/present"
#define _PATH_FREQUENCY_MAX_LEN 100
#define _PATH_CACHE_MAX_LEN 200
#define DEFAULT_FILE_SIZE 4096
char* read_file(char* path, int* len);
long get_max_freq_from_file(uint32_t core);
long get_min_freq_from_file(uint32_t core);
long get_l1i_cache_size(uint32_t core);
long get_l1d_cache_size(uint32_t core);
long get_l2_cache_size(uint32_t core);
long get_l3_cache_size(uint32_t core);
int get_num_caches_by_level(struct cpuInfo* cpu, uint32_t level);
int get_ncores_from_cpuinfo();
long get_max_freq_from_file(uint32_t core, bool hv_present);
long get_min_freq_from_file(uint32_t core, bool hv_present);
#endif

View File

@@ -1,223 +0,0 @@
#include <stdio.h>
#include <stdlib.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <assert.h>
#include "ppc.h"
#include "uarch.h"
#include "udev.h"
#include "../common/udev.h"
#include "../common/global.h"
struct cache* get_cache_info(struct cpuInfo* cpu) {
struct cache* cach = emalloc(sizeof(struct cache));
init_cache_struct(cach);
cach->L1i->size = get_l1i_cache_size(0);
cach->L1d->size = get_l1d_cache_size(0);
cach->L2->size = get_l2_cache_size(0);
cach->L3->size = get_l3_cache_size(0);
if(cach->L1i->size > 0) {
cach->L1i->exists = true;
cach->L1i->num_caches = get_num_caches_by_level(cpu, 0);
cach->max_cache_level = 1;
}
if(cach->L1d->size > 0) {
cach->L1d->exists = true;
cach->L1d->num_caches = get_num_caches_by_level(cpu, 1);
cach->max_cache_level = 2;
}
if(cach->L2->size > 0) {
cach->L2->exists = true;
cach->L2->num_caches = get_num_caches_by_level(cpu, 2);
cach->max_cache_level = 3;
}
if(cach->L3->size > 0) {
cach->L3->exists = true;
cach->L3->num_caches = get_num_caches_by_level(cpu, 3);
cach->max_cache_level = 4;
}
return cach;
}
struct topology* get_topology_info(struct cache* cach) {
struct topology* topo = emalloc(sizeof(struct topology));
init_topology_struct(topo, cach);
// 1. Total cores detection
if((topo->total_cores = sysconf(_SC_NPROCESSORS_ONLN)) == -1) {
printWarn("sysconf(_SC_NPROCESSORS_ONLN): %s", strerror(errno));
topo->total_cores = 1; // fallback
}
// To find physical cores, we use topo->total_cores and core_ids
// To find number of sockets, we use package_ids
int* core_ids = emalloc(sizeof(int) * topo->total_cores);
int* package_ids = emalloc(sizeof(int) * topo->total_cores);
if(!fill_core_ids_from_sys(core_ids, topo->total_cores)) {
printWarn("fill_core_ids_from_sys failed, output may be incomplete/invalid");
for(int i=0; i < topo->total_cores; i++) core_ids[i] = 0;
}
if(!fill_package_ids_from_sys(package_ids, topo->total_cores)) {
printWarn("fill_package_ids_from_sys failed, output may be incomplete/invalid");
for(int i=0; i < topo->total_cores; i++) package_ids[i] = 0;
}
// 2. Socket detection
int *package_ids_count = emalloc(sizeof(int) * topo->total_cores);
for(int i=0; i < topo->total_cores; i++) {
package_ids_count[i] = 0;
}
for(int i=0; i < topo->total_cores; i++) {
package_ids_count[package_ids[i]]++;
}
for(int i=0; i < topo->total_cores; i++) {
if(package_ids_count[i] != 0) {
topo->sockets++;
}
}
// 3. Physical cores detection
int *core_ids_unified = emalloc(sizeof(int) * topo->total_cores);
for(int i=0; i < topo->total_cores; i++) {
core_ids_unified[i] = -1;
}
bool found = false;
for(int i=0; i < topo->total_cores; i++) {
for(int j=0; j < topo->total_cores && !found; j++) {
if(core_ids_unified[j] == core_ids[i]) found = true;
}
if(!found) {
core_ids_unified[topo->physical_cores] = core_ids[i];
topo->physical_cores++;
}
found = false;
}
topo->physical_cores = topo->physical_cores / topo->sockets; // only count cores on one socket
topo->logical_cores = topo->total_cores / topo->sockets; // only count threads on one socket
topo->smt_supported = topo->logical_cores / topo->physical_cores;
free(core_ids);
free(package_ids);
free(package_ids_count);
free(core_ids_unified);
return topo;
}
static inline uint32_t mfpvr() {
uint32_t pvr;
asm ("mfpvr %0"
: "=r"(pvr));
return pvr;
}
struct uarch* get_cpu_uarch(struct cpuInfo* cpu) {
return get_uarch_from_pvr(cpu->pvr);
}
struct frequency* get_frequency_info() {
struct frequency* freq = emalloc(sizeof(struct frequency));
freq->max = get_max_freq_from_file(0);
freq->base = get_min_freq_from_file(0);
return freq;
}
int64_t get_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t freq) {
/*
* Not sure about this
* PP(SP) = N_CORES * FREQUENCY * 4(If altivec)
*/
//First check we have consistent data
if(freq == UNKNOWN_DATA) {
return -1;
}
struct features* feat = cpu->feat;
int64_t flops = topo->physical_cores * topo->sockets * (freq * 1000000);
if(feat->altivec) flops = flops * 4;
// POWER9 has the concept called "slices". Each SMT4 core has two super-slices,
// and each super-slice is capable of doing two FLOPS per cycle. In the case of
// SMT8, it has 4 super-slices, thus four FLOPS per cycle.
if(is_power9(cpu->arch)) {
int threads_per_core = topo->logical_cores / topo->physical_cores;
flops = flops * (threads_per_core / 2);
}
return flops;
}
struct cpuInfo* get_cpu_info() {
struct cpuInfo* cpu = emalloc(sizeof(struct cpuInfo));
struct features* feat = emalloc(sizeof(struct features));
cpu->feat = feat;
bool *ptr = &(feat->AES);
for(uint32_t i = 0; i < sizeof(struct features)/sizeof(bool); i++, ptr++) {
*ptr = false;
}
int len;
char* path = emalloc(sizeof(char) * (strlen(_PATH_DT) + strlen(_PATH_DT_PART) + 1));
sprintf(path, "%s%s", _PATH_DT, _PATH_DT_PART);
cpu->cpu_name = read_file(path, &len);
cpu->pvr = mfpvr();
cpu->arch = get_cpu_uarch(cpu);
cpu->freq = get_frequency_info();
cpu->topo = get_topology_info(cpu->cach);
cpu->cach = get_cache_info(cpu);
feat->altivec = has_altivec(cpu->arch);
cpu->peak_performance = get_peak_performance(cpu, cpu->topo, get_freq(cpu->freq));
if(cpu->cach == NULL || cpu->topo == NULL) {
return NULL;
}
return cpu;
}
char* get_str_altivec(struct cpuInfo* cpu) {
char* string = ecalloc(4, sizeof(char));
if(cpu->feat->altivec) strcpy(string, "Yes");
else strcpy(string, "No");
return string;
}
char* get_str_topology(struct topology* topo, bool dual_socket) {
char* string;
if(topo->smt_supported > 1) {
uint32_t size = 3+3+17+1;
string = emalloc(sizeof(char)*size);
if(dual_socket)
snprintf(string, size, "%d cores (%d threads)", topo->physical_cores * topo->sockets, topo->logical_cores * topo->sockets);
else
snprintf(string, size, "%d cores (%d threads)",topo->physical_cores,topo->logical_cores);
}
else {
uint32_t size = 3+7+1;
string = emalloc(sizeof(char)*size);
if(dual_socket)
snprintf(string, size, "%d cores",topo->physical_cores * topo->sockets);
else
snprintf(string, size, "%d cores",topo->physical_cores);
}
return string;
}
void print_debug(struct cpuInfo* cpu) {
printf("PVR: 0x%.8X\n", cpu->pvr);
}

View File

@@ -1,11 +0,0 @@
#ifndef __POWERPC__
#define __POWERPC__
#include "../common/cpu.h"
struct cpuInfo* get_cpu_info();
char* get_str_altivec(struct cpuInfo* cpu);
char* get_str_topology(struct topology* topo, bool dual_socket);
void print_debug(struct cpuInfo* cpu);
#endif

View File

@@ -1,28 +0,0 @@
#!/bin/bash
# This script takes as input cputable.c from linux kernel
# and generates a valid output for cpufetch in src/ppc/uarch.c
CPUTABLE_PATH="linux-5.13.7/arch/powerpc/kernel/cputable.c"
raw_values=$(grep '\.pvr_value' "$CPUTABLE_PATH" | grep -oP "= .*," | cut -d' ' -f2 | tr -d ',')
raw_masks=$(grep '\.pvr_mask' "$CPUTABLE_PATH" | grep -oE "0x........")
raw_v_len=$(echo "$raw_values" | wc -l)
raw_m_len=$(echo "$raw_masks" | wc -l)
if [ $raw_v_len -ne $raw_m_len ]
then
echo "Lengths do not match!"
echo "values length: $raw_v_len"
echo "masks length: $raw_m_len"
exit 1
fi
IFS=$'\n' read -r -d ' ' -a values <<< "$raw_values"
IFS=$'\n' read -r -d ' ' -a masks <<< "$raw_masks"
for i in "${!values[@]}"
do
echo ' CHECK_UARCH(arch, pvr, '"${masks[i]}"', '"${values[i]}"', "POWERX", UARCH_POWERX, -1)'
done

View File

@@ -1,286 +0,0 @@
#include <stdint.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/auxv.h>
#include <errno.h>
#include "uarch.h"
#include "../common/global.h"
typedef uint32_t MICROARCH;
// Data not available
#define NA -1
// Unknown manufacturing process
#define UNK -1
enum {
UARCH_UNKNOWN,
UARCH_PPC604,
UARCH_PPCG3,
UARCH_PPCG4,
UARCH_PPC405,
UARCH_PPC603,
UARCH_PPC440,
UARCH_PPC470,
UARCH_PPC970,
UARCH_PPC970FX,
UARCH_PPC970MP,
UARCH_CELLBE,
UARCH_POWER5,
UARCH_POWER5PLUS,
UARCH_POWER6,
UARCH_POWER7,
UARCH_POWER7PLUS,
UARCH_POWER8,
UARCH_POWER9,
UARCH_POWER9_DD20,
UARCH_POWER9_DD21,
UARCH_POWER9_DD22,
UARCH_POWER9_DD23,
UARCH_POWER10,
};
struct uarch {
MICROARCH uarch;
char* uarch_str;
int32_t process; // measured in nanometers
};
#define UARCH_START if (false) {}
#define CHECK_UARCH(arch, cpu_pvr, pvr_mask, pvr_value, uarch) \
else if ((cpu_pvr & pvr_mask) == pvr_value) fill_uarch(arch, uarch);
#define UARCH_END else { printBug("Unknown microarchitecture detected: 0x%.8X", pvr); fill_uarch(arch, UARCH_UNKNOWN); }
#define FILL_START if (false) {}
#define FILL_UARCH(u, uarch, uarch_str, uarch_process) \
else if(u == uarch) { fill = true; str = uarch_str; process = uarch_process; }
#define FILL_END else { printBug("Found invalid microarchitecture: %d", u); }
void fill_uarch(struct uarch* arch, MICROARCH u) {
arch->uarch = u;
char* str = NULL;
int32_t process = UNK;
bool fill = false;
FILL_START
FILL_UARCH(arch->uarch, UARCH_UNKNOWN, STRING_UNKNOWN, UNK)
FILL_UARCH(arch->uarch, UARCH_PPC604, "PowerPC 604", 500)
FILL_UARCH(arch->uarch, UARCH_PPCG3, "PowerPC G3", UNK) // varies
FILL_UARCH(arch->uarch, UARCH_PPCG4, "PowerPC G4", UNK) // varies
FILL_UARCH(arch->uarch, UARCH_PPC405, "PowerPC 405", UNK)
FILL_UARCH(arch->uarch, UARCH_PPC603, "PowerPC 603", UNK) // varies
FILL_UARCH(arch->uarch, UARCH_PPC440, "PowerPC 440", UNK)
FILL_UARCH(arch->uarch, UARCH_PPC470, "PowerPC 470", 45) // strange...
FILL_UARCH(arch->uarch, UARCH_PPC970, "PowerPC 970", 130)
FILL_UARCH(arch->uarch, UARCH_PPC970FX, "PowerPC 970FX", 90)
FILL_UARCH(arch->uarch, UARCH_PPC970MP, "PowerPC 970MP", 90)
FILL_UARCH(arch->uarch, UARCH_CELLBE, "Cell BE", UNK) // varies depending on manufacturer
FILL_UARCH(arch->uarch, UARCH_POWER5, "POWER5", 130)
FILL_UARCH(arch->uarch, UARCH_POWER5PLUS, "POWER5+", 90)
FILL_UARCH(arch->uarch, UARCH_POWER6, "POWER6", 65)
FILL_UARCH(arch->uarch, UARCH_POWER7, "POWER7", 45)
FILL_UARCH(arch->uarch, UARCH_POWER7PLUS, "POWER7+", 32)
FILL_UARCH(arch->uarch, UARCH_POWER8, "POWER8", 22)
FILL_UARCH(arch->uarch, UARCH_POWER9, "POWER9", 14)
FILL_UARCH(arch->uarch, UARCH_POWER9_DD20, "POWER9 (DD2.0)", 14)
FILL_UARCH(arch->uarch, UARCH_POWER9_DD21, "POWER9 (DD2.1)", 14)
FILL_UARCH(arch->uarch, UARCH_POWER9_DD22, "POWER9 (DD2.2)", 14)
FILL_UARCH(arch->uarch, UARCH_POWER9_DD23, "POWER9 (DD2.3)", 14)
FILL_UARCH(arch->uarch, UARCH_POWER10, "POWER10", 7)
FILL_END
if(fill) {
arch->uarch_str = emalloc(sizeof(char) * (strlen(str)+1));
strcpy(arch->uarch_str, str);
arch->process= process;
}
}
/*
* PVR masks/values from arch/powerpc/kernel/cputable.c (Linux kernel)
* This list may be incorrect, incomplete or overly simplified,
* specially in the case of 32 bit entries
*/
struct uarch* get_uarch_from_pvr(uint32_t pvr) {
struct uarch* arch = emalloc(sizeof(struct uarch));
UARCH_START
// 64 bit
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00390000, UARCH_PPC970)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x003c0000, UARCH_PPC970FX)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x00440100, UARCH_PPC970MP)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00440000, UARCH_PPC970MP)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x003a0000, UARCH_POWER5)
CHECK_UARCH(arch, pvr, 0xffffff00, 0x003b0300, UARCH_POWER5PLUS)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x003b0000, UARCH_POWER5)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000001, UARCH_POWER5)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x003e0000, UARCH_POWER6)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000002, UARCH_POWER6)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000003, UARCH_POWER7)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000004, UARCH_POWER8)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000005, UARCH_POWER9)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x0f000006, UARCH_POWER10)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x003f0000, UARCH_POWER7)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x004A0000, UARCH_POWER7PLUS)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x004b0000, UARCH_POWER8)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x004c0000, UARCH_POWER8)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x004d0000, UARCH_POWER8)
CHECK_UARCH(arch, pvr, 0xffffefff, 0x004e0200, UARCH_POWER9_DD20)
CHECK_UARCH(arch, pvr, 0xffffefff, 0x004e0201, UARCH_POWER9_DD21)
CHECK_UARCH(arch, pvr, 0xffffefff, 0x004e0202, UARCH_POWER9_DD22)
CHECK_UARCH(arch, pvr, 0xffffefff, 0x004e0203, UARCH_POWER9_DD23)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00800000, UARCH_POWER10)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00700000, UARCH_CELLBE)
// 32 bit
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00040000, UARCH_PPC604)
CHECK_UARCH(arch, pvr, 0xfffff000, 0x00090000, UARCH_PPC604)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00090000, UARCH_PPC604)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x000a0000, UARCH_PPC604)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x00084202, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xfffffff0, 0x00080100, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xfffffff0, 0x00082200, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xfffffff0, 0x00082210, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x00083214, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xfffff0e0, 0x00087000, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xfffff000, 0x00083000, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffffff00, 0x70000100, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x70000200, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x70000000, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x70020000, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00080000, UARCH_PPCG3)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x000c1101, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x000c0000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x800c0000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x80000200, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x80000201, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x80000000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffff00, 0x80010100, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x80010200, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x80010000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x80020100, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x80020101, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x80020000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x80030000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x80040000, UARCH_PPCG4)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00030000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00060000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00070000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00810000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00820000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00830000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00840000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00850000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0x7fff0000, 0x00860000, UARCH_PPC603)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x41810000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x41610000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x40B10000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x41410000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x50910000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x51510000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x41F10000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x51210000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910007, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x1291000d, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x1291000f, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910003, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910005, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910001, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910009, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x1291000b, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff000f, 0x12910002, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x41510000, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x7ff11432, UARCH_PPC405)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x40000850, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x40000858, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x400008d3, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000ff7, 0x400008d4, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x400008db, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000ffb, 0x200008D0, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000ffb, 0x200008D8, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x40000440, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x40000481, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x50000850, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x50000851, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x50000892, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xf0000fff, 0x50000894, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xfff00fff, 0x53200891, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xfff00fff, 0x53400890, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xfff00fff, 0x53400891, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffff0006, 0x13020002, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffff0007, 0x13020004, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffff0006, 0x13020000, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffff0007, 0x13020005, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffffff00, 0x13541800, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xfffffff0, 0x12C41C80, UARCH_PPC440)
CHECK_UARCH(arch, pvr, 0xffffffff, 0x11a52080, UARCH_PPC470)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x7ff50000, UARCH_PPC470)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00050000, UARCH_PPC470)
CHECK_UARCH(arch, pvr, 0xffff0000, 0x11a50000, UARCH_PPC470)
UARCH_END
return arch;
}
bool has_altivec(struct uarch* arch) {
switch(arch->uarch) {
case UARCH_PPC970FX:
case UARCH_PPC970MP:
case UARCH_CELLBE:
case UARCH_POWER6:
case UARCH_POWER7:
case UARCH_POWER7PLUS:
case UARCH_POWER8:
case UARCH_POWER9:
case UARCH_POWER9_DD20:
case UARCH_POWER9_DD21:
case UARCH_POWER9_DD22:
case UARCH_POWER9_DD23:
case UARCH_POWER10:
return true;
default:
return false;
}
}
bool is_power9(struct uarch* arch) {
return arch->uarch == UARCH_POWER9 ||
arch->uarch == UARCH_POWER9_DD20 ||
arch->uarch == UARCH_POWER9_DD21 ||
arch->uarch == UARCH_POWER9_DD22 ||
arch->uarch == UARCH_POWER9_DD23;
}
char* get_str_uarch(struct cpuInfo* cpu) {
return cpu->arch->uarch_str;
}
char* get_str_process(struct cpuInfo* cpu) {
char* str = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
int32_t process = cpu->arch->process;
if(process == UNK) {
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
else if(process > 100) {
sprintf(str, "%.2fum", (double)process/100);
}
else if(process > 0){
sprintf(str, "%dnm", process);
}
else {
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
printBug("Found invalid process: '%d'", process);
}
return str;
}
void free_uarch_struct(struct uarch* arch) {
free(arch->uarch_str);
free(arch);
}

View File

@@ -1,16 +0,0 @@
#ifndef __UARCH__
#define __UARCH__
#include <stdint.h>
#include "ppc.h"
struct uarch;
struct uarch* get_uarch_from_pvr(uint32_t pvr);
bool has_altivec(struct uarch* arch);
bool is_power9(struct uarch* arch);
char* get_str_uarch(struct cpuInfo* cpu);
char* get_str_process(struct cpuInfo* cpu);
void free_uarch_struct(struct uarch* arch);
#endif

View File

@@ -1,40 +0,0 @@
#include <errno.h>
#include "../common/global.h"
#include "udev.h"
#define _PATH_TOPO_CORE_ID "topology/core_id"
#define _PATH_TOPO_PACKAGE_ID "topology/physical_package_id"
bool fill_array_from_sys(int *core_ids, int total_cores, char* SYS_PATH) {
int filelen;
char* buf;
char* end;
char path[128];
for(int i=0; i < total_cores; i++) {
sprintf(path, "%s%s/cpu%d/%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, i, SYS_PATH);
if((buf = read_file(path, &filelen)) == NULL) {
printWarn("fill_array_from_sys: %s: %s", path, strerror(errno));
return false;
}
errno = 0;
core_ids[i] = strtol(buf, &end, 10);
if(errno != 0) {
printWarn("fill_array_from_sys: %s:", strerror(errno));
return false;
}
free(buf);
}
return true;
}
bool fill_core_ids_from_sys(int *core_ids, int total_cores) {
return fill_array_from_sys(core_ids, total_cores, _PATH_TOPO_CORE_ID);
}
bool fill_package_ids_from_sys(int* package_ids, int total_cores) {
return fill_array_from_sys(package_ids, total_cores, _PATH_TOPO_PACKAGE_ID);
}

View File

@@ -1,11 +0,0 @@
#ifndef __UDEV_PPC__
#define __UDEV_PPC__
#include "../common/udev.h"
#define _PATH_DT "/proc/device-tree/vpd/root-node-vpd@a000/enclosure@1e00/backplane@800/processor@1000"
#define _PATH_DT_PART "/part-number"
bool fill_core_ids_from_sys(int *core_ids, int total_cores);
bool fill_package_ids_from_sys(int* package_ids, int total_cores);
#endif

View File

@@ -1,14 +1,10 @@
#ifdef _WIN32
#define NOMINMAX
#include <windows.h>
#include <windows.h>
#elif defined __linux__
#define _GNU_SOURCE
#include <sched.h>
#elif defined __FreeBSD__
#include <sys/param.h>
#include <sys/cpuset.h>
#define _GNU_SOURCE
#include <sched.h>
#elif defined __APPLE__
#define UNUSED(x) (void)(x)
#define UNUSED(x) (void)(x)
#endif
#include <stdlib.h>
@@ -16,7 +12,6 @@
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <errno.h>
#include "apic.h"
#include "cpuid_asm.h"
@@ -28,7 +23,7 @@
*/
unsigned char bit_scan_reverse(uint32_t* index, uint64_t mask) {
for(uint64_t i = (8 * sizeof(uint64_t)); i > 0; i--) {
if((mask & (1ULL << (i-1))) != 0) {
if((mask & (1LL << (i-1))) != 0) {
*index = (uint64_t) (i-1);
break;
}
@@ -80,21 +75,12 @@ bool bind_to_cpu(int cpu_id) {
HANDLE process = GetCurrentProcess();
DWORD_PTR processAffinityMask = 1 << cpu_id;
return SetProcessAffinityMask(process, processAffinityMask);
#elif defined __linux__
#else
cpu_set_t currentCPU;
CPU_ZERO(&currentCPU);
CPU_SET(cpu_id, &currentCPU);
if (sched_setaffinity (0, sizeof(currentCPU), &currentCPU) == -1) {
printWarn("sched_setaffinity: %s", strerror(errno));
return false;
}
return true;
#elif defined __FreeBSD__
cpuset_t currentCPU;
CPU_ZERO(&currentCPU);
CPU_SET(cpu_id, &currentCPU);
if(cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_TID, -1, sizeof(cpuset_t), &currentCPU) == -1) {
printWarn("cpuset_setaffinity: %s", strerror(errno));
perror("sched_setaffinity");
return false;
}
return true;
@@ -209,9 +195,9 @@ uint32_t max_apic_id_size(uint32_t** cache_id_apic, struct topology* topo) {
bool build_topo_from_apic(uint32_t* apic_pkg, uint32_t* apic_smt, uint32_t** cache_id_apic, struct topology* topo) {
uint32_t size = max_apic_id_size(cache_id_apic, topo);
uint32_t* sockets = emalloc(sizeof(uint32_t) * size);
uint32_t* smt = emalloc(sizeof(uint32_t) * size);
uint32_t* apic_id = emalloc(sizeof(uint32_t) * size);
uint32_t* sockets = malloc(sizeof(uint32_t) * size);
uint32_t* smt = malloc(sizeof(uint32_t) * size);
uint32_t* apic_id = malloc(sizeof(uint32_t) * size);
uint32_t num_caches = 0;
memset(sockets, 0, sizeof(uint32_t) * size);
@@ -313,66 +299,33 @@ bool fill_apic_ids(uint32_t* apic_ids, int n, bool x2apic_id) {
usleep(1000);
}
#else
#ifdef __linux__
// In Linux we reset the affinity; first we get the original mask
cpu_set_t original_mask;
if(sched_getaffinity(0, sizeof(original_mask), &original_mask) == -1) {
printWarn("sched_getaffinity: %s", strerror(errno));
return false;
}
#endif
for(int i=0; i < n; i++) {
if(!bind_to_cpu(i)) {
printErr("Failed binding the process to CPU %d", i);
printErr("Failed binding to CPU %d", i);
return false;
}
apic_ids[i] = get_apic_id(x2apic_id);
}
#ifdef __linux__
// With the original mask previosly retrieved, we reset the affinity
if (sched_setaffinity (0, sizeof(original_mask), &original_mask) == -1) {
printWarn("sched_setaffinity: %s", strerror(errno));
return false;
}
#endif
#endif
return true;
}
bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo) {
uint32_t apic_id;
uint32_t* apic_ids = emalloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_pkg = emalloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_core = emalloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_smt = emalloc(sizeof(uint32_t) * topo->total_cores);
uint32_t** cache_smt_id_apic = emalloc(sizeof(uint32_t*) * topo->total_cores);
uint32_t** cache_id_apic = emalloc(sizeof(uint32_t*) * topo->total_cores);
bool x2apic_id;
if(cpu->maxLevels >= 0x0000000B) {
uint32_t eax = 0x0000000B;
uint32_t ebx = 0;
uint32_t ecx = 0;
uint32_t edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
if(ebx == 0) x2apic_id = false;
else x2apic_id = true;
}
else {
x2apic_id = false;
}
uint32_t* apic_ids = malloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_pkg = malloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_core = malloc(sizeof(uint32_t) * topo->total_cores);
uint32_t* apic_smt = malloc(sizeof(uint32_t) * topo->total_cores);
uint32_t** cache_smt_id_apic = malloc(sizeof(uint32_t*) * topo->total_cores);
uint32_t** cache_id_apic = malloc(sizeof(uint32_t*) * topo->total_cores);
bool x2apic_id = cpu->maxLevels >= 0x0000000B;
for(int i=0; i < topo->total_cores; i++) {
cache_smt_id_apic[i] = emalloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
cache_id_apic[i] = emalloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
cache_smt_id_apic[i] = malloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
cache_id_apic[i] = malloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
}
topo->apic->cache_select_mask = emalloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
topo->apic->cache_id_apic = emalloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
topo->apic->cache_select_mask = malloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
topo->apic->cache_id_apic = malloc(sizeof(uint32_t) * (topo->cach->max_cache_level));
if(x2apic_id) {
if(!fill_topo_masks_x2apic(topo))

View File

@@ -17,8 +17,4 @@ struct apic {
bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo);
uint32_t is_smt_enabled_amd(struct topology* topo);
#ifndef __APPLE__
bool bind_to_cpu(int cpu_id);
#endif
#endif

560
src/x86/cpuid.c Normal file → Executable file
View File

@@ -1,5 +1,4 @@
#ifdef _WIN32
#define NOMINMAX
#include <windows.h>
#else
#include "../common/udev.h"
@@ -15,10 +14,8 @@
#include "cpuid.h"
#include "cpuid_asm.h"
#include "../common/global.h"
#include "../common/args.h"
#include "apic.h"
#include "uarch.h"
#include "freq/freq.h"
#define CPU_VENDOR_INTEL_STRING "GenuineIntel"
#define CPU_VENDOR_AMD_STRING "AuthenticAMD"
@@ -39,9 +36,11 @@ static char *hv_vendors_name[] = {
[HV_VENDOR_VMWARE] = "VMware",
[HV_VENDOR_XEN] = "Xen",
[HV_VENDOR_PARALLELS] = "Parallels",
[HV_VENDOR_INVALID] = STRING_UNKNOWN
[HV_VENDOR_INVALID] = "Unknown"
};
#define STRING_UNKNOWN "Unknown"
#define HYPERVISOR_NAME_MAX_LENGTH 17
#define MASK 0xFF
@@ -51,6 +50,36 @@ static char *hv_vendors_name[] = {
* cpuid amd: https://www.amd.com/system/files/TechDocs/25481.pdf
*/
void init_topology_struct(struct topology* topo, struct cache* cach) {
topo->total_cores = 0;
topo->physical_cores = 0;
topo->logical_cores = 0;
topo->smt_available = 0;
topo->smt_supported = 0;
topo->sockets = 0;
topo->apic = malloc(sizeof(struct apic));
topo->cach = cach;
}
void init_cache_struct(struct cache* cach) {
cach->L1i = malloc(sizeof(struct cach));
cach->L1d = malloc(sizeof(struct cach));
cach->L2 = malloc(sizeof(struct cach));
cach->L3 = malloc(sizeof(struct cach));
cach->cach_arr = malloc(sizeof(struct cach*) * 4);
cach->cach_arr[0] = cach->L1i;
cach->cach_arr[1] = cach->L1d;
cach->cach_arr[2] = cach->L2;
cach->cach_arr[3] = cach->L3;
cach->max_cache_level = 0;
cach->L1i->exists = false;
cach->L1d->exists = false;
cach->L2->exists = false;
cach->L3->exists = false;
}
void get_name_cpuid(char* name, uint32_t reg1, uint32_t reg2, uint32_t reg3) {
uint32_t c = 0;
@@ -77,7 +106,7 @@ char* get_str_cpu_name_internal() {
uint32_t edx = 0;
uint32_t c = 0;
char * name = emalloc(sizeof(char) * CPU_NAME_MAX_LENGTH);
char * name = malloc(sizeof(char) * CPU_NAME_MAX_LENGTH);
memset(name, 0, CPU_NAME_MAX_LENGTH);
for(int i=0; i < 3; i++) {
@@ -118,50 +147,6 @@ char* get_str_cpu_name_internal() {
return name;
}
bool abbreviate_intel_cpu_name(char** name) {
char* old_name = *name;
char* new_name = ecalloc(strlen(old_name) + 1, sizeof(char));
char* old_name_ptr = old_name;
char* new_name_ptr = new_name;
char* aux_ptr = NULL;
// 1. Remove "(R)"
old_name_ptr = strstr(old_name_ptr, "Intel(R)");
if(old_name_ptr == NULL) return false;
strcpy(new_name_ptr, "Intel");
new_name_ptr += strlen("Intel");
old_name_ptr += strlen("Intel(R)");
// 2. Remove "(R)" or "(TM)"
aux_ptr = strstr(old_name_ptr, "(");
if(aux_ptr == NULL) return false;
strncpy(new_name_ptr, old_name_ptr, aux_ptr-old_name_ptr);
new_name_ptr += aux_ptr-old_name_ptr;
strcpy(new_name_ptr, " ");
new_name_ptr++;
old_name_ptr = strstr(aux_ptr, ")");
if(old_name_ptr == NULL) return false;
old_name_ptr++;
while(*old_name_ptr == ' ') old_name_ptr++;
// 3. Copy the CPU name
aux_ptr = strstr(old_name_ptr, "@");
if(aux_ptr == NULL) return false;
strncpy(new_name_ptr, old_name_ptr, (aux_ptr-1)-old_name_ptr);
// 4. Remove dummy strings in Intel CPU names
strremove(new_name, " CPU");
strremove(new_name, " Dual");
strremove(new_name, " 0");
free(old_name);
*name = new_name;
return true;
}
struct uarch* get_cpu_uarch(struct cpuInfo* cpu) {
uint32_t eax = 0x00000001;
uint32_t ebx = 0;
@@ -176,66 +161,11 @@ struct uarch* get_cpu_uarch(struct cpuInfo* cpu) {
uint32_t family = (eax >> 8) & 0xF;
uint32_t efamily = (eax >> 20) & 0xFF;
return get_uarch_from_cpuid(cpu, eax, efamily, family, emodel, model, (int)stepping);
}
int64_t get_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t max_freq, bool accurate_pp) {
/*
* PP = PeakPerformance
* SP = SinglePrecision
*
* PP(SP) =
* N_CORES *
* FREQUENCY *
* 2(Two vector units) *
* 2(If cpu has fma) *
* 16(If AVX512), 8(If AVX), 4(If SSE) *
*/
int64_t freq;
#ifdef __linux__
if(accurate_pp)
freq = measure_frequency(cpu);
else
freq = max_freq;
#else
// Silence compiler warning
(void)(accurate_pp);
freq = max_freq;
#endif
//First, check we have consistent data
if(freq == UNKNOWN_DATA || topo->logical_cores == UNKNOWN_DATA) {
return -1;
}
struct features* feat = cpu->feat;
int vpus = get_number_of_vpus(cpu);
int64_t flops = topo->physical_cores * topo->sockets * (freq*1000000) * vpus;
if(feat->FMA3 || feat->FMA4)
flops = flops*2;
// Ice Lake has AVX512, but it has 1 VPU for AVX512, while
// it has 2 for AVX2. If this is a Ice Lake CPU, we are computing
// the peak performance supposing AVX2, not AVX512
if(feat->AVX512 && vpus_are_AVX512(cpu))
flops = flops*16;
else if(feat->AVX || feat->AVX2)
flops = flops*8;
else if(feat->SSE)
flops = flops*4;
// See https://sites.utexas.edu/jdm4372/2018/01/22/a-peculiar-
// throughput-limitation-on-intels-xeon-phi-x200-knights-landing/
if(is_knights_landing(cpu))
flops = flops * 6 / 7;
return flops;
return get_uarch_from_cpuid(cpu, efamily, family, emodel, model, (int)stepping);
}
struct hypervisor* get_hp_info(bool hv_present) {
struct hypervisor* hv = emalloc(sizeof(struct hypervisor));
struct hypervisor* hv = malloc(sizeof(struct hypervisor));
if(!hv_present) {
hv->present = false;
return hv;
@@ -275,8 +205,8 @@ struct hypervisor* get_hp_info(bool hv_present) {
}
struct cpuInfo* get_cpu_info() {
struct cpuInfo* cpu = emalloc(sizeof(struct cpuInfo));
struct features* feat = emalloc(sizeof(struct features));
struct cpuInfo* cpu = malloc(sizeof(struct cpuInfo));
struct features* feat = malloc(sizeof(struct features));
cpu->feat = feat;
bool *ptr = &(feat->AES);
@@ -320,20 +250,20 @@ struct cpuInfo* get_cpu_info() {
if (cpu->maxLevels >= 0x00000001){
eax = 0x00000001;
cpuid(&eax, &ebx, &ecx, &edx);
feat->SSE = (edx & (1U << 25)) != 0;
feat->SSE2 = (edx & (1U << 26)) != 0;
feat->SSE3 = (ecx & (1U << 0)) != 0;
feat->SSE = (edx & ((int)1 << 25)) != 0;
feat->SSE2 = (edx & ((int)1 << 26)) != 0;
feat->SSE3 = (ecx & ((int)1 << 0)) != 0;
feat->SSSE3 = (ecx & (1U << 9)) != 0;
feat->SSE4_1 = (ecx & (1U << 19)) != 0;
feat->SSE4_2 = (ecx & (1U << 20)) != 0;
feat->SSSE3 = (ecx & ((int)1 << 9)) != 0;
feat->SSE4_1 = (ecx & ((int)1 << 19)) != 0;
feat->SSE4_2 = (ecx & ((int)1 << 20)) != 0;
feat->AES = (ecx & (1U << 25)) != 0;
feat->AES = (ecx & ((int)1 << 25)) != 0;
feat->AVX = (ecx & (1U << 28)) != 0;
feat->FMA3 = (ecx & (1U << 12)) != 0;
feat->AVX = (ecx & ((int)1 << 28)) != 0;
feat->FMA3 = (ecx & ((int)1 << 12)) != 0;
bool hv_present = (ecx & (1U << 31)) != 0;
bool hv_present = (ecx & ((int)1 << 31)) != 0;
if((cpu->hv = get_hp_info(hv_present)) == NULL)
return NULL;
}
@@ -345,16 +275,16 @@ struct cpuInfo* get_cpu_info() {
eax = 0x00000007;
ecx = 0x00000000;
cpuid(&eax, &ebx, &ecx, &edx);
feat->AVX2 = (ebx & (1U << 5)) != 0;
feat->SHA = (ebx & (1U << 29)) != 0;
feat->AVX512 = (((ebx & (1U << 16)) != 0) ||
((ebx & (1U << 28)) != 0) ||
((ebx & (1U << 26)) != 0) ||
((ebx & (1U << 27)) != 0) ||
((ebx & (1U << 31)) != 0) ||
((ebx & (1U << 30)) != 0) ||
((ebx & (1U << 17)) != 0) ||
((ebx & (1U << 21)) != 0));
feat->AVX2 = (ebx & ((int)1 << 5)) != 0;
feat->SHA = (ebx & ((int)1 << 29)) != 0;
feat->AVX512 = (((ebx & ((int)1 << 16)) != 0) ||
((ebx & ((int)1 << 28)) != 0) ||
((ebx & ((int)1 << 26)) != 0) ||
((ebx & ((int)1 << 27)) != 0) ||
((ebx & ((int)1 << 31)) != 0) ||
((ebx & ((int)1 << 30)) != 0) ||
((ebx & ((int)1 << 17)) != 0) ||
((ebx & ((int)1 << 21)) != 0));
}
else {
printWarn("Can't read features information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000007, cpu->maxLevels);
@@ -363,8 +293,8 @@ struct cpuInfo* get_cpu_info() {
if (cpu->maxExtendedLevels >= 0x80000001){
eax = 0x80000001;
cpuid(&eax, &ebx, &ecx, &edx);
feat->SSE4a = (ecx & (1U << 6)) != 0;
feat->FMA4 = (ecx & (1U << 16)) != 0;
feat->SSE4a = (ecx & ((int)1 << 6)) != 0;
feat->FMA4 = (ecx & ((int)1 << 16)) != 0;
}
else {
printWarn("Can't read features information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x80000001, cpu->maxExtendedLevels);
@@ -374,32 +304,21 @@ struct cpuInfo* get_cpu_info() {
cpu->cpu_name = get_str_cpu_name_internal();
}
else {
cpu->cpu_name = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1));
strcpy(cpu->cpu_name, STRING_UNKNOWN);
cpu->cpu_name = malloc(sizeof(char)*8);
sprintf(cpu->cpu_name,"Unknown");
printWarn("Can't read cpu name from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x80000004, cpu->maxExtendedLevels);
}
cpu->topology_extensions = false;
if(cpu->cpu_vendor == CPU_VENDOR_AMD && cpu->maxExtendedLevels >= 0x80000001) {
eax = 0x80000001;
cpuid(&eax, &ebx, &ecx, &edx);
cpu->topology_extensions = (ecx >> 22) & 1;
}
cpu->arch = get_cpu_uarch(cpu);
cpu->freq = get_frequency_info(cpu);
cpu->cach = get_cache_info(cpu);
cpu->topo = get_topology_info(cpu, cpu->cach);
cpu->peak_performance = get_peak_performance(cpu, cpu->topo, get_freq(cpu->freq), accurate_pp());
if(cpu->cach == NULL || cpu->topo == NULL) {
return NULL;
}
return cpu;
}
bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
if(cpu->maxExtendedLevels >= 0x8000001D && cpu->topology_extensions) {
if(cpu->maxExtendedLevels >= 0x8000001D) {
uint32_t i, eax, ebx, ecx, edx, num_sharing_cache, cache_type, cache_level;
i = 0;
@@ -442,12 +361,13 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
topo->cach->L3->num_caches = topo->logical_cores / num_sharing_cache;
}
else {
printWarn("Found unknown unified cache at level %d", cache_level);
printBug("Found unified cache at level %d (expected == 2 or 3)", cache_level);
return false;
}
break;
default: // Unknown cache type
printBug("Unknown cache type %d with level %d found at i=%d", cache_type, cache_level, i);
default: // Unknown Type Cache
printBug("Unknown Type Cache found at ID %d", i);
return false;
}
}
@@ -456,7 +376,7 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
} while (cache_type > 0);
}
else {
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X and topology_extensions=%s). Guessing cache topology", 0x8000001D, cpu->maxExtendedLevels, cpu->topology_extensions ? "true" : "false");
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X). Guessing cache sizes", 0x8000001D, cpu->maxExtendedLevels);
topo->cach->L1i->num_caches = topo->physical_cores;
topo->cach->L1d->num_caches = topo->physical_cores;
@@ -472,20 +392,10 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
return true;
}
void get_topology_from_udev(struct cpuInfo* cpu, struct topology* topo) {
// TODO: To be improved in the future
topo->total_cores = get_ncores_from_cpuinfo();
topo->logical_cores = topo->total_cores;
topo->physical_cores = topo->total_cores;
topo->smt_available = 1;
topo->smt_supported = 1;
topo->sockets = 1;
}
// Main reference: https://software.intel.com/content/www/us/en/develop/articles/intel-64-architecture-processor-topology-enumeration.html
// Very interesting resource: https://wiki.osdev.org/Detecting_CPU_Topology_(80x86)
struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach) {
struct topology* topo = emalloc(sizeof(struct topology));
struct topology* topo = malloc(sizeof(struct topology));
init_topology_struct(topo, cach);
uint32_t eax = 0;
@@ -503,7 +413,7 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach) {
topo->total_cores = info.dwNumberOfProcessors;
#else
if((topo->total_cores = sysconf(_SC_NPROCESSORS_ONLN)) == -1) {
printWarn("sysconf(_SC_NPROCESSORS_ONLN): %s", strerror(errno));
perror("sysconf");
topo->total_cores = topo->logical_cores; // fallback
}
#endif
@@ -511,22 +421,10 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach) {
switch(cpu->cpu_vendor) {
case CPU_VENDOR_INTEL:
if (cpu->maxLevels >= 0x00000004) {
bool toporet = get_topology_from_apic(cpu, topo);
if(!toporet) {
#ifdef __linux__
printWarn("Failed to retrieve topology from APIC, using udev...\n");
get_topology_from_udev(cpu, topo);
#else
printErr("Failed to retrieve topology from APIC, assumming default values...\n");
topo->logical_cores = UNKNOWN_DATA;
topo->physical_cores = UNKNOWN_DATA;
topo->smt_available = 1;
topo->smt_supported = 1;
#endif
}
get_topology_from_apic(cpu, topo);
}
else {
printWarn("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000001, cpu->maxLevels);
printErr("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000001, cpu->maxLevels);
topo->physical_cores = 1;
topo->logical_cores = 1;
topo->smt_available = 1;
@@ -539,18 +437,18 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach) {
cpuid(&eax, &ebx, &ecx, &edx);
topo->logical_cores = (ecx & 0xFF) + 1;
if (cpu->maxExtendedLevels >= 0x8000001E && cpu->topology_extensions) {
if (cpu->maxExtendedLevels >= 0x8000001E) {
eax = 0x8000001E;
cpuid(&eax, &ebx, &ecx, &edx);
topo->smt_supported = ((ebx >> 8) & 0x03) + 1;
}
else {
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X and topology_extensions=%s)", 0x8000001E, cpu->maxExtendedLevels, cpu->topology_extensions ? "true" : "false");
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x8000001E, cpu->maxExtendedLevels);
topo->smt_supported = 1;
}
}
else {
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x80000008, cpu->maxExtendedLevels);
printErr("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x80000008, cpu->maxExtendedLevels);
topo->physical_cores = 1;
topo->logical_cores = 1;
topo->smt_supported = 1;
@@ -672,13 +570,13 @@ struct cache* get_cache_info_general(struct cache* cach, uint32_t level) {
cach->L3->exists = true;
}
else {
printWarn("Found unknown unified cache at level %d (size is %d bytes)", cache_level, cache_total_size);
cach->max_cache_level--;
printBug("Found unified cache at level %d (expected == 2 or 3)", cache_level);
return NULL;
}
break;
default: // Unknown cache type
printBug("Unknown cache type %d with level %d found at i=%d", cache_type, cache_level, i);
default: // Unknown Type Cache
printBug("Unknown Type Cache found at ID %d", i);
return NULL;
}
}
@@ -690,7 +588,7 @@ struct cache* get_cache_info_general(struct cache* cach, uint32_t level) {
}
struct cache* get_cache_info(struct cpuInfo* cpu) {
struct cache* cach = emalloc(sizeof(struct cache));
struct cache* cach = malloc(sizeof(struct cache));
init_cache_struct(cach);
uint32_t level;
@@ -701,7 +599,7 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
if(cpu->cpu_vendor == CPU_VENDOR_INTEL) {
level = 0x00000004;
if(cpu->maxLevels < level) {
printWarn("Can't read cache information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", level, cpu->maxLevels);
printErr("Can't read cache information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", level, cpu->maxLevels);
return NULL;
}
else {
@@ -710,11 +608,11 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
}
else {
level = 0x8000001D;
if(cpu->maxExtendedLevels < level || !cpu->topology_extensions) {
printWarn("Can't read cache information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X and topology_extensions=%s)", level, cpu->maxExtendedLevels, cpu->topology_extensions ? "true" : "false");
if(cpu->maxExtendedLevels < level) {
printWarn("Can't read cache information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", level, cpu->maxExtendedLevels);
level = 0x80000006;
if(cpu->maxExtendedLevels < level) {
printWarn("Can't read cache information from cpuid using old method (needed extended level is 0x%.8X, max is 0x%.8X)", level, cpu->maxExtendedLevels);
printErr("Can't read cache information from cpuid using old method (needed extended level is 0x%.8X, max is 0x%.8X)", level, cpu->maxExtendedLevels);
return NULL;
}
printWarn("Fallback to old method using 0x%.8X and 0x%.8X", level-1, level);
@@ -725,25 +623,68 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
}
}
// Sanity checks. If we read values greater than this, they can't be valid ones
// The values were chosen by me
if(cach->L1i->size > 64 * 1024) {
printBug("Invalid L1i size: %dKB", cach->L1i->size/1024);
return NULL;
}
if(cach->L1d->size > 64 * 1024) {
printBug("Invalid L1d size: %dKB", cach->L1d->size/1024);
return NULL;
}
if(cach->L2->exists) {
if(cach->L3->exists && cach->L2->size > 2 * 1048576) {
printBug("Invalid L2 size: %dMB", cach->L2->size/(1048576));
return NULL;
}
else if(cach->L2->size > 100 * 1048576) {
printBug("Invalid L2 size: %dMB", cach->L2->size/(1048576));
return NULL;
}
}
if(cach->L3->exists && cach->L3->size > 100 * 1048576) {
printBug("Invalid L3 size: %dMB", cach->L3->size/(1048576));
return NULL;
}
if(!cach->L2->exists) {
printBug("Could not find L2 cache");
return NULL;
}
return cach;
}
struct frequency* get_frequency_info(struct cpuInfo* cpu) {
struct frequency* freq = emalloc(sizeof(struct frequency));
struct frequency* freq = malloc(sizeof(struct frequency));
if(cpu->maxLevels < 0x00000016) {
#if defined (_WIN32) || defined (__APPLE__)
#ifdef _WIN32
if(cpu->hv->present) {
printWarn("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000016, cpu->maxLevels);
freq->base = UNKNOWN_DATA;
freq->max = UNKNOWN_DATA;
}
else {
printErr("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000016, cpu->maxLevels);
}
freq->base = UNKNOWN_FREQ;
freq->max = UNKNOWN_FREQ;
#elif defined __APPLE__
printErr("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000016, cpu->maxLevels);
freq->base = UNKNOWN_FREQ;
freq->max = UNKNOWN_FREQ;
#else
printWarn("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X). Using udev", 0x00000016, cpu->maxLevels);
freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(0);
freq->base = UNKNOWN_FREQ;
freq->max = get_max_freq_from_file(0, cpu->hv->present);
if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz");
freq->max = UNKNOWN_DATA;
if(cpu->hv->present) {
printWarn("Read max CPU frequency and got 0 MHz");
}
else {
printBug("Read max CPU frequency and got 0 MHz");
}
freq->max = UNKNOWN_FREQ;
}
#endif
}
@@ -759,72 +700,131 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
freq->max = ebx;
if(freq->base == 0) {
printWarn("Read base CPU frequency from CPUID and got 0 MHz");
freq->base = UNKNOWN_DATA;
if(cpu->hv->present) {
printWarn("Read base CPU frequency and got 0 MHz");
}
else {
printBug("Read base CPU frequency and got 0 MHz");
}
freq->base = UNKNOWN_FREQ;
}
if(freq->max == 0) {
printWarn("Read max CPU frequency from CPUID and got 0 MHz");
#ifdef __linux__
printWarn("Using udev to detect frequency");
freq->max = get_max_freq_from_file(0);
if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz");
freq->max = UNKNOWN_DATA;
if(cpu->hv->present) {
printWarn("Read max CPU frequency and got 0 MHz");
}
#else
freq->max = UNKNOWN_DATA;
#endif
else {
printBug("Read max CPU frequency and got 0 MHz");
}
freq->max = UNKNOWN_FREQ;
}
}
return freq;
}
// STRING FUNCTIONS
char* get_str_cpu_name_abbreviated(struct cpuInfo* cpu) {
if(cpu->cpu_vendor == CPU_VENDOR_INTEL) {
if(!abbreviate_intel_cpu_name(&cpu->cpu_name)) {
printWarn("Failed to abbreviate CPU name");
/*** STRING FUNCTIONS ***/
char* get_str_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t freq) {
/***
PP = PeakPerformance
SP = SinglePrecision
PP(SP) =
N_CORES *
FREQUENCY *
2(Two vector units) *
2(If cpu has fma) *
16(If AVX512), 8(If AVX), 4(If SSE) *
***/
//7 for GFLOP/s and 6 for digits,eg 412.14
uint32_t size = 7+6+1+1;
assert(strlen(STRING_UNKNOWN)+1 <= size);
char* string = malloc(sizeof(char)*size);
//First check we have consistent data
if(freq == UNKNOWN_FREQ) {
snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN);
return string;
}
}
return cpu->cpu_name;
struct features* feat = cpu->feat;
double flops = topo->physical_cores * topo->sockets * (freq*1000000);
int vpus = get_number_of_vpus(cpu);
flops = flops * vpus;
if(feat->FMA3 || feat->FMA4)
flops = flops*2;
// Ice Lake has AVX512, but it has 1 VPU for AVX512, while
// it has 2 for AVX2. If this is a Ice Lake CPU, we are computing
// the peak performance supposing AVX2, not AVX512
if(feat->AVX512 && vpus_are_AVX512(cpu))
flops = flops*16;
else if(feat->AVX || feat->AVX2)
flops = flops*8;
else if(feat->SSE)
flops = flops*4;
// See https://sites.utexas.edu/jdm4372/2018/01/22/a-peculiar-
// throughput-limitation-on-intels-xeon-phi-x200-knights-landing/
if(is_knights_landing(cpu))
flops = flops * 6 / 7;
if(flops >= (double)1000000000000.0)
snprintf(string,size,"%.2f TFLOP/s",flops/1000000000000);
else if(flops >= 1000000000.0)
snprintf(string,size,"%.2f GFLOP/s",flops/1000000000);
else
snprintf(string,size,"%.2f MFLOP/s",flops/1000000);
return string;
}
// TODO: Refactoring
char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_socket) {
int topo_sockets = dual_socket ? topo->sockets : 1;
char* string;
if(topo->logical_cores == UNKNOWN_DATA) {
string = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1));
strcpy(string, STRING_UNKNOWN);
}
else if(topo->smt_supported > 1) {
// 4 for digits, 21 for ' cores (SMT disabled)' which is the longest possible output
uint32_t max_size = 4+21+1;
string = emalloc(sizeof(char) * max_size);
if(topo->smt_supported > 1) {
//3 for digits, 21 for ' cores (SMT disabled)' which is the longest possible output
uint32_t size = 3+21+1;
string = malloc(sizeof(char)*size);
if(dual_socket) {
if(topo->smt_available > 1)
snprintf(string, max_size, "%d cores (%d threads)", topo->physical_cores * topo_sockets, topo->logical_cores * topo_sockets);
snprintf(string, size, "%d cores (%d threads)",topo->physical_cores * topo->sockets, topo->logical_cores * topo->sockets);
else {
if(cpu->cpu_vendor == CPU_VENDOR_AMD)
snprintf(string, max_size, "%d cores (SMT disabled)", topo->physical_cores * topo_sockets);
snprintf(string, size, "%d cores (SMT disabled)",topo->physical_cores * topo->sockets);
else
snprintf(string, max_size, "%d cores (HT disabled)", topo->physical_cores * topo_sockets);
snprintf(string, size, "%d cores (HT disabled)",topo->physical_cores * topo->sockets);
}
}
else {
uint32_t max_size = 4+7+1;
string = emalloc(sizeof(char) * max_size);
snprintf(string, max_size, "%d cores",topo->physical_cores * topo_sockets);
if(topo->smt_available > 1)
snprintf(string, size, "%d cores (%d threads)",topo->physical_cores,topo->logical_cores);
else {
if(cpu->cpu_vendor == CPU_VENDOR_AMD)
snprintf(string, size, "%d cores (SMT disabled)",topo->physical_cores);
else
snprintf(string, size, "%d cores (HT disabled)",topo->physical_cores);
}
}
}
else {
uint32_t size = 3+7+1;
string = malloc(sizeof(char)*size);
if(dual_socket)
snprintf(string, size, "%d cores",topo->physical_cores * topo->sockets);
else
snprintf(string, size, "%d cores",topo->physical_cores);
}
return string;
}
char* get_str_avx(struct cpuInfo* cpu) {
//If all AVX are available, it will use up to 15
char* string = emalloc(sizeof(char)*17+1);
char* string = malloc(sizeof(char)*17+1);
if(!cpu->feat->AVX)
snprintf(string,2+1,"No");
else if(!cpu->feat->AVX2)
@@ -846,7 +846,7 @@ char* get_str_sse(struct cpuInfo* cpu) {
uint32_t SSE4a_sl = 6;
uint32_t SSE4_1_sl = 7;
uint32_t SSE4_2_sl = 7;
char* string = emalloc(sizeof(char)*SSE_sl+SSE2_sl+SSE3_sl+SSSE3_sl+SSE4a_sl+SSE4_1_sl+SSE4_2_sl+1);
char* string = malloc(sizeof(char)*SSE_sl+SSE2_sl+SSE3_sl+SSSE3_sl+SSE4a_sl+SSE4_1_sl+SSE4_2_sl+1);
if(cpu->feat->SSE) {
snprintf(string+last,SSE_sl+1,"SSE,");
@@ -883,7 +883,7 @@ char* get_str_sse(struct cpuInfo* cpu) {
}
char* get_str_fma(struct cpuInfo* cpu) {
char* string = emalloc(sizeof(char)*9+1);
char* string = malloc(sizeof(char)*9+1);
if(!cpu->feat->FMA3)
snprintf(string,2+1,"No");
else if(!cpu->feat->FMA4)
@@ -903,102 +903,14 @@ void print_debug(struct cpuInfo* cpu) {
cpuid(&eax, &ebx, &ecx, &edx);
printf("%s\n", cpu->cpu_name);
if(cpu->hv->present) {
printf("- Hypervisor: %s\n", cpu->hv->hv_name);
}
if(cpu->hv->present) printf("- Hypervisor: %s\n", cpu->hv->hv_name);
printf("- Max standard level: 0x%.8X\n", cpu->maxLevels);
printf("- Max extended level: 0x%.8X\n", cpu->maxExtendedLevels);
if(cpu->cpu_vendor == CPU_VENDOR_AMD) {
printf("- AMD topology extensions: %d\n", cpu->topology_extensions);
}
printf("- CPUID dump: 0x%.8X\n", eax);
free_cpuinfo_struct(cpu);
}
// TODO: Query HV and Xeon Phi levels
void print_raw(struct cpuInfo* cpu) {
uint32_t eax;
uint32_t ebx;
uint32_t ecx;
uint32_t edx;
printf("%s\n\n", cpu->cpu_name);
printf(" CPUID leaf sub EAX EBX ECX EDX \n");
printf("--------------------------------------------------------------\n");
for(int c=0; c < cpu->topo->total_cores; c++) {
#ifndef __APPLE__
if(!bind_to_cpu(c)) {
printErr("Failed binding to CPU %d", c);
return;
}
#endif
printf("CPU %d:\n", c);
for(uint32_t reg=0x00000000; reg <= cpu->maxLevels; reg++) {
if(reg == 0x00000004) {
for(uint32_t reg2=0x00000000; reg2 < cpu->cach->max_cache_level; reg2++) {
eax = reg;
ebx = 0;
ecx = reg2;
edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
printf(" 0x%.8X 0x%.2X: 0x%.8X 0x%.8X 0x%.8X 0x%.8X\n", reg, reg2, eax, ebx, ecx, edx);
}
}
else if(reg == 0x0000000B) {
for(uint32_t reg2=0x00000000; reg2 < cpu->topo->smt_supported; reg2++) {
eax = reg;
ebx = 0;
ecx = reg2;
edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
printf(" 0x%.8X 0x%.2X: 0x%.8X 0x%.8X 0x%.8X 0x%.8X\n", reg, reg2, eax, ebx, ecx, edx);
}
}
else {
eax = reg;
ebx = 0;
ecx = 0;
edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
printf(" 0x%.8X 0x%.2X: 0x%.8X 0x%.8X 0x%.8X 0x%.8X\n", reg, 0x00, eax, ebx, ecx, edx);
}
}
for(uint32_t reg=0x80000000; reg <= cpu->maxExtendedLevels; reg++) {
if(reg == 0x8000001D) {
for(uint32_t reg2=0x00000000; reg2 < cpu->cach->max_cache_level; reg2++) {
eax = reg;
ebx = 0;
ecx = reg2;
edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
printf(" 0x%.8X 0x%.2X: 0x%.8X 0x%.8X 0x%.8X 0x%.8X\n", reg, reg2, eax, ebx, ecx, edx);
}
}
else {
eax = reg;
ebx = 0;
ecx = 0;
edx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
printf(" 0x%.8X 0x%.2X: 0x%.8X 0x%.8X 0x%.8X 0x%.8X\n", reg, 0x00, eax, ebx, ecx, edx);
}
}
}
}
void free_topo_struct(struct topology* topo) {
free(topo->apic->cache_select_mask);
free(topo->apic->cache_id_apic);

View File

@@ -12,10 +12,9 @@ char* get_str_avx(struct cpuInfo* cpu);
char* get_str_sse(struct cpuInfo* cpu);
char* get_str_fma(struct cpuInfo* cpu);
char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_socket);
char* get_str_cpu_name_abbreviated(struct cpuInfo* cpu);
char* get_str_peak_performance(struct cpuInfo* cpu, struct topology* topo, int64_t freq);
void print_debug(struct cpuInfo* cpu);
void print_raw(struct cpuInfo* cpu);
void free_topo_struct(struct topology* topo);

View File

@@ -1,146 +0,0 @@
#define _GNU_SOURCE
#include <stdio.h>
#include "../../common/global.h"
#include "../uarch.h"
#include "freq.h"
#include "freq_nov.h"
#include "freq_avx.h"
#include "freq_avx512.h"
#include <immintrin.h>
#include <stdlib.h>
#include <stdbool.h>
#include <sys/time.h>
#include <time.h>
#include <errno.h>
#include <string.h>
#include <pthread.h>
#define MAX_NUMBER_THREADS 512
#define FREQ_VECTOR_SIZE 1<<16
struct freq_thread {
bool end;
bool measure;
double freq;
};
double vector_average_harmonic(double* v, int len) {
double acc = 0.0;
for(int i=0; i < len; i++) {
acc += 1 / v[i];
}
return len / acc;
}
void sleep_ms(int64_t ms) {
struct timespec ts;
ts.tv_sec = ms / 1000;
ts.tv_nsec = (ms % 1000) * 1000000;
nanosleep(&ts, &ts);
}
void* measure_freq(void *freq_ptr) {
struct freq_thread* freq = (struct freq_thread*) freq_ptr;
char* end = NULL;
char* line = NULL;
size_t len = 0;
ssize_t read;
int v = 0;
double* freq_vector = malloc(sizeof(double) * FREQ_VECTOR_SIZE);
while(!freq->end) {
if(!freq->measure) continue;
FILE* fp = fopen("/proc/cpuinfo", "r");
if(fp == NULL) return NULL;
while ((read = getline(&line, &len, fp)) != -1) {
if((line = strstr(line, "cpu MHz")) != NULL) {
line = strstr(line, "\t: ");
if(line == NULL) return NULL;
line += sizeof("\t: ") - 1;
double f = strtold(line, &end);
if(errno != 0) {
printf("strtol: %s", strerror(errno));
return NULL;
}
freq_vector[v] = f;
v++;
}
}
fclose(fp);
sleep_ms(500);
}
freq->freq = vector_average_harmonic(freq_vector, v);
printWarn("AVX2 measured freq=%f\n", freq->freq);
return NULL;
}
int64_t measure_frequency(struct cpuInfo* cpu) {
int ret;
int num_spaces;
struct freq_thread* freq_struct = malloc(sizeof(struct freq_thread));
freq_struct->end = false;
freq_struct->measure = false;
void* (*compute_function)(void*);
if(cpu->feat->AVX512 && vpus_are_AVX512(cpu)) {
printf("cpufetch is measuring the AVX512 frequency...");
compute_function = compute_avx512;
num_spaces = 45;
}
else if(cpu->feat->AVX || cpu->feat->AVX2) {
printf("cpufetch is measuring the AVX frequency...");
compute_function = compute_avx;
num_spaces = 42;
}
else {
printf("cpufetch is measuring the frequency (no vector instructions)...");
compute_function = compute_nov;
num_spaces = 63;
}
fflush(stdout);
pthread_t freq_t;
if(pthread_create(&freq_t, NULL, measure_freq, freq_struct)) {
fprintf(stderr, "Error creating thread\n");
return -1;
}
pthread_t* compute_th = malloc(sizeof(pthread_t) * cpu->topo->total_cores);
for(int i=0; i < cpu->topo->total_cores; i++) {
ret = pthread_create(&compute_th[i], NULL, compute_function, NULL);
if(ret != 0) {
fprintf(stderr, "Error creating thread\n");
return -1;
}
}
sleep_ms(500);
freq_struct->measure = true;
for(int i=0; i < cpu->topo->total_cores; i++) {
if(pthread_join(compute_th[i], NULL)) {
fprintf(stderr, "Error joining thread\n");
return -1;
}
freq_struct->end = true;
}
if(pthread_join(freq_t, NULL)) {
fprintf(stderr, "Error joining thread\n");
return -1;
}
printf("\r%*c", num_spaces, ' ');
return freq_struct->freq;
}

View File

@@ -1,12 +0,0 @@
#ifndef __FREQ__
#define __FREQ__
#include <stdint.h>
#include "../../common/cpu.h"
#define MEASURE_TIME_SECONDS 5
#define LOOP_ITERS 1000000000
int64_t measure_frequency(struct cpuInfo* cpu);
#endif

View File

@@ -1,44 +0,0 @@
#include <stdio.h>
#include <immintrin.h>
#include <stdlib.h>
#include <stdbool.h>
#include <sys/time.h>
#include <time.h>
#include <errno.h>
#include <string.h>
#include <pthread.h>
#include <stdint.h>
#include "freq.h"
void* compute_avx() {
bool end = false;
struct timeval begin, now;
__m256 a = _mm256_set1_ps(1.5);
__m256 b = _mm256_set1_ps(1.2);
__m256 c = _mm256_set1_ps(0.0);
gettimeofday(&begin, NULL);
while(!end) {
for(uint64_t i=0; i < LOOP_ITERS; i++) {
c = _mm256_fmadd_ps(a, b, c);
}
gettimeofday(&now, NULL);
double elapsed = (now.tv_sec - begin.tv_sec) + ((now.tv_usec - begin.tv_usec)/1000000.0);
end = elapsed >= (double) MEASURE_TIME_SECONDS;
}
FILE* fp = fopen("/dev/null", "w");
if(fp == NULL) {
printf("fopen: %s", strerror(errno));
}
else {
fprintf(fp, "%f", c[0]);
fclose(fp);
}
return NULL;
}

View File

@@ -1,6 +0,0 @@
#ifndef __FREQ_AVX__
#define __FREQ_AVX__
void* compute_avx();
#endif

View File

@@ -1,63 +0,0 @@
#include <stdio.h>
#include <immintrin.h>
#include <stdlib.h>
#include <stdbool.h>
#include <sys/time.h>
#include <time.h>
#include <errno.h>
#include <string.h>
#include <pthread.h>
#include <stdint.h>
#include "freq.h"
/*
* For AVX512, it seems that multiple independent
* instructions are needed to force the CPU to
* use AVX512 frequency, since with only one instruction
* (as the AVX implementaion) it still uses AVX frequency
*/
void* compute_avx512() {
bool end = false;
struct timeval begin, now;
__m512 a[8];
__m512 b[8];
__m512 mult;
for(int i=0; i < 8; i++) {
a[i] = _mm512_set1_ps(1.5);
b[i] = _mm512_set1_ps(1.2);
}
gettimeofday(&begin, NULL);
while(!end) {
for(uint64_t i=0; i < LOOP_ITERS; i++) {
a[0] = _mm512_fmadd_ps(mult, a[0], b[0]);
a[1] = _mm512_fmadd_ps(mult, a[1], b[1]);
a[2] = _mm512_fmadd_ps(mult, a[2], b[2]);
a[3] = _mm512_fmadd_ps(mult, a[3], b[3]);
a[4] = _mm512_fmadd_ps(mult, a[4], b[4]);
a[5] = _mm512_fmadd_ps(mult, a[5], b[5]);
a[6] = _mm512_fmadd_ps(mult, a[6], b[6]);
a[7] = _mm512_fmadd_ps(mult, a[7], b[7]);
}
gettimeofday(&now, NULL);
double elapsed = (now.tv_sec - begin.tv_sec) + ((now.tv_usec - begin.tv_usec)/1000000.0);
end = elapsed >= (double) MEASURE_TIME_SECONDS;
}
FILE* fp = fopen("/dev/null", "w");
if(fp == NULL) {
printf("fopen: %s", strerror(errno));
}
else {
for(int i=0; i < 8; i++)
fprintf(fp, "%f", a[i][0]);
fclose(fp);
}
return NULL;
}

View File

@@ -1,6 +0,0 @@
#ifndef __FREQ_AVX512__
#define __FREQ_AVX512__
void* compute_avx512();
#endif

View File

@@ -1,44 +0,0 @@
#include <stdio.h>
#include <immintrin.h>
#include <stdlib.h>
#include <stdbool.h>
#include <sys/time.h>
#include <time.h>
#include <errno.h>
#include <string.h>
#include <pthread.h>
#include <stdint.h>
#include "freq.h"
void* compute_nov() {
bool end = false;
struct timeval begin, now;
float a = 1.5;
float b = 1.2;
float c = 0.0;
gettimeofday(&begin, NULL);
while(!end) {
for(uint64_t i=0; i < LOOP_ITERS; i++) {
c = a * b;
}
gettimeofday(&now, NULL);
double elapsed = (now.tv_sec - begin.tv_sec) + ((now.tv_usec - begin.tv_usec)/1000000.0);
end = elapsed >= (double) MEASURE_TIME_SECONDS;
}
FILE* fp = fopen("/dev/null", "w");
if(fp == NULL) {
printf("fopen: %s", strerror(errno));
}
else {
fprintf(fp, "%f", c);
fclose(fp);
}
return NULL;
}

View File

@@ -1,6 +0,0 @@
#ifndef __FREQ_NO_VECTOR__
#define __FREQ_NO_VECTOR__
void* compute_nov();
#endif

View File

@@ -65,7 +65,6 @@ enum {
UARCH_AIRMONT,
UARCH_KABY_LAKE,
UARCH_COMET_LAKE,
UARCH_ROCKET_LAKE,
UARCH_AMBER_LAKE,
UARCH_WHISKEY_LAKE,
UARCH_SKYLAKE,
@@ -78,7 +77,7 @@ enum {
UARCH_SUNNY_COVE,
UARCH_GOLDMONT_PLUS,
UARCH_TREMONT,
UARCH_LAKEMONT,
UARCH_WILLOW_COVE,
UARCH_COFFE_LAKE,
UARCH_ITANIUM,
UARCH_KNIGHTS_FERRY,
@@ -89,7 +88,6 @@ enum {
UARCH_CEDAR_MILL,
UARCH_ITANIUM2,
UARCH_ICE_LAKE,
UARCH_TIGER_LAKE,
// AMD //
UARCH_AM486,
UARCH_AM5X86,
@@ -120,10 +118,10 @@ struct uarch {
#define UARCH_START if (false) {}
#define CHECK_UARCH(arch, ef_, f_, em_, m_, s_, str, uarch, process) \
else if (ef_ == ef && f_ == f && (em_ == NA || em_ == em) && (m_ == NA || m_ == m) && (s_ == NA || s_ == s)) fill_uarch(arch, str, uarch, process);
#define UARCH_END else { printBug("Unknown microarchitecture detected: M=0x%.8X EM=0x%.8X F=0x%.8X EF=0x%.8X S=0x%.8X", m, em, f, ef, s); fill_uarch(arch, STRING_UNKNOWN, UARCH_UNKNOWN, 0); }
#define UARCH_END else { printBug("Unknown microarchitecture detected: M=0x%.8X EM=0x%.8X F=0x%.8X EF=0x%.8X S=0x%.8X", m, em, f, ef, s); fill_uarch(arch, "Unknown", UARCH_UNKNOWN, 0); }
void fill_uarch(struct uarch* arch, char* str, MICROARCH u, uint32_t process) {
arch->uarch_str = emalloc(sizeof(char) * (strlen(str)+1));
arch->uarch_str = malloc(sizeof(char) * (strlen(str)+1));
strcpy(arch->uarch_str, str);
arch->uarch = u;
arch->process= process;
@@ -131,7 +129,7 @@ void fill_uarch(struct uarch* arch, char* str, MICROARCH u, uint32_t process) {
// Inspired in Todd Allen's decode_uarch_intel
struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s) {
struct uarch* arch = emalloc(sizeof(struct uarch));
struct uarch* arch = malloc(sizeof(struct uarch));
// EF: Extended Family //
// F: Family //
@@ -148,9 +146,7 @@ struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, u
CHECK_UARCH(arch, 0, 5, 0, 4, NA, "P5 MMX", UARCH_P5, UNK)
CHECK_UARCH(arch, 0, 5, 0, 7, NA, "P5 MMX", UARCH_P5, UNK)
CHECK_UARCH(arch, 0, 5, 0, 8, NA, "P5 MMX", UARCH_P5, 250)
CHECK_UARCH(arch, 0, 5, 0, 9, 0, "Lakemont", UARCH_LAKEMONT, 32)
CHECK_UARCH(arch, 0, 5, 0, 9, NA, "P5 MMX", UARCH_P5, UNK)
CHECK_UARCH(arch, 0, 5, 0, 10, 0, "Lakemont", UARCH_LAKEMONT, 32)
CHECK_UARCH(arch, 0, 6, 0, 0, NA, "P6 Pentium II", UARCH_P6, UNK)
CHECK_UARCH(arch, 0, 6, 0, 1, NA, "P6 Pentium II", UARCH_P6, UNK) // process depends on core
CHECK_UARCH(arch, 0, 6, 0, 2, NA, "P6 Pentium II", UARCH_P6, UNK)
@@ -221,14 +217,13 @@ struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, u
CHECK_UARCH(arch, 0, 6, 8, 5, NA, "Knights Mill", UARCH_KNIGHTS_MILL, 14) // no spec update; only MSR_CPUID_table* so far
CHECK_UARCH(arch, 0, 6, 8, 6, NA, "Tremont", UARCH_TREMONT, 10) // LX*
CHECK_UARCH(arch, 0, 6, 8, 10, NA, "Tremont", UARCH_TREMONT, 10) // no spec update; only geekbench.com example
CHECK_UARCH(arch, 0, 6, 8, 12, NA, "Tiger Lake", UARCH_TIGER_LAKE, 10) // instlatx64
CHECK_UARCH(arch, 0, 6, 8, 13, NA, "Tiger Lake", UARCH_TIGER_LAKE, 10) // instlatx64
// CHECK_UARCH(arch, 0, 6, 8, 14, 9, ...) It is not possible to determine uarch only from CPUID dump (can be Kaby Lake or Amber Lake)
CHECK_UARCH(arch, 0, 6, 8, 12, NA, "Willow Cove", UARCH_WILLOW_COVE, 10) // found only on en.wikichip.org
CHECK_UARCH(arch, 0, 6, 8, 13, NA, "Willow Cove", UARCH_WILLOW_COVE, 10) // LX*
CHECK_UARCH(arch, 0, 6, 8, 14, 9, "Amber Lake", UARCH_AMBER_LAKE, 14) // wikichip
CHECK_UARCH(arch, 0, 6, 8, 14, 10, "Kaby Lake", UARCH_KABY_LAKE, 14) // wikichip
CHECK_UARCH(arch, 0, 6, 8, 14, 11, "Whiskey Lake", UARCH_WHISKEY_LAKE, 14) // wikichip
CHECK_UARCH(arch, 0, 6, 8, 14, 12, "Comet Lake", UARCH_COMET_LAKE, 14) // wikichip
CHECK_UARCH(arch, 0, 6, 9, 6, NA, "Tremont", UARCH_TREMONT, 10) // LX*
CHECK_UARCH(arch, 0, 6, 9, 10, NA, "Tremont", UARCH_TREMONT, 10) // instlatx64
CHECK_UARCH(arch, 0, 6, 9, 12, NA, "Tremont", UARCH_TREMONT, 10) // LX*
CHECK_UARCH(arch, 0, 6, 9, 13, NA, "Sunny Cove", UARCH_SUNNY_COVE, 10) // LX*
CHECK_UARCH(arch, 0, 6, 9, 14, 9, "Kaby Lake", UARCH_KABY_LAKE, 14)
@@ -238,7 +233,6 @@ struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, u
CHECK_UARCH(arch, 0, 6, 9, 14, 13, "Coffee Lake", UARCH_COFFE_LAKE, 14)
CHECK_UARCH(arch, 0, 6, 10, 5, NA, "Comet Lake", UARCH_COMET_LAKE, 14) // wikichip
CHECK_UARCH(arch, 0, 6, 10, 6, NA, "Comet Lake", UARCH_COMET_LAKE, 14) // instlatx64.atw.hu (i7-10710U)
CHECK_UARCH(arch, 0, 6, 10, 7, NA, "Rocket Lake", UARCH_ROCKET_LAKE, 14) // instlatx64.atw.hu (i7-11700K)
CHECK_UARCH(arch, 0, 11, 0, 0, NA, "Knights Ferry", UARCH_KNIGHTS_FERRY, 45) // found only on en.wikichip.org
CHECK_UARCH(arch, 0, 11, 0, 1, NA, "Knights Corner", UARCH_KNIGHTS_CORNER, 22)
CHECK_UARCH(arch, 0, 15, 0, 0, NA, "Willamette", UARCH_WILLAMETTE, 180)
@@ -257,7 +251,7 @@ struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, u
// iNApired in Todd Allen's decode_uarch_amd
struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s) {
struct uarch* arch = emalloc(sizeof(struct uarch));
struct uarch* arch = malloc(sizeof(struct uarch));
// EF: Extended Family //
// F: Family //
@@ -274,7 +268,6 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
CHECK_UARCH(arch, 0, 4, NA, NA, NA, "Am5x86", UARCH_AM5X86, UNK)
CHECK_UARCH(arch, 0, 5, 0, 6, NA, "K6", UARCH_K6, 300)
CHECK_UARCH(arch, 0, 5, 0, 7, NA, "K6", UARCH_K6, 250) // *p from sandpile.org
CHECK_UARCH(arch, 0, 5, 0, 10, NA, "K7", UARCH_K7, 130) // Geode NX
CHECK_UARCH(arch, 0, 5, 0, 13, NA, "K6", UARCH_K6, 80) // *p from sandpile.org
CHECK_UARCH(arch, 0, 5, NA, NA, NA, "K6", UARCH_K6, UNK)
CHECK_UARCH(arch, 0, 6, 0, 1, NA, "K7", UARCH_K7, 250)
@@ -330,7 +323,7 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
CHECK_UARCH(arch, 2, 15, NA, NA, NA, "Puma 2008", UARCH_PUMA_2008, 65)
CHECK_UARCH(arch, 3, 15, NA, NA, NA, "K10", UARCH_K10, 32)
CHECK_UARCH(arch, 5, 15, NA, NA, NA, "Bobcat", UARCH_BOBCAT, 40)
CHECK_UARCH(arch, 6, 15, 0, 0, NA, "Bulldozer", UARCH_BULLDOZER, 32) // instlatx64 engr sample
CHECK_UARCH(arch, 6, 15, 0, 0, NA, "Bulldozer", UARCH_BULLDOZER, 32) // iNAtlatx64 engr sample
CHECK_UARCH(arch, 6, 15, 0, 1, NA, "Bulldozer", UARCH_BULLDOZER, 32)
CHECK_UARCH(arch, 6, 15, 0, 2, NA, "Piledriver", UARCH_PILEDRIVER, 32)
CHECK_UARCH(arch, 6, 15, 1, 0, NA, "Piledriver", UARCH_PILEDRIVER, 32)
@@ -338,55 +331,34 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
CHECK_UARCH(arch, 6, 15, 3, 0, NA, "Steamroller", UARCH_STEAMROLLER, 28)
CHECK_UARCH(arch, 6, 15, 3, 8, NA, "Steamroller", UARCH_STEAMROLLER, 28)
CHECK_UARCH(arch, 6, 15, 4, 0, NA, "Steamroller", UARCH_STEAMROLLER, 28) // Software Optimization Guide (15h) says it has the same iNAt latencies as (6,15),(3,x).
CHECK_UARCH(arch, 6, 15, 6, 0, NA, "Excavator", UARCH_EXCAVATOR, 28) // undocumented, but instlatx64 samples
CHECK_UARCH(arch, 6, 15, 6, 0, NA, "Excavator", UARCH_EXCAVATOR, 28) // undocumented, but iNAtlatx64 samples
CHECK_UARCH(arch, 6, 15, 6, 5, NA, "Excavator", UARCH_EXCAVATOR, 28) // undocumented, but sample from Alexandros Couloumbis
CHECK_UARCH(arch, 6, 15, 7, 0, NA, "Excavator", UARCH_EXCAVATOR, 28)
CHECK_UARCH(arch, 7, 15, 0, 0, NA, "Jaguar", UARCH_JAGUAR, 28)
CHECK_UARCH(arch, 7, 15, 2, 6, NA, "Jaguar", UARCH_JAGUAR, 28) // AMD Cato (Xbox One?)
CHECK_UARCH(arch, 7, 15, 3, 0, NA, "Puma 2014", UARCH_PUMA_2014, 28)
CHECK_UARCH(arch, 8, 15, 0, 0, NA, "Zen", UARCH_ZEN, 14) // instlatx64 engr sample
CHECK_UARCH(arch, 8, 15, 0, 0, NA, "Zen", UARCH_ZEN, 14) // iNAtlatx64 engr sample
CHECK_UARCH(arch, 8, 15, 0, 1, NA, "Zen", UARCH_ZEN, 14)
CHECK_UARCH(arch, 8, 15, 0, 8, NA, "Zen+", UARCH_ZEN_PLUS, 12)
CHECK_UARCH(arch, 8, 15, 1, 1, NA, "Zen", UARCH_ZEN, 14) // found only on en.wikichip.org & instlatx64 examples
CHECK_UARCH(arch, 8, 15, 1, 1, NA, "Zen", UARCH_ZEN, 14) // found only on en.wikichip.org & iNAtlatx64 examples
CHECK_UARCH(arch, 8, 15, 1, 8, NA, "Zen+", UARCH_ZEN_PLUS, 12) // found only on en.wikichip.org
CHECK_UARCH(arch, 8, 15, 2, 0, NA, "Zen", UARCH_ZEN, 14) // Dali, found on instlatx64 and en.wikichip.org
CHECK_UARCH(arch, 8, 15, 3, 1, NA, "Zen 2", UARCH_ZEN2, 7) // found only on en.wikichip.org
CHECK_UARCH(arch, 8, 15, 4, 7, NA, "Zen 2", UARCH_ZEN2, 7) // instlatx64 example (AMD 4700S)
CHECK_UARCH(arch, 8, 15, 5, 0, NA, "Zen", UARCH_ZEN, 14) // instlatx64 example (Subor Z+)
CHECK_UARCH(arch, 8, 15, 6, 0, NA, "Zen 2", UARCH_ZEN2, 7) // undocumented, geekbench.com example
CHECK_UARCH(arch, 8, 15, 6, 8, NA, "Zen 2", UARCH_ZEN2, 7) // found on instlatx64
CHECK_UARCH(arch, 8, 15, 7, 1, NA, "Zen 2", UARCH_ZEN2, 7) // samples from Steven Noonan and instlatx64
CHECK_UARCH(arch, 10, 15, 0, 1, NA, "Zen 3", UARCH_ZEN3, 7) // instlatx64
CHECK_UARCH(arch, 10, 15, 2, 1, NA, "Zen 3", UARCH_ZEN3, 7) // instlatx64
CHECK_UARCH(arch, 10, 15, 5, 0, NA, "Zen 3", UARCH_ZEN3, 7) // instlatx64
CHECK_UARCH(arch, 8, 15, 7, 1, NA, "Zen 2", UARCH_ZEN2, 7) // undocumented, but samples from Steven Noonan
CHECK_UARCH(arch, 10, 15, NA, NA, NA, "Zen 3", UARCH_ZEN3, 7) // undocumented, LX*
UARCH_END
return arch;
}
struct uarch* get_uarch_from_cpuid(struct cpuInfo* cpu, uint32_t dump, uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s) {
if(cpu->cpu_vendor == CPU_VENDOR_INTEL) {
if(dump == 0x000806E9) {
// It is not possible to determine uarch only from CPUID dump (can be Kaby Lake or Amber Lake)
struct uarch* arch = emalloc(sizeof(struct uarch));
if(strstr(cpu->cpu_name, "Y") != NULL) {
fill_uarch(arch, "Amber Lake", UARCH_AMBER_LAKE, 14);
}
else {
fill_uarch(arch, "Kaby Lake", UARCH_KABY_LAKE, 14);
}
return arch;
}
struct uarch* get_uarch_from_cpuid(struct cpuInfo* cpu, uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s) {
if(cpu->cpu_vendor == CPU_VENDOR_INTEL)
return get_uarch_from_cpuid_intel(ef, f, em, m, s);
}
else
return get_uarch_from_cpuid_amd(ef, f, em, m, s);
}
bool vpus_are_AVX512(struct cpuInfo* cpu) {
return cpu->arch->uarch != UARCH_ICE_LAKE && cpu->arch->uarch != UARCH_TIGER_LAKE;
return cpu->arch->uarch != UARCH_ICE_LAKE;
}
bool is_knights_landing(struct cpuInfo* cpu) {
@@ -395,7 +367,6 @@ bool is_knights_landing(struct cpuInfo* cpu) {
int get_number_of_vpus(struct cpuInfo* cpu) {
switch(cpu->arch->uarch) {
// Intel
case UARCH_HASWELL:
case UARCH_BROADWELL:
@@ -403,7 +374,6 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_CASCADE_LAKE:
case UARCH_KABY_LAKE:
case UARCH_COMET_LAKE:
case UARCH_ROCKET_LAKE:
case UARCH_AMBER_LAKE:
case UARCH_WHISKEY_LAKE:
case UARCH_COFFE_LAKE:
@@ -413,9 +383,8 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_KNIGHTS_MILL:
case UARCH_ICE_LAKE:
case UARCH_TIGER_LAKE:
// AMD
// Right now is just a guess!
case UARCH_ZEN2:
case UARCH_ZEN3:
return 2;
@@ -424,37 +393,18 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
}
}
bool choose_new_intel_logo_uarch(struct cpuInfo* cpu) {
switch(cpu->arch->uarch) {
case UARCH_ROCKET_LAKE:
case UARCH_TIGER_LAKE:
return true;
default:
return false;
}
}
char* get_str_uarch(struct cpuInfo* cpu) {
return cpu->arch->uarch_str;
}
char* get_str_process(struct cpuInfo* cpu) {
char* str = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
int32_t process = cpu->arch->process;
char* str = malloc(sizeof(char) * (4+2+1));
uint32_t process = cpu->arch->process;
if(process == UNK) {
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
else if(process > 100) {
if(process > 100)
sprintf(str, "%.2fum", (double)process/100);
}
else if(process > 0){
else
sprintf(str, "%dnm", process);
}
else {
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
printBug("Found invalid process: '%d'", process);
}
return str;
}

View File

@@ -7,11 +7,10 @@
struct uarch;
struct uarch* get_uarch_from_cpuid(struct cpuInfo* cpu, uint32_t dump, uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s);
struct uarch* get_uarch_from_cpuid(struct cpuInfo* cpu, uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s);
bool vpus_are_AVX512(struct cpuInfo* cpu);
bool is_knights_landing(struct cpuInfo* cpu);
int get_number_of_vpus(struct cpuInfo* cpu);
bool choose_new_intel_logo_uarch(struct cpuInfo* cpu);
char* get_str_uarch(struct cpuInfo* cpu);
char* get_str_process(struct cpuInfo* cpu);
void free_uarch_struct(struct uarch* arch);

View File

@@ -1,23 +0,0 @@
#!/bin/bash -u
CPUID=0x00A50F00
efamily=$(((${CPUID}>>20)&0xFF))
family=$(((${CPUID}>>8)&0xF))
emodel=$(((${CPUID}>>16)&0xF))
model=$(((${CPUID}>>4)&0xF))
stepping=$((${CPUID}&0xF))
printf 'CPUID: 0x%.8X\n' $CPUID
printf -- '- EF = 0x%X (%d)\n' $efamily $efamily
printf -- '- F = 0x%X (%d)\n' $family $family
printf -- '- EM = 0x%X (%d)\n' $emodel $emodel
printf -- '- M = 0x%X (%d)\n' $model $model
printf -- '- S = 0x%X (%d)\n' $stepping $stepping
#EF=$efamily
#F=$family
#EM=$emodel
#M=$model
#S=$stepping
#grep -E "\s*CHECK_UARCH\(arch,\s*${EF},\s*${F},\s*(${EM}|NA),\s*(${M}|NA),\s*(${S}|NA)" uarch.c