Compare commits

..

57 Commits
wiiu ... i279

Author SHA1 Message Date
Dr-Noob
5c4702bc1e [v1.06][ARM] Make Marvell logo shorter 2024-09-09 19:21:48 +01:00
Dr-Noob
177a92ba86 [v1.06][ARM] Add support for Marvell SoC (#279) 2024-09-09 19:17:27 +01:00
Dr-Noob
343150e516 [v1.06][ARM] Add Tegra Orin (#275) 2024-09-09 08:19:18 +01:00
Dr-Noob
1e2c7e565c [v1.06][ARM] Add SC8280XP (on device tree) (#272) 2024-09-09 07:11:57 +01:00
Dr-Noob
977c35a9af [v1.06][X86] Add Zen5 uarch 2024-09-05 20:14:52 +01:00
Dr-Noob
eb8fad2843 [v1.06][ARM] Simplify is_ARMv8_or_newer 2024-09-02 08:27:58 +01:00
Dr-Noob
bd38951439 [v1.06][ARM] Update get_vpus_width to match SVE detection 2024-09-02 08:26:58 +01:00
Dr-Noob
057a36efd5 [v1.06][ARM] Add new microarchitectures 2024-09-02 08:20:40 +01:00
Dr-Noob
56901d70ab [v1.06][ARM] Add more NXP SoCs 2024-08-31 18:40:35 +01:00
Dr-Noob
5bd507e4b6 [v1.06][ARM] Add support for Amlogic A311D (#268) 2024-08-31 09:37:50 +01:00
Dr-Noob
9192ba3eb8 [v1.06][ARM] Add (another) cpufamily for M3 and set the ARM version, fixing peak performance wrong result (#230) 2024-08-29 08:13:05 +01:00
Dr-Noob
807a13d29e [v1.06] Fix manpage file extension (fixes #269) 2024-08-28 21:33:48 +01:00
Dr-Noob
15a803dae5 [v1.06][ARM] Check if HWCAP2_SVE2 is defined before using it (fixes #270) 2024-08-28 21:26:27 +01:00
Dr-Noob
0507355372 [v1.06][X86] Bugfix: set affinity in --accurate-pp
There are cases where measure_frequency is called after binding the
process to a specific core via bind_to_cpu (e.g., when iterating over
modules in hybrid architectures). Thus, in measure_frequency we must
set the affinity of the newly created threads, ensuring they are
binded to the right core.
2024-08-26 12:31:18 +01:00
Dr-Noob
9f66a137c5 [v1.06][ARM] Add support for NXP i.MX 8M Plus (#261) 2024-08-25 17:44:29 +01:00
Dr-Noob
324d0fbe94 [v1.06][PPC] Add support for Espresso (#231) 2024-08-25 16:50:58 +01:00
Dr-Noob
af8bb16302 [v1.06][ARM] Fix for commit 025e28c 2024-08-24 15:44:06 +01:00
Dr-Noob
40374121b8 [v1.06] Replace emalloc+memset with ecalloc when possible. Refactor some memory allocation code 2024-08-24 15:32:33 +01:00
Dr-Noob
025e28c516 [v1.06][ARM] Set Android properties as defines 2024-08-24 14:47:34 +01:00
Dr-Noob
7ad19d113c [v1.06] Remove soc_ prefix from field names in system_on_chip struct 2024-08-24 12:44:24 +01:00
Dr-Noob
13605ed0ce [v1.06][ARM] Remove BCM prefix from Broadcom vendor string 2024-08-24 12:34:57 +01:00
Dr-Noob
7689355a72 [v1.06][ARM] Add support for Apple SoCs in Asahi Linux (#263) 2024-08-23 08:37:13 +01:00
Timothy Warren
321a1ec375 [v1.06][X86] Add old Intel and AMD CPUs (#260)
* Add Intel and AMD 486, Intel Pentium Pro, and AMD K5 chips
* Update infer_cpu_name_from_uarch to support added CPU uarches
* Add sources for more of the legacy chip data
* Add the more specific codename for Intel Pentium MMX Mobile chips
* Document source of AMD 486/K5 variants
* Add link to documentation for Intel 486

---------

Co-authored-by: Timothy Warren <tim@timshomepage.net>
2024-08-20 09:25:01 +02:00
Dr-Noob
48c598cf3b [v1.06][ARM] Add support for Ampere Altra (#262) 2024-08-19 08:46:07 +01:00
Dr-Noob
aa94389bbe [v1.06][ARM] Fix two off-by-one bugs (#264) 2024-08-19 08:39:52 +01:00
Er2
8d10a03adc [v1.06][FreeBSD][Apple] Implement fallback frequency calculation (#251) 2024-08-19 09:21:41 +02:00
Dr-Noob
2410fd16d3 [v1.06] Bump version 2024-08-18 15:12:27 +01:00
Dr-Noob
f63178b41c [v1.05][ARM] Fix compile warning in SVE cntb 2024-08-10 11:23:13 +01:00
Dr-Noob
2788e6831e [v1.05][ARM] Fix SVE cntb datatype 2024-08-10 11:16:22 +01:00
Dr-Noob
146f2a13aa [v1.05][ARM] Show SVE cntb in debug 2024-08-10 11:11:46 +01:00
Dr-Noob
90624b9aaa [v1.05][ARM] Preeliminary support for SVE detection (#259) 2024-08-10 11:08:39 +01:00
Dr-Noob
e42f04cca8 [v1.05][ARM] Add support for Kirin 9000S and TSV120 (#259) 2024-08-10 11:03:22 +01:00
Dr-Noob
3aacaf5f9e [v1.05] Add RISC-V picture to README (thanks #241!) 2024-08-03 16:31:56 +01:00
Dr-Noob
50f66ec571 [v1.05][X86] Fix compilation issue in clang and fallback to get_topology_from_udev also in AMD 2024-08-03 15:45:10 +01:00
Dr-Noob
cb186a2f97 [v1.05][X86] Do not show empty SSE if not supported (#260) 2024-08-02 10:09:51 +01:00
Dr-Noob
6164884415 [v1.05][ARM] Add latest Snapdragon SoCs (closes #256) 2024-08-02 08:07:47 +01:00
Dr-Noob
260f9ec3b8 [v1.05] Add new contributor to acknowledgements 2024-07-25 08:29:05 +01:00
Dr-Noob
79013d0ec9 [v1.05][X86] Improve robustness in case of old CPUs (verified by #220)
- Use udev to get topo when apic failed or is not available.
- Assume single core in udev when total cores is 1.
- Print core/cores accordingly to the number of cores.
2024-07-25 08:23:56 +01:00
Dr-Noob
e4227388b9 [v1.05][ARM] Add new SnapD SoCs and use ro.soc.mode in Android to improve SoC detection (#253) 2024-07-19 08:21:11 +01:00
Dr-Noob
8fca4cb250 [v1.05][X86] Fix frequency fetching from udev and measurement in hybrid architectures 2024-07-11 22:27:42 +01:00
Dr-Noob
7c947bdf64 [v1.05] Use UNKNOWN_DATA instead of -1 in frequency measurement 2024-07-11 22:10:00 +01:00
Dr-Noob
1ed3a0f2bf [v1.05] Adapt frequency measurement iterations depending on CPU speed
This is achieved by running a first measurement which gets a taste of
CPU speed, then estimate a reasonable value for the iterations of the
real measurement and then running the actual measurement. This is very
helpful to reduce the runtime of the measurement, especially for slow
CPUs
2024-07-11 21:55:01 +01:00
Dr-Noob
0fe6fc3f4d [v1.05][ARM] Fix mistake in Makefile 2024-07-11 08:17:26 +01:00
Dr-Noob
96c784026b [v1.05] Fix formatting issues in Makefile 2024-07-09 08:47:34 +01:00
Dr-Noob
59cd2dd128 [v1.05][X86] Add support for Hygon CPUs (#244) 2024-07-09 08:34:44 +01:00
Dr-Noob
da1981b97c [v1.05] Check read return value in frequency measurement 2024-07-09 08:32:24 +01:00
Dr-Noob
8506c91e00 [v1.05] Add --measure-max-freq (available on x86 and ARM) 2024-07-08 09:07:57 +01:00
Dr-Noob
ece28cbdee [v1.05] Small fix in help message 2024-07-08 08:31:00 +01:00
Dr-Noob
7b46c78249 [v1.05] Replace printf with proper printErr 2024-07-08 08:28:48 +01:00
Dr-Noob
e0095c303d [v1.05] Print a tilde in case the freq was measured (indicating that this value is an approximation) 2024-07-08 08:23:56 +01:00
Dr-Noob
65378aaed9 [v1.05] Move sysctl from ARM-specific to common (#251) 2024-07-07 12:43:03 +01:00
Dr-Noob
946729dd06 [v1.05] Compile measure freq only in Linux (avoids compiler warning in non-linux builds) 2024-07-06 11:28:46 +01:00
Dr-Noob
9212f19de1 [v1.05] Add support for frequency measurement (both x86 and ARM) (branch measure-freq #220) 2024-07-05 08:44:34 +01:00
Dr-Noob
b019256515 [v1.05] Continue merging measure-freq #220
- [v1.05][X86] Show SSE if AVX/FMA is not supported
- [v1.05][X86] Do not stop if cach is NULL and check for non-NULL cache in get_topology_info functions
- [v1.05][X86] Fix bug where the number of cpus were not set if NULL was returned inside the loop. Ensure topo is not NULL in get_peak_performance. Fallback to UNKNOWN_DATA when we have no information about topology
2024-07-05 08:37:54 +01:00
Dr-Noob
d4cadbd807 [v1.05] Move bind_to_cpu from x86-specific to global (merging measure-freq #220) 2024-07-05 08:32:11 +01:00
Dr-Noob
4f081ef1a2 [v1.05] Add newline to fix dummy warning with clang 2024-07-03 09:09:37 +02:00
Dr-Noob
1b746bc67d [v1.05][ARM] Add support to detect SoC from PCI (#245) with initial support for NVIDIA Tegra 2024-07-03 08:01:53 +01:00
40 changed files with 1461 additions and 328 deletions

View File

@@ -13,17 +13,27 @@ COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_C
ifneq ($(OS),Windows_NT)
GIT_VERSION := "$(shell git describe --abbrev=4 --dirty --always --tags)"
arch := $(shell uname -m)
os := $(shell uname -s)
ifeq ($(os), Linux)
COMMON_SRC += $(SRC_COMMON)freq.c
COMMON_HDR += $(SRC_COMMON)freq.h
endif
ifeq ($(arch), $(filter $(arch), x86_64 amd64 i386 i486 i586 i686))
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 += $(SRC_DIR)freq/freq.h
CFLAGS += -pthread
endif
ifeq ($(os), FreeBSD)
SOURCE += $(SRC_COMMON)sysctl.c
HEADERS += $(SRC_COMMON)sysctl.h
endif
CFLAGS += -DARCH_X86 -std=c99 -fstack-protector-all
else ifeq ($(arch), $(filter $(arch), ppc64le ppc64 ppcle ppc))
SRC_DIR=src/ppc/
@@ -32,14 +42,19 @@ ifneq ($(OS),Windows_NT)
CFLAGS += -DARCH_PPC -std=gnu99 -fstack-protector-all -Wno-language-extension-token
else ifeq ($(arch), $(filter $(arch), arm aarch64_be aarch64 arm64 armv8b armv8l armv7l armv6l))
SRC_DIR=src/arm/
SOURCE += $(COMMON_SRC) $(SRC_DIR)midr.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_DIR)udev.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)midr.h $(SRC_DIR)uarch.h $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_DIR)udev.c $(SRC_DIR)socs.h
SOURCE += $(COMMON_SRC) $(SRC_DIR)midr.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_COMMON)pci.c $(SRC_DIR)udev.c sve.o
HEADERS += $(COMMON_HDR) $(SRC_DIR)midr.h $(SRC_DIR)uarch.h $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_COMMON)pci.h $(SRC_DIR)udev.c $(SRC_DIR)socs.h
CFLAGS += -DARCH_ARM -Wno-unused-parameter -std=c99 -fstack-protector-all
os := $(shell uname -s)
# Check if the compiler supports -march=armv8-a+sve. We will use it (if supported) to compile SVE detection code later
is_sve_flag_supported := $(shell $(CC) -march=armv8-a+sve -c $(SRC_DIR)sve.c -o sve_test.o 2> /dev/null && echo 'yes'; rm -f sve_test.o)
ifeq ($(is_sve_flag_supported), yes)
SVE_FLAGS += -march=armv8-a+sve
endif
ifeq ($(os), Darwin)
SOURCE += $(SRC_DIR)sysctl.c
HEADERS += $(SRC_DIR)sysctl.h
SOURCE += $(SRC_COMMON)sysctl.c
HEADERS += $(SRC_COMMON)sysctl.h
endif
else ifeq ($(arch), $(filter $(arch), riscv64 riscv32))
SRC_DIR=src/riscv/
@@ -86,6 +101,9 @@ freq_avx.o: Makefile $(SRC_DIR)freq/freq_avx.c $(SRC_DIR)freq/freq_avx.h $(SRC_D
freq_avx512.o: Makefile $(SRC_DIR)freq/freq_avx512.c $(SRC_DIR)freq/freq_avx512.h $(SRC_DIR)freq/freq.h
$(CC) $(CFLAGS) $(SANITY_FLAGS) -c -mavx512f -pthread $(SRC_DIR)freq/freq_avx512.c -o $@
sve.o: Makefile $(SRC_DIR)sve.c $(SRC_DIR)sve.h
$(CC) $(CFLAGS) $(SANITY_FLAGS) $(SVE_FLAGS) -c $(SRC_DIR)sve.c -o $@
$(OUTPUT): Makefile $(SOURCE) $(HEADERS)
ifeq ($(GIT_VERSION),"")
$(CC) $(CFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT)
@@ -102,9 +120,9 @@ clean:
install: $(OUTPUT)
install -Dm755 "cpufetch" "$(DESTDIR)$(PREFIX)/bin/cpufetch"
install -Dm644 "LICENSE" "$(DESTDIR)$(PREFIX)/share/licenses/cpufetch-git/LICENSE"
install -Dm644 "cpufetch.1" "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1.gz"
install -Dm644 "cpufetch.1" "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1"
uninstall:
rm -f "$(DESTDIR)$(PREFIX)/bin/cpufetch"
rm -f "$(DESTDIR)$(PREFIX)/share/licenses/cpufetch-git/LICENSE"
rm -f "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1.gz"
rm -f "$(DESTDIR)$(PREFIX)/share/man/man1/cpufetch.1"

View File

@@ -45,6 +45,7 @@ cpufetch is a command-line tool written in C that displays the CPU information i
- [3.1 x86_64](#31-x86_64)
- [3.2 ARM](#32-arm)
- [3.3 PowerPC](#33-powerpc)
- [3.4 RISC-V](#34-risc-v)
- [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)
@@ -120,6 +121,11 @@ make
<p align="center"><img width=90% src="pictures/ibm.png"></p>
<p align="center">Talos II</p>
## 3.4 RISC-V
<p align="center"><img width=80% src="pictures/starfive.png"></p>
<p align="center">StarFive VisionFive 2</p>
## 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:
@@ -175,6 +181,7 @@ Thanks to the fellow contributors and interested people in the project. Special
- [mdoksa76](https://github.com/mdoksa76) and [exkc](https://github.com/exkc): Excellent ideas and feedback for supporting Allwinner SoCs.
- [Sakura286](https://github.com/Sakura286), [exkc](https://github.com/exkc) and [Patola](https://github.com/Patola): Helped with RISC-V port with ssh access, ideas, testing, etc.
- [ThomasKaiser](https://github.com/ThomasKaiser): Very valuable feedback on improving ARM SoC detection (Apple, Allwinner, Rockchip).
- [zerkerX](https://github.com/zerkerX): Helped with feedback for supporting old (e.g., Pentium III) Intel CPUs.
## 8. cpufetch for GPUs (gpufetch)
See [gpufetch](https://github.com/Dr-Noob/gpufetch) project!

BIN
pictures/starfive.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 42 KiB

View File

@@ -8,15 +8,18 @@
#ifdef __linux__
#include <sys/auxv.h>
#include <asm/hwcap.h>
#include "../common/freq.h"
#elif defined __APPLE__ || __MACH__
#include "sysctl.h"
#include "../common/sysctl.h"
#endif
#include "../common/global.h"
#include "../common/soc.h"
#include "../common/args.h"
#include "udev.h"
#include "midr.h"
#include "uarch.h"
#include "sve.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];
@@ -39,8 +42,17 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(uint32_t core) {
struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(core);
#ifdef __linux__
if (freq->max == UNKNOWN_DATA || measure_max_frequency_flag()) {
if (freq->max == UNKNOWN_DATA)
printWarn("Unable to find max frequency from udev, measuring CPU frequency");
freq->max = measure_max_frequency(core);
freq->measured = true;
}
#endif
return freq;
}
@@ -157,6 +169,17 @@ struct features* get_features_info(void) {
feat->SHA1 = hwcaps & HWCAP_SHA1;
feat->SHA2 = hwcaps & HWCAP_SHA2;
feat->NEON = hwcaps & HWCAP_ASIMD;
feat->SVE = hwcaps & HWCAP_SVE;
hwcaps = getauxval(AT_HWCAP2);
if (errno == ENOENT) {
printWarn("Unable to retrieve AT_HWCAP2 using getauxval");
}
else {
#ifdef HWCAP2_SVE2
feat->SVE2 = hwcaps & HWCAP2_SVE2;
#endif
}
}
#else
else {
@@ -172,6 +195,8 @@ struct features* get_features_info(void) {
feat->CRC32 = hwcaps & HWCAP2_CRC32;
feat->SHA1 = hwcaps & HWCAP2_SHA1;
feat->SHA2 = hwcaps & HWCAP2_SHA2;
feat->SVE = false;
feat->SVE2 = false;
}
#endif // ifdef __aarch64__
#elif defined __APPLE__ || __MACH__
@@ -181,8 +206,14 @@ struct features* get_features_info(void) {
feat->SHA1 = true;
feat->SHA2 = true;
feat->NEON = true;
feat->SVE = false;
feat->SVE2 = false;
#endif // ifdef __linux__
if (feat->SVE || feat->SVE2) {
feat->cntb = sve_cntb();
}
return feat;
}
@@ -383,6 +414,7 @@ struct cpuInfo* get_cpu_info_mach(struct cpuInfo* cpu) {
cpu->peak_performance = get_peak_performance(cpu);
}
else if(cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_2 ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_PRO ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_MAX) {
fill_cpu_info_everest_sawtooth(cpu, pcores, ecores);
@@ -419,7 +451,7 @@ char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_soc
char* get_str_features(struct cpuInfo* cpu) {
struct features* feat = cpu->feat;
uint32_t max_len = strlen("NEON,SHA1,SHA2,AES,CRC32,") + 1;
uint32_t max_len = strlen("NEON,SHA1,SHA2,AES,CRC32,SVE,SVE2,") + 1;
uint32_t len = 0;
char* string = ecalloc(max_len, sizeof(char));
@@ -427,6 +459,14 @@ char* get_str_features(struct cpuInfo* cpu) {
strcat(string, "NEON,");
len += 5;
}
if(feat->SVE) {
strcat(string, "SVE,");
len += 4;
}
if(feat->SVE2) {
strcat(string, "SVE2,");
len += 5;
}
if(feat->SHA1) {
strcat(string, "SHA1,");
len += 5;
@@ -476,6 +516,10 @@ void print_debug(struct cpuInfo* cpu) {
}
}
if (cpu->feat->SVE || cpu->feat->SVE2) {
printf("- cntb: %d\n", (int) cpu->feat->cntb);
}
#if defined(__APPLE__) || defined(__MACH__)
printf("hw.cpufamily: 0x%.8X\n", get_sys_info_by_name("hw.cpufamily"));
printf("hw.cpusubfamily: 0x%.8X\n", get_sys_info_by_name("hw.cpusubfamily"));

View File

@@ -8,15 +8,21 @@
#include "udev.h"
#include "uarch.h"
#include "../common/global.h"
#include "../common/pci.h"
#if defined(__APPLE__) || defined(__MACH__)
#include "sysctl.h"
#include "../common/sysctl.h"
#endif
#define NA -1
#define min(a,b) (((a)<(b))?(a):(b))
#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
#define PROP_MTK_PLATFORM "ro.mediatek.platform"
#define PROP_SOC_MODEL "ro.soc.model"
#define PROP_PRODUCT_BOARD "ro.product.board"
#define PROP_BOARD_PLATFORM "ro.board.platform"
static char* soc_rpi_string[] = {
"BCM2835",
"BCM2836",
@@ -27,8 +33,7 @@ static char* soc_rpi_string[] = {
char* toupperstr(char* str) {
int len = strlen(str) + 1;
char* ret = emalloc(sizeof(char) * len);
memset(ret, 0, sizeof(char) * len);
char* ret = ecalloc(len, sizeof(char));
for(int i=0; i < len; i++) {
ret[i] = toupper((unsigned char) str[i]);
@@ -101,7 +106,7 @@ bool get_sunxisoc_from_sid(struct system_on_chip* soc, char* raw_name, uint32_t
int index = 0;
while(socFromSid[index].sid != 0x0) {
if(socFromSid[index].sid == sid) {
fill_soc(soc, socFromSid[index].soc.soc_name, socFromSid[index].soc.soc_model, socFromSid[index].soc.process);
fill_soc(soc, socFromSid[index].soc.name, socFromSid[index].soc.model, socFromSid[index].soc.process);
return true;
}
index++;
@@ -127,24 +132,24 @@ bool match_broadcom(char* soc_name, struct system_on_chip* soc) {
if((tmp = strstr(soc_name, "BCM")) == NULL)
return false;
soc->soc_vendor = SOC_VENDOR_BROADCOM;
soc->vendor = SOC_VENDOR_BROADCOM;
SOC_START
SOC_EQ(tmp, "BCM2835", "2835", SOC_BCM_2835, soc, 65)
SOC_EQ(tmp, "BCM2836", "2836", SOC_BCM_2836, soc, 40)
SOC_EQ(tmp, "BCM2837", "2837", SOC_BCM_2837, soc, 40)
SOC_EQ(tmp, "BCM2837B0", "2837B0", SOC_BCM_2837B0, soc, 40)
SOC_EQ(tmp, "BCM21553", "21553", SOC_BCM_21553, soc, 65)
SOC_EQ(tmp, "BCM21553-Thunderbird", "21553 Thunderbird", SOC_BCM_21553T, soc, 65)
SOC_EQ(tmp, "BCM21663", "21663", SOC_BCM_21663, soc, 40)
SOC_EQ(tmp, "BCM21664", "21664", SOC_BCM_21664, soc, 40)
SOC_EQ(tmp, "BCM28155", "28155", SOC_BCM_28155, soc, 40)
SOC_EQ(tmp, "BCM23550", "23550", SOC_BCM_23550, soc, 40)
SOC_EQ(tmp, "BCM28145", "28145", SOC_BCM_28145, soc, 40)
SOC_EQ(tmp, "BCM2157", "2157", SOC_BCM_2157, soc, 65)
SOC_EQ(tmp, "BCM21654", "21654", SOC_BCM_21654, soc, 40)
SOC_EQ(tmp, "BCM2711", "2711", SOC_BCM_2711, soc, 28)
SOC_EQ(tmp, "BCM2712", "2712", SOC_BCM_2712, soc, 16)
SOC_EQ(tmp, "BCM2835", "BCM2835", SOC_BCM_2835, soc, 65)
SOC_EQ(tmp, "BCM2836", "BCM2836", SOC_BCM_2836, soc, 40)
SOC_EQ(tmp, "BCM2837", "BCM2837", SOC_BCM_2837, soc, 40)
SOC_EQ(tmp, "BCM2837B0", "BCM2837B0", SOC_BCM_2837B0, soc, 40)
SOC_EQ(tmp, "BCM21553", "BCM21553", SOC_BCM_21553, soc, 65)
SOC_EQ(tmp, "BCM21553-Thunderbird", "BCM21553 Thunderbird", SOC_BCM_21553T, soc, 65)
SOC_EQ(tmp, "BCM21663", "BCM21663", SOC_BCM_21663, soc, 40)
SOC_EQ(tmp, "BCM21664", "BCM21664", SOC_BCM_21664, soc, 40)
SOC_EQ(tmp, "BCM28155", "BCM28155", SOC_BCM_28155, soc, 40)
SOC_EQ(tmp, "BCM23550", "BCM23550", SOC_BCM_23550, soc, 40)
SOC_EQ(tmp, "BCM28145", "BCM28145", SOC_BCM_28145, soc, 40)
SOC_EQ(tmp, "BCM2157", "BCM2157", SOC_BCM_2157, soc, 65)
SOC_EQ(tmp, "BCM21654", "BCM21654", SOC_BCM_21654, soc, 40)
SOC_EQ(tmp, "BCM2711", "BCM2711", SOC_BCM_2711, soc, 28)
SOC_EQ(tmp, "BCM2712", "BCM2712", SOC_BCM_2712, soc, 16)
SOC_END
}
@@ -155,7 +160,7 @@ bool match_google(char* soc_name, struct system_on_chip* soc) {
if((tmp = strstr(soc_name, "gs")) == NULL)
return false;
soc->soc_vendor = SOC_VENDOR_GOOGLE;
soc->vendor = SOC_VENDOR_GOOGLE;
SOC_START
SOC_EQ(tmp, "gs101", "Tensor", SOC_GOOGLE_TENSOR, soc, 5)
@@ -166,13 +171,15 @@ bool match_google(char* soc_name, struct system_on_chip* soc) {
// https://www.techinsights.com/
// https://datasheetspdf.com/pdf-file/1316605/HiSilicon/Hi3660/1
// https://github.com/Dr-Noob/cpufetch/issues/259
bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
char* tmp;
if((tmp = strstr(soc_name, "hi")) == NULL)
return false;
if((tmp = strstr(soc_name, "hi")) != NULL);
else if((tmp = strstr(soc_name, "kirin")) != NULL);
else return false;
soc->soc_vendor = SOC_VENDOR_KIRIN;
soc->vendor = SOC_VENDOR_KIRIN;
SOC_START
SOC_EQ(tmp, "hi3620GFC", "K3V2", SOC_HISILICON_3620, soc, 40)
@@ -203,6 +210,7 @@ bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
SOC_EQ(tmp, "hi3680", "980", SOC_HISILICON_3680, soc, 7)
//SOC_EQ(tmp, "?", "985", SOC_KIRIN, soc, 7)
SOC_EQ(tmp, "hi3690", "990", SOC_HISILICON_3690, soc, 7)
SOC_EQ(tmp, "kirin9000s", "9000s", SOC_HISILICON_9000S,soc, 7)
SOC_END
}
@@ -213,7 +221,7 @@ bool match_exynos(char* soc_name, struct system_on_chip* soc) {
else if((tmp = strstr(soc_name, "exynos")) != NULL);
else return false;
soc->soc_vendor = SOC_VENDOR_EXYNOS;
soc->vendor = SOC_VENDOR_EXYNOS;
// Because exynos are recently using "exynosXXXX" instead
// of "universalXXXX" as codenames, SOC_EXY_EQ will check for
@@ -273,7 +281,7 @@ bool match_mediatek(char* soc_name, struct system_on_chip* soc) {
if((tmp = strstr(soc_name_upper, "MT")) == NULL)
return false;
soc->soc_vendor = SOC_VENDOR_MEDIATEK;
soc->vendor = SOC_VENDOR_MEDIATEK;
SOC_START
// Dimensity //
@@ -420,6 +428,9 @@ bool match_mediatek(char* soc_name, struct system_on_chip* soc) {
}
/*
* Good sources:
* https://www.geektopia.es/es/products/company/qualcomm/socs/
*
* APQ: Application Processor Qualcomm
* MSM: Mobile Station Modem
* In a APQXXXX or MSMXXXX, the second digit represents:
@@ -453,7 +464,7 @@ bool match_qualcomm(char* soc_name, struct system_on_chip* soc) {
else if((tmp = strstr(soc_name_upper, "QSD")) != NULL);
else return false;
soc->soc_vendor = SOC_VENDOR_SNAPDRAGON;
soc->vendor = SOC_VENDOR_SNAPDRAGON;
SOC_START
// Snapdragon S1 //
@@ -577,6 +588,25 @@ bool match_qualcomm(char* soc_name, struct system_on_chip* soc) {
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)
// Snapdragon Gen 4 //
SOC_EQ(tmp, "SM4375", "4 Gen 1", SOC_SNAPD_SM4375, soc, 6)
SOC_EQ(tmp, "SM4450", "4 Gen 2", SOC_SNAPD_SM4450, soc, 4)
SOC_EQ(tmp, "SM4635", "4s Gen 2", SOC_SNAPD_SM4635, soc, 4)
// Snapdragon Gen 6 //
SOC_EQ(tmp, "SM6375-AC", "6s Gen 3", SOC_SNAPD_SM6375_AC, soc, 6)
SOC_EQ(tmp, "SM6450", "6 Gen 1", SOC_SNAPD_SM6450, soc, 4)
// Snapdragon Gen 7 //
SOC_EQ(tmp, "SM7435-AB", "7s Gen 2", SOC_SNAPD_SM7435_AB, soc, 4)
SOC_EQ(tmp, "SM7450", "7 Gen 1", SOC_SNAPD_SM7450, soc, 4)
SOC_EQ(tmp, "SM7475", "7+ Gen 2", SOC_SNAPD_SM7475, soc, 4)
SOC_EQ(tmp, "SM7550-AB", "7 Gen 3", SOC_SNAPD_SM7550_AB, soc, 4)
SOC_EQ(tmp, "SM7675-AB", "7+ Gen 3", SOC_SNAPD_SM7675_AB, soc, 4)
// Snapdragon Gen 8 //
SOC_EQ(tmp, "SM8450", "8 Gen 1", SOC_SNAPD_SM8450, soc, 4)
SOC_EQ(tmp, "SM8475", "8+ Gen 1", SOC_SNAPD_SM8475, soc, 4)
SOC_EQ(tmp, "SM8550-AB", "8 Gen 2", SOC_SNAPD_SM8550_AB, soc, 4)
SOC_EQ(tmp, "SM8635", "8s Gen 3", SOC_SNAPD_SM8635, soc, 4)
SOC_EQ(tmp, "SM8650-AB", "8 Gen 3", SOC_SNAPD_SM8650_AB, soc, 4)
SOC_END
}
@@ -587,7 +617,7 @@ bool match_allwinner(char* soc_name, struct system_on_chip* soc) {
if((tmp = strstr(soc_name, "sun")) == NULL)
return false;
soc->soc_vendor = SOC_VENDOR_ALLWINNER;
soc->vendor = SOC_VENDOR_ALLWINNER;
SOC_START
// SoCs we can detect just with with the name
@@ -623,12 +653,37 @@ bool match_special(char* soc_name, struct system_on_chip* soc) {
return true;
}
// Snapdragon 8 Gen 1 reported as "taro"
// New Snapdragon SoCs codenames
// https://github.com/sm8450-mainline/fdt?tab=readme-ov-file#chipsets
// https://github.com/Dr-Noob/cpufetch/issues/253
if (strcmp(soc_name, "cape") == 0) {
fill_soc(soc, "8+ Gen 1", SOC_SNAPD_SM8475, 4);
return true;
}
if(strcmp(soc_name, "taro") == 0) {
fill_soc(soc, "8 Gen 1", SOC_SNAPD_SM8450, 4);
return true;
}
if(strcmp(soc_name, "ukee") == 0) {
fill_soc(soc, "7+ Gen 2", SOC_SNAPD_SM7475, 4);
return true;
}
if(strcmp(soc_name, "diwali") == 0) {
fill_soc(soc, "7 Gen 1", SOC_SNAPD_SM7450, 4);
return true;
}
// parrot can be either SM7435 or SM6450, we need more data
// to distingish between those two
if(strcmp(soc_name, "ravelin") == 0) {
fill_soc(soc, "4 Gen 2", SOC_SNAPD_SM4450, 4);
return true;
}
// Google Pixel 6
// https://github.com/Dr-Noob/cpufetch/issues/134
if(strcmp(soc_name, "oriole") == 0) {
@@ -686,7 +741,7 @@ void try_parse_soc_from_string(struct system_on_chip* soc, int soc_len, char* so
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;
soc->vendor = SOC_VENDOR_UNKNOWN;
parse_soc_from_string(soc);
}
@@ -694,24 +749,34 @@ 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);
property_len = android_property_get(PROP_MTK_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);
if(soc->vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property %s: %s", PROP_MTK_PLATFORM, tmp);
else return soc;
}
property_len = android_property_get("ro.product.board", (char *) &tmp);
// https://github.com/Dr-Noob/cpufetch/issues/253
// ro.soc.model might be more reliable than ro.product.board or
// ro.board.platform, so try with it first
property_len = android_property_get(PROP_SOC_MODEL, (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);
if(soc->vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property %s: %s", PROP_SOC_MODEL, tmp);
else return soc;
}
property_len = android_property_get("ro.board.platform", (char *) &tmp);
property_len = android_property_get(PROP_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.board.platform: %s", tmp);
if(soc->vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property %s: %s", PROP_PRODUCT_BOARD, tmp);
else return soc;
}
property_len = android_property_get(PROP_BOARD_PLATFORM, (char *) &tmp);
if(property_len > 0) {
try_parse_soc_from_string(soc, property_len, tmp);
if(soc->vendor == SOC_VENDOR_UNKNOWN) printWarn("SoC detection failed using Android property %s: %s", PROP_BOARD_PLATFORM, tmp);
else return soc;
}
@@ -777,7 +842,7 @@ bool get_rk_soc_from_efuse(struct system_on_chip* soc, char* efuse) {
int index = 0;
while(socFromRK[index].rk_soc != 0x0) {
if(socFromRK[index].rk_soc == rk_soc) {
fill_soc(soc, socFromRK[index].soc.soc_name, socFromRK[index].soc.soc_model, socFromRK[index].soc.process);
fill_soc(soc, socFromRK[index].soc.name, socFromRK[index].soc.model, socFromRK[index].soc.process);
return true;
}
index++;
@@ -824,7 +889,7 @@ struct system_on_chip* guess_soc_from_uarch(struct system_on_chip* soc, struct c
int index = 0;
while(socFromUarch[index].u != UARCH_UNKNOWN) {
if(socFromUarch[index].u == get_uarch(arch)) {
fill_soc(soc, socFromUarch[index].soc.soc_name, socFromUarch[index].soc.soc_model, socFromUarch[index].soc.process);
fill_soc(soc, socFromUarch[index].soc.name, socFromUarch[index].soc.model, socFromUarch[index].soc.process);
return soc;
}
index++;
@@ -834,6 +899,141 @@ struct system_on_chip* guess_soc_from_uarch(struct system_on_chip* soc, struct c
return soc;
}
// Return the dt string without the NULL characters.
char* get_dt_str(char* dt, int filelen) {
char* dt_without_null = (char *) malloc(sizeof(char) * filelen);
memcpy(dt_without_null, dt, filelen);
for (int i=0; i < filelen-1; i++) {
if (dt_without_null[i] == '\0')
dt_without_null[i] = ',';
}
return dt_without_null;
}
bool match_dt(struct system_on_chip* soc, char* dt, int filelen, char* expected_name, char* soc_name, SOC soc_model, int32_t process) {
// The /proc/device-tree/compatible file (passed by dt) uses NULL
// to separate the strings, so we need to make an special case here
// and iterate over the NULL characters, thus iterating over each
// individual compatible strings.
if (strstr(dt, expected_name) != NULL) {
fill_soc(soc, soc_name, soc_model, process);
return true;
}
char *compatible = dt;
char *end_of_dt = dt + filelen;
while ((compatible = strchr(compatible, '\0')) != end_of_dt) {
compatible++;
if (strstr(compatible, expected_name) != NULL) {
fill_soc(soc, soc_name, soc_model, process);
return true;
}
}
return false;
}
#define DT_START if (false) {}
#define DT_EQ(dt, filelen, soc, expected_name, soc_name, soc_model, process) \
else if (match_dt(soc, dt, filelen, expected_name, soc_name, soc_model, process)) return soc;
#define DT_END(dt, filelen) else { printWarn("guess_soc_from_devtree: No match found for '%s'", get_dt_str(dt, filelen)); return soc; }
// TODO: Move this to doc
// The number of fields seems non-standard, so for now it seems wiser
// to just get the entire string with all fields and just look for the
// substring.
// TODO: Implement this by going trough NULL-separated fields rather than
// using strstr.
// https://trac.gateworks.com/wiki/linux/devicetree
struct system_on_chip* guess_soc_from_devtree(struct system_on_chip* soc) {
int len;
char* dt = get_devtree_compatible(&len);
if (dt == NULL) {
return soc;
}
DT_START
// The following are internal codenames of Asahi Linux
// https://github.com/AsahiLinux/docs/wiki/Codenames
// https://github.com/Dr-Noob/cpufetch/issues/263
DT_EQ(dt, len, soc, "apple,t8103", "M1", SOC_APPLE_M1, 5)
DT_EQ(dt, len, soc, "apple,t6000", "M1 Pro", SOC_APPLE_M1_PRO, 5)
DT_EQ(dt, len, soc, "apple,t6001", "M1 Max", SOC_APPLE_M1_MAX, 5)
DT_EQ(dt, len, soc, "apple,t6002", "M1 Ultra", SOC_APPLE_M1_ULTRA, 5)
DT_EQ(dt, len, soc, "apple,t8112", "M2", SOC_APPLE_M2, 5)
DT_EQ(dt, len, soc, "apple,t6020", "M2 Pro", SOC_APPLE_M2_PRO, 5)
DT_EQ(dt, len, soc, "apple,t6021", "M2 Max", SOC_APPLE_M2_MAX, 5)
DT_EQ(dt, len, soc, "apple,t6022", "M2 Ultra", SOC_APPLE_M2_ULTRA, 5)
DT_EQ(dt, len, soc, "apple,t8122", "M3", SOC_APPLE_M3, 3)
DT_EQ(dt, len, soc, "apple,t6030", "M3 Pro", SOC_APPLE_M3_PRO, 3)
DT_EQ(dt, len, soc, "apple,t6031", "M3 Max", SOC_APPLE_M3_MAX, 3)
DT_EQ(dt, len, soc, "apple,t6034", "M3 Max", SOC_APPLE_M3_MAX, 3)
// NVIDIA
DT_EQ(dt, len, soc, "nvidia,tegra234", "Tegra Orin", SOC_TEGRA_ORIN, 8) // https://www.phoronix.com/news/NVIDIA-Orin-Tegra234-Audio, https://github.com/Dr-Noob/cpufetch/issues/275, https://en.wikipedia.org/wiki/Tegra#Orin
// Qualcomm now also in devtree...
// TODO: Integrate this with SOC_EQ
DT_EQ(dt, len, soc, "qcom,sc8280", "8cx Gen 3", SOC_SNAPD_SC8280XP, 5)
// grep -oR -h --color -E '"fsl,.*' *.dtsi | sort | uniq | cut -d ',' -f1-2 | grep -v '-'
// https://elixir.bootlin.com/linux/v6.10.6/source/arch/arm64/boot/dts/freescale
DT_EQ(dt, len, soc, "fsl,imx8qm", "i.MX 8QuadMax", SOC_NXP_IMX8QM, 28) // https://www.nxp.com/docs/en/fact-sheet/IMX8FAMFS.pdf
DT_EQ(dt, len, soc, "fsl,imx8qp", "i.MX 8QuadPlus", SOC_NXP_IMX8QP, 28) // Actually not in dtsi, compatible string is just a guess
DT_EQ(dt, len, soc, "fsl,imx8mp", "i.MX 8M Plus", SOC_NXP_IMX8MP, 14) // https://www.nxp.com/docs/en/fact-sheet/IMX8MPLUSFS.pdf https://github.com/Dr-Noob/cpufetch/issues/261
DT_EQ(dt, len, soc, "fsl,imx8mn", "i.MX 8M Nano", SOC_NXP_IMX8MN, NA)
DT_EQ(dt, len, soc, "fsl,imx8mm", "i.MX 8M Mini", SOC_NXP_IMX8MM, NA) // https://www.nxp.com/docs/en/fact-sheet/IMX8MMINIFS.pdf
DT_EQ(dt, len, soc, "fsl,imx8dxp", "i.MX 8DualXPlus", SOC_NXP_IMX8DXP, NA)
DT_EQ(dt, len, soc, "fsl,imx8qxp", "i.MX 8QuadXPlus", SOC_NXP_IMX8QXP, NA)
DT_EQ(dt, len, soc, "fsl,imx93", "i.MX 93", SOC_NXP_IMX93, NA)
// TODO: Add more Amlogic SoCs: https://elixir.bootlin.com/linux/v6.10.6/source/arch/arm64/boot/dts/amlogic
// https://github.com/Dr-Noob/cpufetch/issues/268
// https://www.amlogic.com/#Products/393/index.html
// https://wikimovel.com/index.php/Amlogic_A311D
DT_EQ(dt, len, soc, "amlogic,a311d", "A311D", SOC_AMLOGIC_A311D, 12)
// Marvell
DT_EQ(dt, len, soc, "marvell,armada3700", "Armada 3700", SOC_MARVELL_A3700, 28) // http://wiki.espressobin.net/tiki-index.php?page=Armada+3700 (pdf), https://github.com/Dr-Noob/cpufetch/issues/279
DT_END(dt, len)
}
struct system_on_chip* guess_soc_from_pci(struct system_on_chip* soc, struct cpuInfo* cpu) {
struct pci_devices * pci = get_pci_devices();
if (pci == NULL) {
printWarn("guess_soc_from_pci: Unable to find suitable PCI devices");
return soc;
}
typedef struct {
uint16_t vendor_id;
uint16_t device_id;
struct system_on_chip soc;
} pciToSoC;
pciToSoC socFromPCI[] = {
{PCI_VENDOR_NVIDIA, PCI_DEVICE_TEGRA_X1, {SOC_TEGRA_X1, SOC_VENDOR_NVIDIA, 20, "Tegra X1", NULL} },
// {PCI_VENDOR_NVIDIA, PCI_DEVICE_GH_200,{SOC_GH_200, SOC_VENDOR_NVIDIA, ?, "Grace Hopper", NULL} },
{PCI_VENDOR_AMPERE, PCI_DEVICE_ALTRA, {SOC_AMPERE_ALTRA, SOC_VENDOR_AMPERE, 7, "Altra", NULL} }, // https://www.anandtech.com/show/15575/amperes-altra-80-core-n1-soc-for-hyperscalers-against-rome-and-xeon
{0x0000, 0x0000, {UNKNOWN, SOC_VENDOR_UNKNOWN, -1, "", NULL} }
};
int index = 0;
while (socFromPCI[index].vendor_id != 0x0) {
for (int i=0; i < pci->num_devices; i++) {
struct pci_device * dev = pci->devices[i];
if (socFromPCI[index].vendor_id == dev->vendor_id &&
socFromPCI[index].device_id == dev->device_id) {
fill_soc(soc, socFromPCI[index].soc.name, socFromPCI[index].soc.model, socFromPCI[index].soc.process);
return soc;
}
}
index++;
}
printWarn("guess_soc_from_pci: No PCI device matched the list");
return soc;
}
int hex2int(char c) {
if (c >= '0' && c <= '9')
return c - '0';
@@ -907,12 +1107,12 @@ struct system_on_chip* guess_soc_apple(struct system_on_chip* soc) {
}
else {
printBug("Found invalid physical cpu number: %d", physicalcpu);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
}
else {
printBugCheckRelease("Found invalid cpu_subfamily: 0x%.8X", cpu_subfamily);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
}
else if(cpu_family == CPUFAMILY_ARM_AVALANCHE_BLIZZARD) {
@@ -934,19 +1134,21 @@ struct system_on_chip* guess_soc_apple(struct system_on_chip* soc) {
}
else {
printBug("Found invalid physical cpu number: %d", physicalcpu);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
}
else {
printBugCheckRelease("Found invalid cpu_subfamily: 0x%.8X", cpu_subfamily);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
}
else if(cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_2 ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_PRO ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_MAX) {
// Check M3 version
if(cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH) {
if(cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH ||
cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_2) {
fill_soc(soc, "M3", SOC_APPLE_M3, 3);
}
else if(cpu_family == CPUFAMILY_ARM_EVEREST_SAWTOOTH_PRO) {
@@ -957,12 +1159,12 @@ struct system_on_chip* guess_soc_apple(struct system_on_chip* soc) {
}
else {
printBugCheckRelease("Found invalid cpu_family: 0x%.8X", cpu_family);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
}
else {
printBugCheckRelease("Found invalid cpu_family: 0x%.8X", cpu_family);
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
}
return soc;
}
@@ -971,15 +1173,15 @@ struct system_on_chip* guess_soc_apple(struct system_on_chip* soc) {
struct system_on_chip* get_soc(struct cpuInfo* cpu) {
struct system_on_chip* soc = emalloc(sizeof(struct system_on_chip));
soc->raw_name = NULL;
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->soc_model = SOC_MODEL_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
soc->model = SOC_MODEL_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) {
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
printErr("[RPi] SoC detection failed using revision code, falling back to cpuinfo detection");
}
else {
@@ -988,7 +1190,7 @@ struct system_on_chip* get_soc(struct cpuInfo* cpu) {
}
soc = guess_soc_from_cpuinfo(soc);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
if(soc->raw_name != NULL) {
printWarn("SoC detection failed using /proc/cpuinfo: Found '%s' string", soc->raw_name);
}
@@ -1000,22 +1202,30 @@ struct system_on_chip* get_soc(struct cpuInfo* cpu) {
if(soc->raw_name == NULL) {
printWarn("SoC detection failed using Android: No string found");
}
else if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
else if(soc->vendor == SOC_VENDOR_UNKNOWN) {
printWarn("SoC detection failed using Android: Found '%s' string", soc->raw_name);
}
#endif // ifdef __ANDROID__
// If cpufinfo/Android (if available) detection fails, try with nvmem
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
// If previous steps failed, try with the device tree
if (soc->vendor == SOC_VENDOR_UNKNOWN) {
soc = guess_soc_from_devtree(soc);
}
// If previous steps failed, try with nvmem
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
soc = guess_soc_from_nvmem(soc);
}
// If everything else failed, try infering it from the microarchitecture
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
// If previous steps failed, try infering it from the microarchitecture
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
soc = guess_soc_from_uarch(soc, cpu);
}
// If previous steps failed, try infering it from the pci device id
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
soc = guess_soc_from_pci(soc, cpu);
}
}
#elif defined __APPLE__ || __MACH__
soc = guess_soc_apple(soc);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
printWarn("SoC detection failed using cpu_subfamily");
}
else {
@@ -1023,7 +1233,7 @@ struct system_on_chip* get_soc(struct cpuInfo* cpu) {
}
#endif // ifdef __linux__
if(soc->soc_model == SOC_MODEL_UNKNOWN) {
if(soc->model == SOC_MODEL_UNKNOWN) {
// raw_name might not be NULL, but if we were unable to find
// the exact SoC, just print "Unkwnown"
soc->raw_name = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));

View File

@@ -29,6 +29,7 @@ enum {
SOC_HISILICON_3670,
SOC_HISILICON_3680,
SOC_HISILICON_3690,
SOC_HISILICON_9000S,
// Kunpeng //
SOC_KUNPENG_920,
SOC_KUNPENG_930,
@@ -270,11 +271,16 @@ enum {
SOC_SNAPD_SDM660,
SOC_SNAPD_SM6115,
SOC_SNAPD_SM6125,
SOC_SNAPD_SM6375_AC,
SOC_SNAPD_SM6450,
SOC_SNAPD_SDM670,
SOC_SNAPD_SM6150,
SOC_SNAPD_SM6350,
SOC_SNAPD_SDM710,
SOC_SNAPD_SDM712,
SOC_SNAPD_SM4375,
SOC_SNAPD_SM4450,
SOC_SNAPD_SM4635,
SOC_SNAPD_SM7125,
SOC_SNAPD_SM7150_AA,
SOC_SNAPD_SM7150_AB,
@@ -283,6 +289,11 @@ enum {
SOC_SNAPD_SM7250_AA,
SOC_SNAPD_SM7250_AB,
SOC_SNAPD_SM7250_AC,
SOC_SNAPD_SM7435_AB,
SOC_SNAPD_SM7450,
SOC_SNAPD_SM7475,
SOC_SNAPD_SM7550_AB,
SOC_SNAPD_SM7675_AB,
SOC_SNAPD_MSM8974AA,
SOC_SNAPD_MSM8974AB,
SOC_SNAPD_MSM8974AC,
@@ -303,6 +314,11 @@ enum {
SOC_SNAPD_SM8250_AB,
SOC_SNAPD_SM8350,
SOC_SNAPD_SM8450,
SOC_SNAPD_SM8475,
SOC_SNAPD_SM8550_AB,
SOC_SNAPD_SM8635,
SOC_SNAPD_SM8650_AB,
SOC_SNAPD_SC8280XP,
// APPLE
SOC_APPLE_M1,
SOC_APPLE_M1_PRO,
@@ -363,21 +379,44 @@ enum {
SOC_GOOGLE_TENSOR,
SOC_GOOGLE_TENSOR_G2,
SOC_GOOGLE_TENSOR_G3,
// NVIDIA,
SOC_TEGRA_X1,
SOC_TEGRA_ORIN,
// ALTRA
SOC_AMPERE_ALTRA,
// NXP
SOC_NXP_IMX8QM,
SOC_NXP_IMX8QP,
SOC_NXP_IMX8MP,
SOC_NXP_IMX8MN,
SOC_NXP_IMX8MM,
SOC_NXP_IMX8DXP,
SOC_NXP_IMX8QXP,
SOC_NXP_IMX93,
// AMLOGIC
SOC_AMLOGIC_A311D,
// MARVELL
SOC_MARVELL_A3700,
// UNKNOWN
SOC_MODEL_UNKNOWN
};
inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
if(soc >= SOC_BCM_2835 && soc <= SOC_BCM_2712) return SOC_VENDOR_BROADCOM;
else if(soc >= SOC_HISILICON_3620 && soc <= SOC_HISILICON_3690) return SOC_VENDOR_KIRIN;
else if(soc >= SOC_HISILICON_3620 && soc <= SOC_HISILICON_9000S) return SOC_VENDOR_KIRIN;
else if(soc >= SOC_KUNPENG_920 && soc <= SOC_KUNPENG_930) return SOC_VENDOR_KUNPENG;
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_SNAPD_QSD8650 && soc <= SOC_SNAPD_SM8450) return SOC_VENDOR_SNAPDRAGON;
else if(soc >= SOC_SNAPD_QSD8650 && soc <= SOC_SNAPD_SC8280XP) return SOC_VENDOR_SNAPDRAGON;
else if(soc >= SOC_APPLE_M1 && soc <= SOC_APPLE_M3_MAX) return SOC_VENDOR_APPLE;
else if(soc >= SOC_ALLWINNER_A10 && soc <= SOC_ALLWINNER_R328) return SOC_VENDOR_ALLWINNER;
else if(soc >= SOC_ROCKCHIP_3288 && soc <= SOC_ROCKCHIP_3588) return SOC_VENDOR_ROCKCHIP;
else if(soc >= SOC_GOOGLE_TENSOR && soc <= SOC_GOOGLE_TENSOR_G3) return SOC_VENDOR_GOOGLE;
else if(soc >= SOC_TEGRA_X1 && soc <= SOC_TEGRA_ORIN) return SOC_VENDOR_NVIDIA;
else if(soc >= SOC_AMPERE_ALTRA && soc <= SOC_AMPERE_ALTRA) return SOC_VENDOR_AMPERE;
else if(soc >= SOC_NXP_IMX8QM && soc <= SOC_NXP_IMX93) return SOC_VENDOR_NXP;
else if(soc >= SOC_AMLOGIC_A311D && soc <= SOC_AMLOGIC_A311D) return SOC_VENDOR_AMLOGIC;
else if(soc >= SOC_MARVELL_A3700 && soc <= SOC_MARVELL_A3700) return SOC_VENDOR_MARVELL;
return SOC_VENDOR_UNKNOWN;
}

15
src/arm/sve.c Normal file
View File

@@ -0,0 +1,15 @@
#include <stdint.h>
#include "../common/global.h"
// https://learn.arm.com/learning-paths/servers-and-cloud-computing/sve/sve_basics/#:~:text=Using%20a%20text%20editor%20of%20your%20choice%2C%20copy,svcntb%28%29%29%3B%20%7D%20This%20program%20prints%20the%20vector%20length
uint64_t sve_cntb(void) {
#ifdef __ARM_FEATURE_SVE
uint64_t x0 = 0;
__asm volatile("cntb %0"
: "=r"(x0));
return x0;
#else
printWarn("sve_cntb: Hardware supports SVE, but it was not enabled by the compiler");
return 0;
#endif
}

6
src/arm/sve.h Normal file
View File

@@ -0,0 +1,6 @@
#ifndef __SVE_DETECTION__
#define __SVE_DETECTION__
uint64_t sve_cntb(void);
#endif

View File

@@ -33,7 +33,9 @@ enum {
ISA_ARMv8_3_A,
ISA_ARMv8_4_A,
ISA_ARMv8_5_A,
ISA_ARMv9_A
ISA_ARMv8_6_A,
ISA_ARMv9_A,
ISA_ARMv9_2_A
};
static const ISA isas_uarch[] = {
@@ -61,20 +63,32 @@ 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_A78C] = ISA_ARMv8_2_A,
[UARCH_CORTEX_A78AE] = ISA_ARMv8_2_A,
[UARCH_CORTEX_A510] = ISA_ARMv9_A,
[UARCH_CORTEX_A520] = ISA_ARMv9_2_A,
[UARCH_CORTEX_A710] = ISA_ARMv9_A,
[UARCH_CORTEX_A715] = ISA_ARMv9_A,
[UARCH_CORTEX_A720] = ISA_ARMv9_2_A,
[UARCH_CORTEX_A725] = ISA_ARMv9_2_A,
[UARCH_CORTEX_X1] = ISA_ARMv8_2_A,
[UARCH_CORTEX_X1C] = ISA_ARMv8_2_A, // Assuming same as X1
[UARCH_CORTEX_X2] = ISA_ARMv9_A,
[UARCH_CORTEX_X3] = ISA_ARMv9_A,
[UARCH_CORTEX_X4] = ISA_ARMv9_2_A,
[UARCH_CORTEX_X925] = ISA_ARMv9_2_A,
[UARCH_NEOVERSE_N1] = ISA_ARMv8_2_A,
[UARCH_NEOVERSE_N2] = ISA_ARMv9_A,
[UARCH_NEOVERSE_E1] = ISA_ARMv8_2_A,
[UARCH_NEOVERSE_V1] = ISA_ARMv8_4_A,
[UARCH_NEOVERSE_V2] = ISA_ARMv9_A,
[UARCH_NEOVERSE_V3] = ISA_ARMv9_2_A,
[UARCH_BRAHMA_B15] = ISA_ARMv7_A, // Same as Cortex-A15
[UARCH_BRAHMA_B53] = ISA_ARMv8_A, // Same as Cortex-A53
[UARCH_THUNDERX] = ISA_ARMv8_A,
[UARCH_THUNDERX2] = ISA_ARMv8_1_A,
[UARCH_TAISHAN_V110] = ISA_ARMv8_2_A,
[UARCH_TAISHAN_V120] = ISA_ARMv8_2_A, // Not confirmed
[UARCH_TAISHAN_V200] = ISA_ARMv8_2_A, // Not confirmed
[UARCH_DENVER] = ISA_ARMv8_A,
[UARCH_DENVER2] = ISA_ARMv8_A,
@@ -92,8 +106,10 @@ static const ISA isas_uarch[] = {
[UARCH_EXYNOS_M5] = ISA_ARMv8_2_A,
[UARCH_ICESTORM] = ISA_ARMv8_5_A, // https://github.com/llvm/llvm-project/blob/main/llvm/include/llvm/Support/AArch64TargetParser.def
[UARCH_FIRESTORM] = ISA_ARMv8_5_A,
[UARCH_BLIZZARD] = ISA_ARMv8_5_A, // Not confirmed
[UARCH_AVALANCHE] = ISA_ARMv8_5_A,
[UARCH_BLIZZARD] = ISA_ARMv8_6_A, // https://github.com/llvm/llvm-project/blob/main/llvm/unittests/TargetParser/TargetParserTest.cpp
[UARCH_AVALANCHE] = ISA_ARMv8_6_A, // https://github.com/llvm/llvm-project/blob/main/llvm/unittests/TargetParser/TargetParserTest.cpp
[UARCH_SAWTOOTH] = ISA_ARMv8_6_A, // https://github.com/llvm/llvm-project/blob/main/llvm/unittests/TargetParser/TargetParserTest.cpp
[UARCH_EVEREST] = ISA_ARMv8_6_A, // https://github.com/llvm/llvm-project/blob/main/llvm/unittests/TargetParser/TargetParserTest.cpp
[UARCH_PJ4] = ISA_ARMv7_A,
[UARCH_XIAOMI] = ISA_ARMv8_A,
};
@@ -111,7 +127,9 @@ static char* isas_string[] = {
[ISA_ARMv8_3_A] = "ARMv8.3",
[ISA_ARMv8_4_A] = "ARMv8.4",
[ISA_ARMv8_5_A] = "ARMv8.5",
[ISA_ARMv9_A] = "ARMv9"
[ISA_ARMv8_6_A] = "ARMv8.6",
[ISA_ARMv9_A] = "ARMv9",
[ISA_ARMv9_2_A] = "ARMv9.2",
};
#define UARCH_START if (false) {}
@@ -183,13 +201,24 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
CHECK_UARCH(arch, cpu, 'A', 0xD0E, NA, NA, "Cortex-A76", UARCH_CORTEX_A76, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD40, NA, NA, "Neoverse V1", UARCH_NEOVERSE_V1, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD41, NA, NA, "Cortex-A78", UARCH_CORTEX_A78, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD42, NA, NA, "Cortex-A78AE", UARCH_CORTEX_A78AE, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD44, NA, NA, "Cortex-X1", UARCH_CORTEX_X1, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD46, NA, NA, "CortexA510", UARCH_CORTEX_A510, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD47, NA, NA, "CortexA710", UARCH_CORTEX_A710, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD48, NA, NA, "Cortex-X2", UARCH_CORTEX_X2, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD49, NA, NA, "Neoverse N2", UARCH_NEOVERSE_N2, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4A, NA, NA, "Neoverse E1", UARCH_NEOVERSE_E1, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4B, NA, NA, "Cortex-A78C", UARCH_CORTEX_A78C, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4C, NA, NA, "Cortex-X1C", UARCH_CORTEX_X1C, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4D, NA, NA, "Cortex-A715", UARCH_CORTEX_A715, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4E, NA, NA, "Cortex-X3", UARCH_CORTEX_X3, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD4F, NA, NA, "Neoverse V2", UARCH_NEOVERSE_V2, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD80, NA, NA, "Cortex-A520", UARCH_CORTEX_A520, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD81, NA, NA, "Cortex-A720", UARCH_CORTEX_A720, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD82, NA, NA, "Cortex-X4", UARCH_CORTEX_X4, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD84, NA, NA, "Neoverse V3", UARCH_NEOVERSE_V3, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD85, NA, NA, "Cortex-X925", UARCH_CORTEX_X925, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'A', 0xD87, NA, NA, "Cortex-A725", UARCH_CORTEX_A725, CPU_VENDOR_ARM)
CHECK_UARCH(arch, cpu, 'B', 0x00F, NA, NA, "Brahma B15", UARCH_BRAHMA_B15, CPU_VENDOR_BROADCOM)
CHECK_UARCH(arch, cpu, 'B', 0x100, NA, NA, "Brahma B53", UARCH_BRAHMA_B53, CPU_VENDOR_BROADCOM)
@@ -202,8 +231,10 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
CHECK_UARCH(arch, cpu, 'C', 0x0AF, NA, NA, "ThunderX2 99XX", UARCH_THUNDERX2, CPU_VENDOR_CAVIUM)
CHECK_UARCH(arch, cpu, 'H', 0xD01, NA, NA, "TaiShan v110", UARCH_TAISHAN_V110, CPU_VENDOR_HUAWEI) // Kunpeng 920 series
CHECK_UARCH(arch, cpu, 'H', 0xD02, 2, 2, "TaiShan v120", UARCH_TAISHAN_V120, CPU_VENDOR_HUAWEI) // Kiring 9000S Big cores (https://github.com/Dr-Noob/cpufetch/issues/259)
CHECK_UARCH(arch, cpu, 'H', 0xD02, NA, NA, "TaiShan v200", UARCH_TAISHAN_V200, CPU_VENDOR_HUAWEI) // Kunpeng 930 series (found in openeuler: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/XQCV7NX2UKRIUWUFKRF4PO3QENCOUFR3)
CHECK_UARCH(arch, cpu, 'H', 0xD40, NA, NA, "Cortex-A76", UARCH_CORTEX_A76, CPU_VENDOR_ARM) // Kirin 980 Big/Medium cores -> Cortex-A76
CHECK_UARCH(arch, cpu, 'H', 0xD42, NA, NA, "TaiShan v120", UARCH_TAISHAN_V120, CPU_VENDOR_HUAWEI) // Kiring 9000S Small Cores (https://github.com/Dr-Noob/cpufetch/issues/259)
CHECK_UARCH(arch, cpu, 'N', 0x000, NA, NA, "Denver", UARCH_DENVER, CPU_VENDOR_NVIDIA)
CHECK_UARCH(arch, cpu, 'N', 0x003, NA, NA, "Denver2", UARCH_DENVER2, CPU_VENDOR_NVIDIA)
@@ -245,6 +276,8 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
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, 'a', 0x024, NA, NA, "Icestorm", UARCH_ICESTORM, CPU_VENDOR_APPLE) // https://github.com/Dr-Noob/cpufetch/issues/263
CHECK_UARCH(arch, cpu, 'a', 0x025, NA, NA, "Firestorm", UARCH_FIRESTORM, CPU_VENDOR_APPLE) // https://github.com/Dr-Noob/cpufetch/issues/263
CHECK_UARCH(arch, cpu, 'a', 0x030, NA, NA, "Blizzard", UARCH_BLIZZARD, CPU_VENDOR_APPLE)
CHECK_UARCH(arch, cpu, 'a', 0x031, NA, NA, "Avalanche", UARCH_AVALANCHE, CPU_VENDOR_APPLE)
CHECK_UARCH(arch, cpu, 'a', 0x048, NA, NA, "Sawtooth", UARCH_SAWTOOTH, CPU_VENDOR_APPLE)
@@ -259,14 +292,7 @@ struct uarch* get_uarch_from_midr(uint32_t midr, struct cpuInfo* cpu) {
}
bool is_ARMv8_or_newer(struct cpuInfo* cpu) {
return cpu->arch->isa == ISA_ARMv8_A ||
cpu->arch->isa == ISA_ARMv8_A_AArch32 ||
cpu->arch->isa == ISA_ARMv8_1_A ||
cpu->arch->isa == ISA_ARMv8_2_A ||
cpu->arch->isa == ISA_ARMv8_3_A ||
cpu->arch->isa == ISA_ARMv8_4_A ||
cpu->arch->isa == ISA_ARMv8_5_A ||
cpu->arch->isa == ISA_ARMv9_A;
return cpu->arch->isa >= ISA_ARMv8_A;
}
bool has_fma_support(struct cpuInfo* cpu) {
@@ -279,19 +305,17 @@ int get_vpus_width(struct cpuInfo* cpu) {
// If the CPU has NEON, width can be 64 or 128 [1].
// In >= ARMv8, NEON are 128 bits width [2]
// If the CPU has SVE/SVE2, width can be between 128-2048 [3],
// so we must check the exact width depending on
// the exact chip (Neoverse V1 uses 256b implementations.)
// so we get the exact value from cntb [4]
//
// [1] https://en.wikipedia.org/wiki/ARM_architecture_family#Advanced_SIMD_(Neon)
// [2] https://developer.arm.com/documentation/102474/0100/Fundamentals-of-Armv8-Neon-technology
// [3] https://www.anandtech.com/show/16640/arm-announces-neoverse-v1-n2-platforms-cpus-cmn700-mesh/5
// [4] https://developer.arm.com/documentation/ddi0596/2020-12/SVE-Instructions/CNTB--CNTD--CNTH--CNTW--Set-scalar-to-multiple-of-predicate-constraint-element-count-
MICROARCH ua = cpu->arch->uarch;
switch(ua) {
case UARCH_NEOVERSE_V1:
return 256;
default:
if(cpu->feat->NEON) {
if (cpu->feat->SVE && cpu->feat->cntb > 0) {
return cpu->feat->cntb * 8;
}
else if (cpu->feat->NEON) {
if(is_ARMv8_or_newer(cpu)) {
return 128;
}
@@ -303,19 +327,24 @@ int get_vpus_width(struct cpuInfo* cpu) {
return 32;
}
}
}
int get_number_of_vpus(struct cpuInfo* cpu) {
MICROARCH ua = cpu->arch->uarch;
switch(ua) {
case UARCH_CORTEX_X925: // [https://www.anandtech.com/show/21399/arm-unveils-2024-cpu-core-designs-cortex-x925-a725-and-a520-arm-v9-2-redefined-for-3nm-/2]
return 6;
case UARCH_EVEREST: // Just a guess, needs confirmation.
case UARCH_FIRESTORM: // [https://dougallj.github.io/applecpu/firestorm-simd.html]
case UARCH_AVALANCHE: // [https://en.wikipedia.org/wiki/Comparison_of_ARM_processors]
case UARCH_CORTEX_X1: // [https://www.anandtech.com/show/15813/arm-cortex-a78-cortex-x1-cpu-ip-diverging/3]
case UARCH_CORTEX_X1C: // Assuming same as X1
case UARCH_CORTEX_X2: // [https://www.anandtech.com/show/16693/arm-announces-mobile-armv9-cpu-microarchitectures-cortexx2-cortexa710-cortexa510/2]
case UARCH_CORTEX_X3: // [https://www.hwcooling.net/en/cortex-x3-the-new-fastest-arm-core-architecture-analysis: "The FPU and SIMD unit of the core still has four pipelines"]
case UARCH_CORTEX_X4: // [https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/2]: "Cortex-X4: Out-of-Order Core"
case UARCH_NEOVERSE_V1: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/neoverse_v1]
case UARCH_NEOVERSE_V2: // [https://chipsandcheese.com/2023/09/11/hot-chips-2023-arms-neoverse-v2/]
case UARCH_NEOVERSE_V3: // Assuming same as V2
return 4;
case UARCH_SAWTOOTH: // Needs confirmation, rn this is the best we know: https://mastodon.social/@dougall/111118317031041336
case UARCH_EXYNOS_M3: // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
@@ -325,6 +354,7 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_ICESTORM: // [https://dougallj.github.io/applecpu/icestorm-simd.html]
case UARCH_BLIZZARD: // [https://en.wikipedia.org/wiki/Comparison_of_ARM_processors]
case UARCH_TAISHAN_V110:// [https://www-file.huawei.com/-/media/corp2020/pdf/publications/huawei-research/2022/huawei-research-issue1-en.pdf]: "128-bit x 2 for single precision"
case UARCH_TAISHAN_V120:// Not confirmed, asssuming same as v110
case UARCH_TAISHAN_V200:// Not confirmed, asssuming same as v110
case UARCH_CORTEX_A57: // [https://www.anandtech.com/show/8718/the-samsung-galaxy-note-4-exynos-review/5]
case UARCH_CORTEX_A72: // [https://www.anandtech.com/show/10347/arm-cortex-a73-artemis-unveiled/2]
@@ -333,16 +363,22 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_CORTEX_A76: // [https://www.anandtech.com/show/12785/arm-cortex-a76-cpu-unveiled-7nm-powerhouse/3]
case UARCH_CORTEX_A77: // [https://fuse.wikichip.org/news/2339/arm-unveils-cortex-a77-emphasizes-single-thread-performance]
case UARCH_CORTEX_A78: // [https://fuse.wikichip.org/news/3536/arm-unveils-the-cortex-a78-when-less-is-more]
case UARCH_CORTEX_A78C: // Assuming same as A78
case UARCH_CORTEX_A78AE:// Assuming same as A78
case UARCH_EXYNOS_M1: // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
case UARCH_EXYNOS_M2: // [https://www.anandtech.com/show/12361/samsung-exynos-m3-architecture]
case UARCH_NEOVERSE_N1: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/neoverse_n1#Individual_Core]
case UARCH_NEOVERSE_N2: // [https://chipsandcheese.com/2023/08/18/arms-neoverse-n2-cortex-a710-for-servers/]
case UARCH_CORTEX_A710: // [https://chipsandcheese.com/2023/08/11/arms-cortex-a710-winning-by-default/]: Fig in Core Overview. Table in Instruction Scheduling and Execution
case UARCH_CORTEX_A715: // [https://www.hwcooling.net/en/arm-introduces-new-cortex-a715-core-architecture-analysis/]: "the numbers of ALU and FPU execution units themselves >
case UARCH_CORTEX_A720: // Assuming same as A715: https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/3
case UARCH_CORTEX_A725: // Assuming same as A720
return 2;
case UARCH_NEOVERSE_E1: // [https://www.anandtech.com/show/13959/arm-announces-neoverse-n1-platform/5]
// A510 is integrated as part of a Complex. Normally, each complex would incorporate two Cortex-A510 cores.
// Each complex incorporates a single VPU with 2 ports, so for each A510 there is theoretically 1 port.
case UARCH_CORTEX_A510: // [https://en.wikichip.org/wiki/arm_holdings/microarchitectures/cortex-a510#Vector_Processing_Unit_.28VPU.29]
case UARCH_CORTEX_A520: // Assuming same as A50: https://www.anandtech.com/show/18871/arm-unveils-armv92-mobile-architecture-cortex-x4-a720-and-a520-64bit-exclusive/4
return 1;
default:
// ARMv6

View File

@@ -34,15 +34,26 @@ enum {
UARCH_CORTEX_A76,
UARCH_CORTEX_A77,
UARCH_CORTEX_A78,
UARCH_CORTEX_A78AE,
UARCH_CORTEX_A78C,
UARCH_CORTEX_A510,
UARCH_CORTEX_A520,
UARCH_CORTEX_A710,
UARCH_CORTEX_A715,
UARCH_CORTEX_A720,
UARCH_CORTEX_A725,
UARCH_CORTEX_X1,
UARCH_CORTEX_X1C,
UARCH_CORTEX_X2,
UARCH_CORTEX_X3,
UARCH_CORTEX_X4,
UARCH_CORTEX_X925,
UARCH_NEOVERSE_N1,
UARCH_NEOVERSE_N2,
UARCH_NEOVERSE_E1,
UARCH_NEOVERSE_V1,
UARCH_NEOVERSE_V2,
UARCH_NEOVERSE_V3,
UARCH_SCORPION,
UARCH_KRAIT,
UARCH_KYRO,
@@ -83,7 +94,9 @@ enum {
UARCH_BRAHMA_B15,
UARCH_BRAHMA_B53,
UARCH_XGENE, // Applied Micro X-Gene.
// HUAWEI
UARCH_TAISHAN_V110, // HiSilicon TaiShan v110
UARCH_TAISHAN_V120, // HiSilicon TaiShan v120
UARCH_TAISHAN_V200, // HiSilicon TaiShan v200
// PHYTIUM
UARCH_XIAOMI, // Not to be confused with Xiaomi Inc

View File

@@ -28,6 +28,7 @@ struct args_struct {
bool help_flag;
bool raw_flag;
bool accurate_pp;
bool measure_max_frequency_flag;
bool full_cpu_name_flag;
bool logo_long;
bool logo_short;
@@ -50,6 +51,7 @@ const char args_chr[] = {
/* [ARG_LOGO_INTEL_NEW] = */ 3,
/* [ARG_LOGO_INTEL_OLD] = */ 4,
/* [ARG_ACCURATE_PP] = */ 5,
/* [ARG_MEASURE_MAX_FREQ] = */ 6,
/* [ARG_DEBUG] = */ 'd',
/* [ARG_VERBOSE] = */ 'v',
/* [ARG_VERSION] = */ 'V',
@@ -66,6 +68,7 @@ const char *args_str[] = {
/* [ARG_LOGO_INTEL_NEW] = */ "logo-intel-new",
/* [ARG_LOGO_INTEL_OLD] = */ "logo-intel-old",
/* [ARG_ACCURATE_PP] = */ "accurate-pp",
/* [ARG_MEASURE_MAX_FREQ] = */ "measure-max-freq",
/* [ARG_DEBUG] = */ "debug",
/* [ARG_VERBOSE] = */ "verbose",
/* [ARG_VERSION] = */ "version",
@@ -101,6 +104,10 @@ bool accurate_pp(void) {
return args.accurate_pp;
}
bool measure_max_frequency_flag(void) {
return args.measure_max_frequency_flag;
}
bool show_full_cpu_name(void) {
return args.full_cpu_name_flag;
}
@@ -218,16 +225,23 @@ bool parse_color(char* optarg_str, struct color*** cs) {
char* build_short_options(void) {
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));
char* str = (char *) ecalloc(len*2 + 1, sizeof(char));
#ifdef ARCH_X86
sprintf(str, "%c:%c:%c%c%c%c%c%c%c%c%c%c%c",
sprintf(str, "%c:%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_ACCURATE_PP], c[ARG_MEASURE_MAX_FREQ],
c[ARG_DEBUG], c[ARG_VERBOSE],
c[ARG_VERSION]);
#elif ARCH_ARM
sprintf(str, "%c:%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_MEASURE_MAX_FREQ],
c[ARG_DEBUG], c[ARG_VERBOSE],
c[ARG_VERSION]);
#else
sprintf(str, "%c:%c:%c%c%c%c%c%c",
@@ -270,8 +284,11 @@ bool parse_args(int argc, char* argv[]) {
{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_MEASURE_MAX_FREQ], no_argument, 0, args_chr[ARG_MEASURE_MAX_FREQ] },
{args_str[ARG_FULLCPUNAME], no_argument, 0, args_chr[ARG_FULLCPUNAME] },
{args_str[ARG_RAW], no_argument, 0, args_chr[ARG_RAW] },
#elif ARCH_ARM
{args_str[ARG_MEASURE_MAX_FREQ], no_argument, 0, args_chr[ARG_MEASURE_MAX_FREQ] },
#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] },
@@ -313,6 +330,9 @@ bool parse_args(int argc, char* argv[]) {
else if(opt == args_chr[ARG_ACCURATE_PP]) {
args.accurate_pp = true;
}
else if(opt == args_chr[ARG_MEASURE_MAX_FREQ]) {
args.measure_max_frequency_flag = true;
}
else if(opt == args_chr[ARG_FULLCPUNAME]) {
args.full_cpu_name_flag = true;
}

View File

@@ -29,6 +29,7 @@ enum {
ARG_LOGO_INTEL_NEW,
ARG_LOGO_INTEL_OLD,
ARG_ACCURATE_PP,
ARG_MEASURE_MAX_FREQ,
ARG_DEBUG,
ARG_VERBOSE,
ARG_VERSION
@@ -43,6 +44,7 @@ int max_arg_str_length(void);
bool parse_args(int argc, char* argv[]);
bool show_help(void);
bool accurate_pp(void);
bool measure_max_frequency_flag(void);
bool show_full_cpu_name(void);
bool show_logo_long(void);
bool show_logo_short(void);

View File

@@ -105,6 +105,19 @@ $C1 MMM :MMM NMM dMMK dMMX MMN \
$C1 MMM :MMM NMM dMMMoo OMM0....:Nx. MMN \
$C1 MMM :WWW XWW lONMM 'xXMMMMNOc MMN "
#define ASCII_HYGON \
"$C1 \
$C1 \
$C1 \
$C1 ## ## ## ## ###### ###### ## # \
$C1 ##....## ## ## ## ## ## #### # \
$C1 ######## ## ## ##. ## ## # #### \
$C1 ## ## ## *######. ###### # ## \
$C1 \
$C1 \
$C1 \
$C1 "
#define ASCII_SNAPD \
" $C1@@$C2######## \
$C1@@@@@$C2########### \
@@ -360,6 +373,78 @@ $C1##########@@@@@@@@@@@@@@@@############## \
$C1######################################## \
$C1 #################################### "
#define ASCII_NVIDIA \
"$C1 'cccccccccccccccccccccccccc \
$C1 ;oooooooooooooooooooooooool \
$C1 .:::. .oooooooooooooooooool \
$C1 .:cll; ,c:::. cooooooooooooool \
$C1 ,clo' ;. oolc: ooooooooooool \
$C1.cloo ;cclo . .olc. coooooooool \
$C1oooo :lo, ;ll; looc :oooooooool \
$C1 oooc ool. ;oooc;clol :looooooooool \
$C1 :ooc ,ol; ;oooooo. .cloo; loool \
$C1 ool; .olc. ,:lool .lool \
$C1 ool:. ,::::ccloo. :clooool \
$C1 oolc::. ':cclooooooool \
$C1 ;oooooooooooooooooooooooool \
$C1 \
$C1 \
$C2######. ## ## ## ###### ## ### \
$C2## ## ## ## ## ## ## ## #: :# \
$C2## ## ## ## ## ## ## ## ####### \
$C2## ## ### ## ###### ## ## ## "
#define ASCII_AMPERE \
"$C1 \
$C1 \
$C1 ## \
$C1 #### \
$C1 ### ## \
$C1 ### ### \
$C1 ### ### \
$C1 ### ### \
$C1 ## ### \
$C1 ####### ### ### \
$C1 ###### ## ###### ### \
$C1 #### ### ######## \
$C1 #### ### #### \
$C1 ### ### #### \
$C1 ## ### ### \
$C1 \
$C1 "
#define ASCII_NXP \
"$C1##### # $C2####### ####### $C3########## \
$C1####### ## $C2####### ####### $C3############### \
$C1########## #### $C2###### ###### $C3### ###### \
$C1############ ##### $C2############ $C3##### ##### \
$C1##### ####### ##### $C2########## $C3################### \
$C1##### ######### $C2############## $C3############### \
$C1##### ###### $C2###### ###### $C3#### \
$C1##### ## $C2###### ###### $C3## "
#define ASCII_AMLOGIC \
"$C1 .#####. ### ### \
$C1 ######## ### \
$C1 ####..### ########## ### ### ##### ### ### \
$C1 .## #. ### ## ## ## ### ## ## ## ## ### ## \
$C1 #### #.# ### ## ## ## ### ## ## ## ## ### ## \
$C1#########.### ## ## ## ## ### ###### ## ### \
$C1 ### \
$C1 ### "
#define ASCII_MARVELL \
"$C1 ........... ........... \
$C1 .### . .## . \
$C1 .##### . #### . \
$C1 ####### . ####### . \
$C1 .#########__________. #########__________. \
$C1 .###########|__________|#########|__________| \
$C1 ############ ______############ __________ \
$C1 .######### |__________|###### |__________| \
$C1 ########### ___########### __________ \
$C1.########## |__________| |__________| "
// --------------------- LONG LOGOS ------------------------- //
#define ASCII_AMD_L \
"$C1 \
@@ -492,6 +577,23 @@ $C1 ###########. ############ \
$C1 ################ \
$C1 ####### "
#define ASCII_NVIDIA_L \
"$C1 MMMMMMMMMMMMMMMMMMMMMMMMMMMMMM \
$C1 MMMMMMMMMMMMMMMMMMMMMMMMMMMMMM \
$C1 .:: 'MMMMMMMMMMMMMMMMMMMMMMMMM \
$C1 ccllooo;:;. ;MMMMMMMMMMMMMMMMMM \
$C1 cloc :ooollcc: :MMMMMMMMMMMMMMM \
$C1 cloc :ccl; lolc, ;MMMMMMMMMMMM \
$C1.cloo: :clo ;c: .ool; MMMMMMMMMMM \
$C1 ooo: ooo :ool, .cloo. ;lMMMMMMMMMMM \
$C1 ooo: ooc :ooooccooo. :MMMM lMMMMMMM \
$C1 ooc. ool: :oooooo' ,cloo. MMMM \
$C1 ool:. olc: .:cloo. :MMMM \
$C1 olc, ;:::cccloo. :MMMMMMMM \
$C1 olcc::; ,:ccloMMMMMMMMM \
$C1 :......oMMMMMMMMMMMMMMMMMMMMMM \
$C1 :lllMMMMMMMMMMMMMMMMMMMMMMMMMM "
typedef struct ascii_logo asciiL;
// +-----------------------------------------------------------------------------------------------------------------+
@@ -500,6 +602,7 @@ typedef struct ascii_logo asciiL;
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_hygon = { ASCII_HYGON, 51, 11, false, {C_FG_RED}, {C_FG_RED, 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} };
@@ -516,6 +619,11 @@ asciiL logo_riscv = { ASCII_RISCV, 63, 18, false, {C_FG_CYAN, C_FG_Y
asciiL logo_sifive = { ASCII_SIFIVE, 48, 19, true, {C_BG_WHITE, C_BG_BLACK}, {C_FG_WHITE, C_FG_BLUE} };
asciiL logo_starfive = { ASCII_STARFIVE, 33, 17, false, {C_FG_WHITE}, {C_FG_WHITE, C_FG_BLUE} };
asciiL logo_sipeed = { ASCII_SIPEED, 41, 16, true, {C_BG_RED, C_BG_WHITE}, {C_FG_RED, C_FG_WHITE} };
asciiL logo_nvidia = { ASCII_NVIDIA, 45, 19, false, {C_FG_GREEN, C_FG_WHITE}, {C_FG_WHITE, C_FG_GREEN} };
asciiL logo_ampere = { ASCII_AMPERE, 50, 17, false, {C_FG_RED}, {C_FG_WHITE, C_FG_RED} };
asciiL logo_nxp = { ASCII_NXP, 55, 8, false, {C_FG_YELLOW, C_FG_CYAN, C_FG_GREEN}, {C_FG_CYAN, C_FG_WHITE} };
asciiL logo_amlogic = { ASCII_AMLOGIC, 58, 8, false, {C_FG_BLUE}, {C_FG_BLUE, C_FG_B_WHITE} };
asciiL logo_marvell = { ASCII_MARVELL, 56, 10, false, {C_FG_B_BLACK}, {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} };
@@ -525,6 +633,7 @@ asciiL logo_arm_l = { ASCII_ARM_L, 60, 8, true, {C_BG_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_starfive_l = { ASCII_STARFIVE_L, 50, 22, false, {C_FG_WHITE}, {C_FG_WHITE, C_FG_BLUE} };
asciiL logo_sifive_l = { ASCII_SIFIVE_L, 53, 21, true, {C_BG_WHITE, C_BG_BLACK}, {C_FG_WHITE, C_FG_CYAN} };
asciiL logo_nvidia_l = { ASCII_NVIDIA_L, 50, 15, false, {C_FG_GREEN, C_FG_WHITE}, {C_FG_WHITE, C_FG_GREEN} };
asciiL logo_unknown = { NULL, 0, 0, false, {COLOR_NONE}, {COLOR_NONE, COLOR_NONE} };
#endif

View File

@@ -145,17 +145,25 @@ 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 = (1+5+1+3+1);
assert(strlen(STRING_UNKNOWN)+1 <= size);
char* string = emalloc(sizeof(char)*size);
memset(string, 0, sizeof(char)*size);
char* string = ecalloc(size, sizeof(char));
if(freq->max == UNKNOWN_DATA || freq->max < 0)
if(freq->max == UNKNOWN_DATA || freq->max < 0) {
snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN);
else if(freq->max >= 1000)
}
else if(freq->max >= 1000) {
if (freq->measured)
snprintf(string,size,"~%.3f "STRING_GIGAHERZ,(float)(freq->max)/1000);
else
snprintf(string,size,"%.3f "STRING_GIGAHERZ,(float)(freq->max)/1000);
}
else {
if (freq->measured)
snprintf(string,size,"~%d "STRING_MEGAHERZ,freq->max);
else
snprintf(string,size,"%d "STRING_MEGAHERZ,freq->max);
}
return string;
}

View File

@@ -8,6 +8,7 @@ enum {
// ARCH_X86
CPU_VENDOR_INTEL,
CPU_VENDOR_AMD,
CPU_VENDOR_HYGON,
// ARCH_ARM
CPU_VENDOR_ARM,
CPU_VENDOR_APPLE,
@@ -57,6 +58,8 @@ typedef int32_t VENDOR;
struct frequency {
int32_t base;
int32_t max;
// Indicates if max frequency was measured
bool measured;
};
struct hypervisor {
@@ -121,6 +124,9 @@ struct features {
bool SHA1;
bool SHA2;
bool CRC32;
bool SVE;
bool SVE2;
uint64_t cntb;
#endif
};

195
src/common/freq.c Normal file
View File

@@ -0,0 +1,195 @@
#ifdef __linux__
#define _GNU_SOURCE
#include <time.h>
#include <stdio.h>
#include <stdint.h>
#include <string.h>
#include <errno.h>
#include <unistd.h>
#include <asm/unistd.h>
#include <sys/ioctl.h>
#include <linux/perf_event.h>
#include "global.h"
#include "cpu.h"
static long
perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
int cpu, int group_fd, unsigned long flags) {
int ret;
ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
group_fd, flags);
return ret;
}
#define INSERT_ASM_ONCE __asm volatile("nop");
#define INSERT_ASM_10_TIMES \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
INSERT_ASM_ONCE \
#define INSERT_ASM_100_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES \
INSERT_ASM_10_TIMES
#define INSERT_ASM_1000_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
INSERT_ASM_100_TIMES \
void nop_function(uint64_t iters) {
for (uint64_t i = 0; i < iters; i++) {
INSERT_ASM_1000_TIMES
INSERT_ASM_1000_TIMES
INSERT_ASM_1000_TIMES
INSERT_ASM_1000_TIMES
}
}
// Run the nop_function with the number of iterations specified and
// measure both the time and number of cycles
int measure_freq_iters(uint64_t iters, uint32_t core, double* freq) {
clockid_t clock = CLOCK_PROCESS_CPUTIME_ID;
struct timespec start, end;
struct perf_event_attr pe;
uint64_t cycles;
int fd;
int pid = 0;
memset(&pe, 0, sizeof(struct perf_event_attr));
pe.type = PERF_TYPE_HARDWARE;
pe.size = sizeof(struct perf_event_attr);
pe.config = PERF_COUNT_HW_CPU_CYCLES;
pe.disabled = 1;
pe.exclude_kernel = 1;
pe.exclude_hv = 1;
fd = perf_event_open(&pe, pid, core, -1, 0);
if (fd == -1) {
perror("perf_event_open");
if (errno == EPERM || errno == EACCES) {
printErr("You may not have permission to collect stats.\n"\
"Consider tweaking /proc/sys/kernel/perf_event_paranoid or running as root");
}
return -1;
}
if (clock_gettime(clock, &start) == -1) {
perror("clock_gettime");
return -1;
}
if(ioctl(fd, PERF_EVENT_IOC_RESET, 0) == -1) {
perror("ioctl");
return -1;
}
if(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) == -1) {
perror("ioctl");
return -1;
}
nop_function(iters);
ssize_t ret = read(fd, &cycles, sizeof(uint64_t));
if (ret == -1) {
perror("read");
return -1;
}
if (ret != sizeof(uint64_t)) {
printErr("Read returned %d, expected %d", ret, sizeof(uint64_t));
return -1;
}
if(ioctl(fd, PERF_EVENT_IOC_DISABLE, 0) == -1) {
perror("ioctl");
return -1;
}
if (clock_gettime(clock, &end) == -1) {
perror("clock_gettime");
return -1;
}
uint64_t nsecs = (end.tv_sec*1e9 + end.tv_nsec) - (start.tv_sec*1e9 + start.tv_nsec);
uint64_t usecs = nsecs/1000;
*freq = cycles/((double)usecs);
return 0;
}
// Return a good number of iterations to run the nop_function in
// order to get a precise measurement of the frequency without taking
// too much time.
uint64_t get_num_iters_from_freq(double frequency) {
// Truncate to reduce variability
uint64_t freq_trunc = ((uint64_t) frequency / 100) * 100;
uint64_t osp_per_iter = 4 * 1000;
return freq_trunc * 1e7 * 1/osp_per_iter;
}
// Differences between x86 measure_frequency and this measure_max_frequency:
// - measure_frequency employs all cores simultaneously whereas
// measure_max_frequency only employs 1.
// - measure_frequency runs the computation and checks /proc/cpuinfo whereas
// measure_max_frequency does not rely on /proc/cpuinfo and simply
// counts cpu cycles to measure frequency.
// - measure_frequency uses actual computation while measuring the frequency
// whereas measure_max_frequency uses nop instructions. This makes the former
// x86 dependant whereas the latter is architecture independant.
int64_t measure_max_frequency(uint32_t core) {
if (!bind_to_cpu(core)) {
printErr("Failed binding the process to CPU %d", core);
return UNKNOWN_DATA;
}
// First, get very rough estimation of clock cycle to
// compute a reasonable value for the iterations
double estimation_freq, frequency;
uint64_t iters = 100000;
if (measure_freq_iters(iters, core, &estimation_freq) == -1)
return UNKNOWN_DATA;
if (estimation_freq <= 0.0) {
printErr("First frequency measurement yielded an invalid value: %f", estimation_freq);
return UNKNOWN_DATA;
}
iters = get_num_iters_from_freq(estimation_freq);
printWarn("Running frequency measurement with %ld iterations on core %d...", iters, core);
// Now perform actual measurement
const char* frequency_banner = "cpufetch is measuring the max frequency...";
printf("%s", frequency_banner);
fflush(stdout);
if (measure_freq_iters(iters, core, &frequency) == -1)
return UNKNOWN_DATA;
// Clean screen once measurement is finished
printf("\r%*c\r", (int) strlen(frequency_banner), ' ');
// Discard last digit in the frequency, which should help providing
// more reliable and predictable values.
return (((int) frequency + 5)/10) * 10;
}
#endif // #ifdef __linux__

6
src/common/freq.h Normal file
View File

@@ -0,0 +1,6 @@
#ifndef __COMMON_FREQ__
#define __COMMON_FREQ__
int64_t measure_max_frequency(uint32_t core);
#endif

View File

@@ -1,3 +1,14 @@
#ifdef _WIN32
#define NOMINMAX
#include <windows.h>
#elif defined __linux__
#define _GNU_SOURCE
#include <sched.h>
#elif defined __FreeBSD__
#include <sys/param.h>
#include <sys/cpuset.h>
#endif
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
@@ -51,7 +62,7 @@
#endif
#ifndef GIT_FULL_VERSION
static const char* VERSION = "1.05";
static const char* VERSION = "1.06";
#endif
enum {
@@ -199,6 +210,34 @@ void* erealloc(void *ptr, size_t size) {
return newptr;
}
#ifndef __APPLE__
bool bind_to_cpu(int cpu_id) {
#ifdef _WIN32
HANDLE process = GetCurrentProcess();
DWORD_PTR processAffinityMask = 1 << cpu_id;
return SetProcessAffinityMask(process, processAffinityMask);
#elif defined __linux__
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));
return false;
}
return true;
#endif
}
#endif
void print_version(FILE *restrict stream) {
#ifdef GIT_FULL_VERSION
fprintf(stream, "cpufetch %s (%s %s)\n", GIT_FULL_VERSION, OS_STR, ARCH_STR);

View File

@@ -19,6 +19,9 @@ char *strremove(char *str, const char *sub);
void* emalloc(size_t size);
void* ecalloc(size_t nmemb, size_t size);
void* erealloc(void *ptr, size_t size);
#ifndef __APPLE__
bool bind_to_cpu(int cpu_id);
#endif
void print_version(FILE *restrict stream);
#endif

View File

@@ -30,11 +30,17 @@ void print_help(char *argv[]) {
#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 Measure the max CPU frequency instead of reading it\n", t[ARG_MEASURE_MAX_FREQ], (int) (max_len-strlen(t[ARG_MEASURE_MAX_FREQ])), "");
#endif // __linux__
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 // ARCH_X86
#ifdef ARCH_ARM
#ifdef __linux__
printf(" --%s %*s Measure the max CPU frequency instead of reading it\n", t[ARG_MEASURE_MAX_FREQ], (int) (max_len-strlen(t[ARG_MEASURE_MAX_FREQ])), "");
#endif
#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])), "");
@@ -45,7 +51,7 @@ void print_help(char *argv[]) {
printf(" * \"amd\": Use AMD color scheme \n");
printf(" * \"ibm\", Use IBM color scheme \n");
printf(" * \"arm\": Use ARM color scheme \n");
printf(" * \"rockchip\": Use ARM color scheme \n");
printf(" * \"rockchip\": Use Rockchip color scheme \n");
printf(" * \"sifive\": Use SiFive 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");
@@ -80,6 +86,11 @@ void print_help(char *argv[]) {
printf(" --accurate-pp option, which will measure the AVX frequency and show a more precise estimation\n");
printf(" (this option is only available in x86 architectures).\n");
printf(" To precisely measure peak performance, see: https://github.com/Dr-Noob/peakperf\n");
printf("\n");
printf(" Both --accurate-pp and --measure-max-freq measure the actual frequency of the CPU. However,\n");
printf(" they differ slightly. The former measures the max frequency while running vectorized SSE/AVX\n");
printf(" instructions and it is thus x86 only, whereas the latter simply measures the max clock cycle\n");
printf(" and is architecture independent.\n");
}
int main(int argc, char* argv[]) {

133
src/common/pci.c Normal file
View File

@@ -0,0 +1,133 @@
#define _GNU_SOURCE
#include <sys/stat.h>
#include <dirent.h>
#include "udev.h"
#include "global.h"
#include "pci.h"
#ifndef PATH_MAX
#define PATH_MAX 1024
#endif
#define PCI_PATH "/sys/bus/pci/devices/"
#define MAX_LENGTH_PCI_DIR_NAME 1024
// Return a list of PCI devices containing only
// the sysfs path
struct pci_devices * get_pci_paths(void) {
DIR *dirp;
if ((dirp = opendir(PCI_PATH)) == NULL) {
perror("opendir");
return NULL;
}
struct dirent *dp;
int numDirs = 0;
errno = 0;
while ((dp = readdir(dirp)) != NULL) {
if (strcmp(dp->d_name, ".") != 0 && strcmp(dp->d_name, "..") != 0)
numDirs++;
}
if (errno != 0) {
perror("readdir");
return NULL;
}
rewinddir(dirp);
struct pci_devices * pci = emalloc(sizeof(struct pci_devices));
pci->num_devices = numDirs;
pci->devices = emalloc(sizeof(struct pci_device) * pci->num_devices);
char * full_path = emalloc(PATH_MAX * sizeof(char));
struct stat stbuf;
int i = 0;
while ((dp = readdir(dirp)) != NULL) {
if (strcmp(dp->d_name, ".") == 0 || strcmp(dp->d_name, "..") == 0)
continue;
if (strlen(dp->d_name) > MAX_LENGTH_PCI_DIR_NAME) {
printErr("Directory name is too long: %s", dp->d_name);
return NULL;
}
memset(full_path, 0, PATH_MAX * sizeof(char));
snprintf(full_path, min(strlen(PCI_PATH) + strlen(dp->d_name) + 1, PATH_MAX), "%s%s", PCI_PATH, dp->d_name);
if (stat(full_path, &stbuf) == -1) {
perror("stat");
return NULL;
}
if ((stbuf.st_mode & S_IFMT) == S_IFDIR) {
int strLen = min(MAX_LENGTH_PCI_DIR_NAME, strlen(dp->d_name)) + 1;
pci->devices[i] = emalloc(sizeof(struct pci_device));
pci->devices[i]->path = ecalloc(strLen, sizeof(char));
strncpy(pci->devices[i]->path, dp->d_name, strLen);
i++;
}
}
if (errno != 0) {
perror("readdir");
return NULL;
}
return pci;
}
// For each PCI device in the list pci, fetch its vendor and
// device id using sysfs (e.g., /sys/bus/pci/devices/XXX/{vendor/device})
void populate_pci_devices(struct pci_devices * pci) {
int filelen;
char* buf;
for (int i=0; i < pci->num_devices; i++) {
struct pci_device* dev = pci->devices[i];
int path_size = strlen(PCI_PATH) + strlen(dev->path) + 2;
// Read vendor_id
char *vendor_id_path = emalloc(sizeof(char) * (path_size + strlen("vendor") + 1));
sprintf(vendor_id_path, "%s/%s/%s", PCI_PATH, dev->path, "vendor");
if ((buf = read_file(vendor_id_path, &filelen)) == NULL) {
printWarn("read_file: %s: %s\n", vendor_id_path, strerror(errno));
dev->vendor_id = 0;
}
else {
dev->vendor_id = strtol(buf, NULL, 16);
}
// Read device_id
char *device_id_path = emalloc(sizeof(char) * (path_size + strlen("device") + 1));
sprintf(device_id_path, "%s/%s/%s", PCI_PATH, dev->path, "device");
if ((buf = read_file(device_id_path, &filelen)) == NULL) {
printWarn("read_file: %s: %s\n", device_id_path, strerror(errno));
dev->device_id = 0;
}
else {
dev->device_id = strtol(buf, NULL, 16);
}
free(vendor_id_path);
free(device_id_path);
}
}
// Return a list of PCI devices that could be used to infer the SoC.
// The criteria to determine which devices are suitable for this task
// is decided in filter_pci_devices.
struct pci_devices * get_pci_devices(void) {
struct pci_devices * pci = get_pci_paths();
if (pci == NULL)
return NULL;
populate_pci_devices(pci);
return pci;
}

23
src/common/pci.h Normal file
View File

@@ -0,0 +1,23 @@
#ifndef __PCI__
#define __PCI__
#define PCI_VENDOR_NVIDIA 0x10de
#define PCI_VENDOR_AMPERE 0x1def
#define PCI_DEVICE_TEGRA_X1 0x0faf
#define PCI_DEVICE_ALTRA 0xe100
struct pci_device {
char * path;
uint16_t vendor_id;
uint16_t device_id;
};
struct pci_devices {
struct pci_device ** devices;
int num_devices;
};
struct pci_devices * get_pci_devices(void);
#endif

View File

@@ -61,6 +61,7 @@ enum {
ATTRIBUTE_NCORES,
ATTRIBUTE_NCORES_DUAL,
#ifdef ARCH_X86
ATTRIBUTE_SSE,
ATTRIBUTE_AVX,
ATTRIBUTE_FMA,
#elif ARCH_PPC
@@ -96,6 +97,7 @@ static const char* ATTRIBUTE_FIELDS [] = {
"Cores:",
"Cores (Total):",
#ifdef ARCH_X86
"SSE:",
"AVX:",
"FMA:",
#elif ARCH_PPC
@@ -131,6 +133,7 @@ static const char* ATTRIBUTE_FIELDS_SHORT [] = {
"Cores:",
"Cores (Total):",
#ifdef ARCH_X86
"SSE:",
"AVX:",
"FMA:",
#elif ARCH_PPC
@@ -357,6 +360,9 @@ void choose_ascii_art(struct ascii* art, struct color** cs, struct terminal* ter
else if(art->vendor == CPU_VENDOR_AMD) {
art->art = choose_ascii_art_aux(&logo_amd_l, &logo_amd, term, lf);
}
else if(art->vendor == CPU_VENDOR_HYGON) {
art->art = &logo_hygon;
}
else {
art->art = &logo_unknown;
}
@@ -383,6 +389,16 @@ void choose_ascii_art(struct ascii* art, struct color** cs, struct terminal* ter
art->art = &logo_allwinner;
else if(art->vendor == SOC_VENDOR_ROCKCHIP)
art->art = &logo_rockchip;
else if(art->vendor == SOC_VENDOR_AMPERE)
art->art = &logo_ampere;
else if(art->vendor == SOC_VENDOR_NXP)
art->art = &logo_nxp;
else if(art->vendor == SOC_VENDOR_AMLOGIC)
art->art = &logo_amlogic;
else if(art->vendor == SOC_VENDOR_MARVELL)
art->art = &logo_marvell;
else if(art->vendor == SOC_VENDOR_NVIDIA)
art->art = choose_ascii_art_aux(&logo_nvidia_l, &logo_nvidia, term, lf);
else {
art->art = choose_ascii_art_aux(&logo_arm_l, &logo_arm, term, lf);
}
@@ -589,6 +605,7 @@ bool print_cpufetch_x86(struct cpuInfo* cpu, STYLE s, struct color** cs, struct
for(int i = 0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
char* max_frequency = get_str_freq(ptr->freq);
char* avx = get_str_avx(ptr);
char* sse = get_str_sse(ptr);
char* fma = get_str_fma(ptr);
char* cpu_num = emalloc(sizeof(char) * 9);
@@ -623,8 +640,18 @@ bool print_cpufetch_x86(struct cpuInfo* cpu, STYLE s, struct color** cs, struct
setAttribute(art, ATTRIBUTE_NCORES, n_cores);
}
}
// Show the most modern vector instructions.
if (strcmp(avx, "No") == 0) {
if (strcmp(sse, "No") != 0) {
setAttribute(art, ATTRIBUTE_SSE, sse);
}
}
else {
setAttribute(art, ATTRIBUTE_AVX, avx);
setAttribute(art, ATTRIBUTE_FMA, fma);
}
if(l1i != NULL) setAttribute(art, ATTRIBUTE_L1i, l1i);
if(l1d != NULL) setAttribute(art, ATTRIBUTE_L1d, l1d);
if(l2 != NULL) setAttribute(art, ATTRIBUTE_L2, l2);

View File

@@ -16,10 +16,15 @@ static char* soc_trademark_string[] = {
[SOC_VENDOR_EXYNOS] = "Exynos ",
[SOC_VENDOR_KIRIN] = "Kirin ",
[SOC_VENDOR_KUNPENG] = "Kunpeng ",
[SOC_VENDOR_BROADCOM] = "Broadcom BCM",
[SOC_VENDOR_BROADCOM] = "Broadcom ",
[SOC_VENDOR_APPLE] = "Apple ",
[SOC_VENDOR_ROCKCHIP] = "Rockchip ",
[SOC_VENDOR_GOOGLE] = "Google ",
[SOC_VENDOR_NVIDIA] = "NVIDIA ",
[SOC_VENDOR_AMPERE] = "Ampere ",
[SOC_VENDOR_NXP] = "NXP ",
[SOC_VENDOR_AMLOGIC] = "Amlogic ",
[SOC_VENDOR_MARVELL] = "Marvell",
// RISC-V
[SOC_VENDOR_SIFIVE] = "SiFive ",
[SOC_VENDOR_STARFIVE] = "StarFive ",
@@ -29,7 +34,7 @@ static char* soc_trademark_string[] = {
};
VENDOR get_soc_vendor(struct system_on_chip* soc) {
return soc->soc_vendor;
return soc->vendor;
}
char* get_str_process(struct system_on_chip* soc) {
@@ -40,39 +45,37 @@ char* get_str_process(struct system_on_chip* soc) {
snprintf(str, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
else {
str = emalloc(sizeof(char) * 5);
memset(str, 0, sizeof(char) * 5);
snprintf(str, 5, "%dnm", soc->process);
int max_process_len = 5 + 1;
str = ecalloc(max_process_len, sizeof(char));
snprintf(str, max_process_len, "%dnm", soc->process);
}
return str;
}
char* get_soc_name(struct system_on_chip* soc) {
if(soc->soc_model == SOC_MODEL_UNKNOWN)
if(soc->model == SOC_MODEL_UNKNOWN)
return soc->raw_name;
return soc->soc_name;
return soc->name;
}
void fill_soc(struct system_on_chip* soc, char* soc_name, SOC soc_model, int32_t process) {
soc->soc_model = soc_model;
soc->soc_vendor = get_soc_vendor_from_soc(soc_model);
soc->model = soc_model;
soc->vendor = get_soc_vendor_from_soc(soc_model);
soc->process = process;
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
printBug("fill_soc: soc->soc_vendor == SOC_VENDOR_UNKOWN");
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
printBug("fill_soc: soc->vendor == SOC_VENDOR_UNKOWN");
// If we fall here there is a bug in socs.h
// Reset everything to avoid segfault
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->soc_model = SOC_MODEL_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
soc->model = SOC_MODEL_UNKNOWN;
soc->process = UNKNOWN;
soc->raw_name = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));
snprintf(soc->raw_name, strlen(STRING_UNKNOWN)+1, STRING_UNKNOWN);
}
else {
soc->process = process;
int len = strlen(soc_name) + strlen(soc_trademark_string[soc->soc_vendor]) + 1;
soc->soc_name = emalloc(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);
int len = strlen(soc_name) + strlen(soc_trademark_string[soc->vendor]) + 1;
soc->name = emalloc(sizeof(char) * len);
sprintf(soc->name, "%s%s", soc_trademark_string[soc->vendor], soc_name);
}
}

View File

@@ -24,6 +24,11 @@ enum {
SOC_VENDOR_APPLE,
SOC_VENDOR_ROCKCHIP,
SOC_VENDOR_GOOGLE,
SOC_VENDOR_NVIDIA,
SOC_VENDOR_AMPERE,
SOC_VENDOR_NXP,
SOC_VENDOR_AMLOGIC,
SOC_VENDOR_MARVELL,
// RISC-V
SOC_VENDOR_SIFIVE,
SOC_VENDOR_STARFIVE,
@@ -33,10 +38,10 @@ enum {
};
struct system_on_chip {
SOC soc_model;
VENDOR soc_vendor;
SOC model;
VENDOR vendor;
int32_t process;
char* soc_name;
char* name;
char* raw_name;
};

View File

@@ -4,8 +4,8 @@
#include <string.h>
#include <errno.h>
#include "../common/global.h"
#include "../common/cpu.h"
#include "global.h"
#include "cpu.h"
uint32_t get_sys_info_by_name(char* name) {
size_t size = 0;

View File

@@ -21,9 +21,12 @@
#define CPUFAMILY_ARM_AVALANCHE_BLIZZARD 0xDA33D83D
#endif
// M3 / A16 / A17
// https://ratfactor.com/zig/stdlib-browseable2/c/darwin.zig.html
// https://github.com/Dr-Noob/cpufetch/issues/210
// M3: https://ratfactor.com/zig/stdlib-browseable2/c/darwin.zig.html
// M3_2: https://github.com/Dr-Noob/cpufetch/issues/230
// PRO: https://github.com/Dr-Noob/cpufetch/issues/225
// MAX: https://github.com/Dr-Noob/cpufetch/issues/210
#define CPUFAMILY_ARM_EVEREST_SAWTOOTH 0x8765EDEA
#define CPUFAMILY_ARM_EVEREST_SAWTOOTH_2 0xFA33415E
#define CPUFAMILY_ARM_EVEREST_SAWTOOTH_PRO 0x5F4DEA93
#define CPUFAMILY_ARM_EVEREST_SAWTOOTH_MAX 0x72015832
@@ -40,6 +43,14 @@
#define CPUSUBFAMILY_ARM_HC_HD 5
#endif
// For alternative way to get CPU frequency on macOS and *BSD
#ifdef __APPLE__
#define CPUFREQUENCY_SYSCTL "hw.cpufrequency_max"
#else
// For FreeBSD, not sure about other *BSD
#define CPUFREQUENCY_SYSCTL "dev.cpu.0.freq"
#endif
uint32_t get_sys_info_by_name(char* name);
#endif

View File

@@ -1,7 +1,10 @@
#include "../common/global.h"
#include "udev.h"
#include "global.h"
#include "cpu.h"
#define _PATH_DEVTREE "/proc/device-tree/compatible"
// https://www.kernel.org/doc/html/latest/core-api/cpu_hotplug.html
int get_ncores_from_cpuinfo(void) {
// Examples:
@@ -143,8 +146,7 @@ char* get_field_from_cpuinfo(char* CPUINFO_FIELD) {
char* tmp2 = strstr(tmp1, "\n");
int strlen = (1 + (tmp2-tmp1));
char* hardware = emalloc(sizeof(char) * strlen);
memset(hardware, 0, sizeof(char) * strlen);
char* hardware = ecalloc(strlen, sizeof(char));
strncpy(hardware, tmp1, tmp2-tmp1);
return hardware;
@@ -349,3 +351,13 @@ bool is_devtree_compatible(char* str) {
}
return true;
}
char* get_devtree_compatible(int *filelen) {
char* buf;
if ((buf = read_file(_PATH_DEVTREE, filelen)) == NULL) {
printWarn("read_file: %s: %s", _PATH_DEVTREE, strerror(errno));
}
return buf;
}

View File

@@ -43,5 +43,6 @@ int get_num_sockets_package_cpus(struct topology* topo);
int get_ncores_from_cpuinfo(void);
char* get_field_from_cpuinfo(char* CPUINFO_FIELD);
bool is_devtree_compatible(char* str);
char* get_devtree_compatible(int *filelen);
#endif

View File

@@ -150,6 +150,7 @@ struct uarch* get_cpu_uarch(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(void) {
struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->max = get_max_freq_from_file(0);
freq->base = get_min_freq_from_file(0);

View File

@@ -76,7 +76,7 @@ void fill_uarch(struct uarch* arch, MICROARCH u) {
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_ESPRESSO, "Espresso", 45) // https://en.wikipedia.org/wiki/PowerPC_7xx#Espresso, https://en.wikipedia.org/wiki/Espresso_(processor)
FILL_UARCH(arch->uarch, UARCH_ESPRESSO, "Espresso", 45) // https://en.wikipedia.org/wiki/PowerPC_7xx#Espresso, https://en.wikipedia.org/wiki/Espresso_(processor), https://github.com/Dr-Noob/cpufetch/issues/231
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)

View File

@@ -13,7 +13,7 @@ bool fill_array_from_sys(int *core_ids, int total_cores, char* SYS_PATH) {
char* buf;
char* end;
char path[128];
memset(path, 0, 128);
memset(name, 0, sizeof(char) * 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);

View File

@@ -19,6 +19,7 @@
struct frequency* get_frequency_info(uint32_t core) {
struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(core);
@@ -99,9 +100,8 @@ struct extensions* get_extensions_from_str(char* str) {
return ext;
}
int len = sizeof(char) * (strlen(str)+1);
ext->str = emalloc(sizeof(char) * len);
memset(ext->str, 0, len);
int len = strlen(str);
ext->str = ecalloc(len+1, sizeof(char));
strncpy(ext->str, str, sizeof(char) * len);
// Code inspired in Linux kernel (riscv_fill_hwcap):

View File

@@ -12,7 +12,7 @@ bool match_sifive(char* soc_name, struct system_on_chip* soc) {
/*if((tmp = strstr(soc_name, "???")) == NULL)
return false;*/
//soc->soc_vendor = ???
//soc->vendor = ???
SOC_START
SOC_EQ(tmp, "fu740", "Freedom U740", SOC_SIFIVE_U740, soc, 40)
@@ -68,12 +68,12 @@ struct system_on_chip* guess_soc_from_devtree(struct system_on_chip* soc) {
struct system_on_chip* get_soc(struct cpuInfo* cpu) {
struct system_on_chip* soc = emalloc(sizeof(struct system_on_chip));
soc->raw_name = NULL;
soc->soc_vendor = SOC_VENDOR_UNKNOWN;
soc->soc_model = SOC_MODEL_UNKNOWN;
soc->vendor = SOC_VENDOR_UNKNOWN;
soc->model = SOC_MODEL_UNKNOWN;
soc->process = UNKNOWN;
soc = guess_soc_from_devtree(soc);
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
if(soc->raw_name != NULL) {
printWarn("SoC detection failed using device tree: Found '%s' string", soc->raw_name);
}
@@ -82,7 +82,7 @@ struct system_on_chip* get_soc(struct cpuInfo* cpu) {
}
}
if(soc->soc_model == SOC_MODEL_UNKNOWN) {
if(soc->model == SOC_MODEL_UNKNOWN) {
// raw_name might not be NULL, but if we were unable to find
// the exact SoC, just print "Unkwnown"
soc->raw_name = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN)+1));

View File

@@ -40,8 +40,7 @@ char* get_field_from_devtree(int DEVTREE_FIELD) {
tmp1++;
int strlen = filelen-(tmp1-buf);
char* hardware = emalloc(sizeof(char) * strlen);
memset(hardware, 0, sizeof(char) * strlen);
char* hardware = ecalloc(strlen, sizeof(char));
strncpy(hardware, tmp1, strlen-1);
return hardware;
@@ -70,9 +69,8 @@ char* parse_cpuinfo_field(char* field_str) {
}
int ret_strlen = (end-tmp);
char* ret = emalloc(sizeof(char) * (ret_strlen+1));
memset(ret, 0, sizeof(char) * (ret_strlen+1));
strncpy(ret, tmp, ret_strlen);
char* ret = ecalloc(ret_strlen+1, sizeof(char));
strncpy(ret, tmp, sizeof(char) * ret_strlen);
return ret;
}

View File

@@ -72,34 +72,6 @@ uint32_t get_apic_id(bool x2apic_id) {
}
}
#ifndef __APPLE__
bool bind_to_cpu(int cpu_id) {
#ifdef _WIN32
HANDLE process = GetCurrentProcess();
DWORD_PTR processAffinityMask = 1 << cpu_id;
return SetProcessAffinityMask(process, processAffinityMask);
#elif defined __linux__
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));
return false;
}
return true;
#endif
}
#endif
#ifdef __linux__
int get_total_cores_module(int total_cores, int module) {
int total_modules = 2;
@@ -262,15 +234,11 @@ 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 = ecalloc(size, sizeof(uint32_t));
uint32_t* smt = ecalloc(size, sizeof(uint32_t));
uint32_t* apic_id = ecalloc(size, sizeof(uint32_t));
uint32_t num_caches = 0;
memset(sockets, 0, sizeof(uint32_t) * size);
memset(smt, 0, sizeof(uint32_t) * size);
memset(apic_id, 0, sizeof(uint32_t) * size);
// System topology
for(int i=0; i < topo->total_cores_module; i++) {
sockets[apic_pkg[i]] = 1;
@@ -397,6 +365,11 @@ bool fill_apic_ids(uint32_t* apic_ids, int first_core, int n, bool x2apic_id) {
}
bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo) {
if (topo->cach == NULL) {
printWarn("get_topology_from_apic: cach is NULL");
return false;
}
uint32_t apic_id;
uint32_t* apic_ids = emalloc(sizeof(uint32_t) * topo->total_cores_module);
uint32_t* apic_pkg = emalloc(sizeof(uint32_t) * topo->total_cores_module);

View File

@@ -17,10 +17,6 @@ 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
#ifdef __linux__
int get_total_cores_module(int total_cores, int module);
#endif

View File

@@ -5,6 +5,13 @@
#include "../common/udev.h"
#include <unistd.h>
#endif
#if defined (__FreeBSD__) || defined (__APPLE__)
#include "../common/sysctl.h"
#endif
#ifdef __linux__
#include "../common/freq.h"
#endif
#include <stdio.h>
#include <stdlib.h>
@@ -22,6 +29,7 @@
#define CPU_VENDOR_INTEL_STRING "GenuineIntel"
#define CPU_VENDOR_AMD_STRING "AuthenticAMD"
#define CPU_VENDOR_HYGON_STRING "HygonGenuine"
static const char *hv_vendors_string[] = {
[HV_VENDOR_KVM] = "KVMKVMKVM",
@@ -83,8 +91,7 @@ char* get_str_cpu_name_internal(void) {
uint32_t edx = 0;
uint32_t c = 0;
char * name = emalloc(sizeof(char) * CPU_NAME_MAX_LENGTH);
memset(name, 0, CPU_NAME_MAX_LENGTH);
char * name = ecalloc(CPU_NAME_MAX_LENGTH, sizeof(char));
for(int i=0; i < 3; i++) {
eax = 0x80000002 + i;
@@ -218,7 +225,7 @@ int64_t get_peak_performance(struct cpuInfo* cpu, bool accurate_pp) {
#endif
//First, check we have consistent data
if(freq == UNKNOWN_DATA || topo->logical_cores == UNKNOWN_DATA) {
if(freq == UNKNOWN_DATA || topo == NULL || topo->logical_cores == UNKNOWN_DATA) {
return -1;
}
@@ -273,7 +280,7 @@ struct hypervisor* get_hp_info(bool hv_present) {
}
else {
char name[13];
memset(name, 0, 13);
memset(name, 0, sizeof(char) * 13);
get_name_cpuid(name, ebx, ecx, edx);
bool found = false;
@@ -451,7 +458,7 @@ struct cpuInfo* get_cpu_info(void) {
cpu->cach = NULL;
cpu->feat = NULL;
uint32_t modules = 1;
cpu->num_cpus = 1;
uint32_t eax = 0;
uint32_t ebx = 0;
uint32_t ecx = 0;
@@ -463,13 +470,15 @@ struct cpuInfo* get_cpu_info(void) {
//Fill vendor
char name[13];
memset(name,0,13);
memset(name, 0, sizeof(char) * 13);
get_name_cpuid(name, ebx, edx, ecx);
if(strcmp(CPU_VENDOR_INTEL_STRING,name) == 0)
cpu->cpu_vendor = CPU_VENDOR_INTEL;
else if (strcmp(CPU_VENDOR_AMD_STRING,name) == 0)
cpu->cpu_vendor = CPU_VENDOR_AMD;
else if (strcmp(CPU_VENDOR_HYGON_STRING,name) == 0)
cpu->cpu_vendor = CPU_VENDOR_HYGON;
else {
cpu->cpu_vendor = CPU_VENDOR_INVALID;
printErr("Unknown CPU vendor: %s", name);
@@ -507,12 +516,12 @@ struct cpuInfo* get_cpu_info(void) {
cpu->hybrid_flag = (edx >> 15) & 0x1;
}
if(cpu->hybrid_flag) modules = 2;
if(cpu->hybrid_flag) cpu->num_cpus = 2;
struct cpuInfo* ptr = cpu;
for(uint32_t i=0; i < modules; i++) {
for(uint32_t i=0; i < cpu->num_cpus; i++) {
int32_t first_core;
set_cpu_module(i, modules, &first_core);
set_cpu_module(i, cpu->num_cpus, &first_core);
if(i > 0) {
ptr->next_cpu = emalloc(sizeof(struct cpuInfo));
@@ -547,11 +556,7 @@ struct cpuInfo* get_cpu_info(void) {
cpu->cpu_name = infer_cpu_name_from_uarch(cpu->arch);
}
// If any field of the struct is NULL,
// return early, as next functions
// require non NULL fields in cach and topo
ptr->cach = get_cache_info(ptr);
if(ptr->cach == NULL) return cpu;
if(cpu->hybrid_flag) {
ptr->topo = get_topology_info(ptr, ptr->cach, i);
@@ -559,16 +564,23 @@ struct cpuInfo* get_cpu_info(void) {
else {
ptr->topo = get_topology_info(ptr, ptr->cach, -1);
}
if(cpu->topo == NULL) return cpu;
// If topo is NULL, return early, as get_peak_performance
// requries non-NULL topology.
if(ptr->topo == NULL) return cpu;
}
cpu->num_cpus = modules;
cpu->peak_performance = get_peak_performance(cpu, accurate_pp());
return cpu;
}
bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
if (topo->cach == NULL) {
printWarn("get_cache_topology_amd: cach is NULL");
return false;
}
if(cpu->maxExtendedLevels >= 0x8000001D && cpu->topology_extensions) {
uint32_t i, eax, ebx, ecx, edx, num_sharing_cache, cache_type, cache_level;
@@ -644,10 +656,17 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
#ifdef __linux__
void get_topology_from_udev(struct topology* topo) {
// TODO: To be improved in the future
topo->total_cores = get_ncores_from_cpuinfo();
// TODO: To be improved in the future
if (topo->total_cores == 1) {
// We can assume it's a single core CPU
topo->logical_cores = topo->total_cores;
topo->physical_cores = topo->total_cores;
}
else {
topo->logical_cores = UNKNOWN_DATA;
topo->physical_cores = UNKNOWN_DATA;
}
topo->smt_available = 1;
topo->smt_supported = 1;
topo->sockets = 1;
@@ -692,32 +711,31 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, int
topo->total_cores_module = topo->total_cores;
}
bool toporet = false;
switch(cpu->cpu_vendor) {
case CPU_VENDOR_INTEL:
if (cpu->maxLevels >= 0x00000004) {
bool toporet = get_topology_from_apic(cpu, topo);
toporet = get_topology_from_apic(cpu, topo);
}
else {
printWarn("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000004, cpu->maxLevels);
}
if(!toporet) {
#ifdef __linux__
printWarn("Failed to retrieve topology from APIC, using udev...\n");
printWarn("Failed to retrieve topology from APIC, using udev...");
get_topology_from_udev(topo);
#else
printErr("Failed to retrieve topology from APIC, assumming default values...\n");
if (cpu->maxLevels >= 0x00000004)
printErr("Failed to retrieve topology from APIC, assumming default values...");
topo->logical_cores = UNKNOWN_DATA;
topo->physical_cores = UNKNOWN_DATA;
topo->smt_available = 1;
topo->smt_supported = 1;
#endif
}
}
else {
printWarn("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;
topo->smt_supported = 1;
}
break;
case CPU_VENDOR_AMD:
case CPU_VENDOR_HYGON:
if (cpu->maxExtendedLevels >= 0x80000008) {
eax = 0x80000008;
cpuid(&eax, &ebx, &ecx, &edx);
@@ -734,10 +752,15 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, int
}
}
else {
#ifdef __linux__
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X), using udev...", 0x80000008, cpu->maxExtendedLevels);
get_topology_from_udev(topo);
#else
printWarn("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;
#endif
}
if (cpu->maxLevels >= 0x00000001) {
@@ -914,16 +937,27 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(struct cpuInfo* cpu) {
struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
if(cpu->maxLevels < 0x00000016) {
#if defined (_WIN32) || defined (__APPLE__)
#if defined (_WIN32)
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;
#elif defined (__FreeBSD__) || defined (__APPLE__)
printWarn("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X). Using sysctl", 0x00000016, cpu->maxLevels);
uint32_t freq_hz = get_sys_info_by_name(CPUFREQUENCY_SYSCTL);
if (freq_hz == 0) {
printWarn("Read max CPU frequency from sysctl and got 0 MHz");
freq->max = UNKNOWN_DATA;
}
freq->base = UNKNOWN_DATA;
freq->max = freq_hz;
#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->max = get_max_freq_from_file(cpu->first_core_id);
if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz");
@@ -950,7 +984,7 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
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);
freq->max = get_max_freq_from_file(cpu->first_core_id);
if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz");
@@ -962,6 +996,15 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
}
}
#ifdef __linux__
if (freq->max == UNKNOWN_DATA || measure_max_frequency_flag()) {
if (freq->max == UNKNOWN_DATA)
printWarn("All previous methods failed, measuring CPU frequency");
freq->max = measure_max_frequency(cpu->first_core_id);
freq->measured = true;
}
#endif
return freq;
}
@@ -983,24 +1026,33 @@ char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_soc
string = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1));
strcpy(string, STRING_UNKNOWN);
}
else if(topo->smt_supported > 1) {
else {
char cores_str[6];
memset(cores_str, 0, sizeof(char) * 6);
if (topo->physical_cores * topo_sockets > 1)
strcpy(cores_str, "cores");
else
strcpy(cores_str, "core");
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_available > 1)
snprintf(string, max_size, "%d cores (%d threads)", topo->physical_cores * topo_sockets, topo->logical_cores * topo_sockets);
snprintf(string, max_size, "%d %s (%d threads)", topo->physical_cores * topo_sockets, cores_str, 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, max_size, "%d %s (SMT disabled)", topo->physical_cores * topo_sockets, cores_str);
else
snprintf(string, max_size, "%d cores (HT disabled)", topo->physical_cores * topo_sockets);
snprintf(string, max_size, "%d %s (HT disabled)", topo->physical_cores * topo_sockets, cores_str);
}
}
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);
snprintf(string, max_size, "%d %s",topo->physical_cores * topo_sockets, cores_str);
}
}
return string;
@@ -1061,8 +1113,14 @@ char* get_str_sse(struct cpuInfo* cpu) {
last+=SSE4_2_sl;
}
if (last == 0) {
snprintf(string, 2+1, "No");
}
else {
//Purge last comma
string[last-1] = '\0';
}
return string;
}

View File

@@ -116,8 +116,25 @@ int64_t measure_frequency(struct cpuInfo* cpu) {
}
pthread_t* compute_th = malloc(sizeof(pthread_t) * cpu->topo->total_cores);
cpu_set_t cpus;
pthread_attr_t attr;
if ((ret = pthread_attr_init(&attr)) != 0) {
printErr("pthread_attr_init: %s", strerror(ret));
return -1;
}
for(int i=0; i < cpu->topo->total_cores; i++) {
ret = pthread_create(&compute_th[i], NULL, compute_function, NULL);
// We might have called bind_to_cpu previously, binding the threads
// to a specific core, so now we must make sure we run the new thread
// on the correct core.
CPU_ZERO(&cpus);
CPU_SET(i, &cpus);
if ((ret = pthread_attr_setaffinity_np(&attr, sizeof(cpu_set_t), &cpus)) != 0) {
printErr("pthread_attr_setaffinity_np: %s", strerror(ret));
return -1;
}
ret = pthread_create(&compute_th[i], &attr, compute_function, NULL);
if(ret != 0) {
fprintf(stderr, "Error creating thread\n");

View File

@@ -47,8 +47,10 @@ typedef uint32_t MICROARCH;
enum {
UARCH_UNKNOWN,
// INTEL //
UARCH_I486,
UARCH_P5,
UARCH_P5_MMX,
UARCH_P6_PRO,
UARCH_P6_PENTIUM_II,
UARCH_P6_PENTIUM_III,
UARCH_DOTHAN,
@@ -97,6 +99,8 @@ enum {
// AMD //
UARCH_AM486,
UARCH_AM5X86,
UARCH_SSA5,
UARCH_K5,
UARCH_K6,
UARCH_K7,
UARCH_K8,
@@ -115,7 +119,9 @@ enum {
UARCH_ZEN3,
UARCH_ZEN3_PLUS,
UARCH_ZEN4,
UARCH_ZEN4C
UARCH_ZEN4C,
UARCH_ZEN5,
UARCH_ZEN5C,
};
struct uarch {
@@ -149,16 +155,30 @@ struct uarch* get_uarch_from_cpuid_intel(uint32_t ef, uint32_t f, uint32_t em, u
// ------------------------------------------------------------------------------- //
// EF F EM M S //
UARCH_START
CHECK_UARCH(arch, 0, 4, 0, 0, NA, "i80486DX", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 1, NA, "i80486DX-50", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 2, NA, "i80486SX", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 3, NA, "i80486DX2", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 4, NA, "i80486SL", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 5, NA, "i80486SX2", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 7, NA, "i80486DX2WB", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 8, NA, "i80486DX4", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 9, NA, "i80486DX4WB", UARCH_I486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 0, NA, "P5", UARCH_P5, 800)
CHECK_UARCH(arch, 0, 5, 0, 1, NA, "P5", UARCH_P5, 800)
CHECK_UARCH(arch, 0, 5, 0, 2, NA, "P5", UARCH_P5, UNK)
CHECK_UARCH(arch, 0, 5, 0, 3, NA, "P5", UARCH_P5, 600)
CHECK_UARCH(arch, 0, 5, 0, 4, NA, "P5 (MMX)", UARCH_P5_MMX, UNK)
CHECK_UARCH(arch, 0, 5, 0, 7, NA, "P5 (MMX)", UARCH_P5_MMX, UNK)
CHECK_UARCH(arch, 0, 5, 0, 8, NA, "P5 (MMX)", UARCH_P5_MMX, 250)
CHECK_UARCH(arch, 0, 5, 0, 2, NA, "P54C", UARCH_P5, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 3, NA, "P24T (Overdrive)", UARCH_P5, 600) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 4, NA, "P55C (MMX)", UARCH_P5_MMX, 350) // https://www.cpu-world.com/CPUs/Pentium/TYPE-Pentium%20MMX.html
CHECK_UARCH(arch, 0, 5, 0, 7, NA, "P54C", UARCH_P5, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 8, NA, "Tillamook", UARCH_P5_MMX, 250) // http://instlatx64.atw.hu./
CHECK_UARCH(arch, 0, 5, 0, 9, 0, "Lakemont", UARCH_LAKEMONT, 32)
CHECK_UARCH(arch, 0, 5, 0, 9, NA, "P5 (MMX)", UARCH_P5_MMX, UNK)
CHECK_UARCH(arch, 0, 5, 0, 10, 0, "Lakemont", UARCH_LAKEMONT, 32)
CHECK_UARCH(arch, 0, 6, 0, 1, 1, "P6", UARCH_P6_PRO, UNK)
CHECK_UARCH(arch, 0, 6, 0, 1, 2, "P6", UARCH_P6_PRO, UNK)
CHECK_UARCH(arch, 0, 6, 0, 1, 6, "P6", UARCH_P6_PRO, 350)
CHECK_UARCH(arch, 0, 6, 0, 1, 7, "P6", UARCH_P6_PRO, 350)
CHECK_UARCH(arch, 0, 6, 0, 1, 9, "P6", UARCH_P6_PRO, 350)
CHECK_UARCH(arch, 0, 6, 0, 0, NA, "P6 (Pentium II)", UARCH_P6_PENTIUM_II, UNK)
CHECK_UARCH(arch, 0, 6, 0, 1, NA, "P6 (Pentium II)", UARCH_P6_PENTIUM_II, UNK) // process depends on core
CHECK_UARCH(arch, 0, 6, 0, 2, NA, "P6 (Pentium II)", UARCH_P6_PENTIUM_II, UNK)
@@ -279,11 +299,16 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
// ----------------------------------------------------------------------------- //
// EF F EM M S //
UARCH_START
CHECK_UARCH(arch, 0, 4, 0, 3, NA, "Am486", UARCH_AM486, UNK)
CHECK_UARCH(arch, 0, 4, 0, 7, NA, "Am486", UARCH_AM486, UNK)
CHECK_UARCH(arch, 0, 4, 0, 8, NA, "Am486", UARCH_AM486, UNK)
CHECK_UARCH(arch, 0, 4, 0, 9, NA, "Am486", UARCH_AM486, UNK)
CHECK_UARCH(arch, 0, 4, NA, NA, NA, "Am5x86", UARCH_AM5X86, UNK)
CHECK_UARCH(arch, 0, 4, 0, 3, NA, "Am486DX2", UARCH_AM486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 7, NA, "Am486DX2WB", UARCH_AM486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 8, NA, "Am486DX4", UARCH_AM486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 9, NA, "Am486DX4WB", UARCH_AM486, UNK) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 14, NA, "Am5x86", UARCH_AM5X86, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 4, 0, 15, NA, "Am5x86WB", UARCH_AM5X86, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 0, NA, "SSA5 (K5)", UARCH_SSA5, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 1, NA, "K5", UARCH_K5, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 2, NA, "K5", UARCH_K5, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
CHECK_UARCH(arch, 0, 5, 0, 3, NA, "K5", UARCH_K5, 350) // https://sandpile.org/x86/cpuid.htm#level_0000_0001h
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
@@ -387,6 +412,31 @@ struct uarch* get_uarch_from_cpuid_amd(uint32_t ef, uint32_t f, uint32_t em, uin
CHECK_UARCH(arch, 10, 15, 8, NA, NA, "Zen 4", UARCH_ZEN4, 5) // instlatx64 (AMD MI300C)
CHECK_UARCH(arch, 10, 15, 9, NA, NA, "Zen 4", UARCH_ZEN4, 5) // instlatx64 (AMD MI300A)
CHECK_UARCH(arch, 10, 15, 10, NA, NA, "Zen 4c", UARCH_ZEN4C, 5) // instlatx64
CHECK_UARCH(arch, 11, 15, 0, NA, NA, "Zen 5", UARCH_ZEN5, 4) // Turin/EPYC (instlatx64)
CHECK_UARCH(arch, 11, 15, 1, NA, NA, "Zen 5c", UARCH_ZEN5C, 3) // Zen5c EPYC (instlatx64, https://en.wikipedia.org/wiki/Zen_5#cite_note-10)
CHECK_UARCH(arch, 11, 15, 2, NA, NA, "Zen 5", UARCH_ZEN5, 4) // Strix Point (instlatx64)
CHECK_UARCH(arch, 11, 15, 4, NA, NA, "Zen 5", UARCH_ZEN5, 4) // Granite Ridge (instlatx64)
CHECK_UARCH(arch, 11, 15, 6, NA, NA, "Zen 5", UARCH_ZEN5, 4) // Krackan Point (instlatx64)
CHECK_UARCH(arch, 11, 15, 7, NA, NA, "Zen 5", UARCH_ZEN5, 4) // Strix Halo (instlatx64)
UARCH_END
return arch;
}
struct uarch* get_uarch_from_cpuid_hygon(uint32_t ef, uint32_t f, uint32_t em, uint32_t m, int s) {
struct uarch* arch = emalloc(sizeof(struct uarch));
// EF: Extended Family //
// F: Family //
// EM: Extended Model //
// M: Model //
// S: Stepping //
// ----------------------------------------------------------------------------- //
// EF F EM M S //
UARCH_START
// https://www.phoronix.com/news/Hygon-Dhyana-AMD-China-CPUs
CHECK_UARCH(arch, 9, 15, 0, 1, NA, "Zen", UARCH_ZEN, UNK) // https://github.com/Dr-Noob/cpufetch/issues/244
// CHECK_UARCH(arch, 9, 15, 0, 2, NA, "???", ?????????, UNK) // http://instlatx64.atw.hu/
UARCH_END
return arch;
@@ -436,9 +486,17 @@ struct uarch* get_uarch_from_cpuid(struct cpuInfo* cpu, uint32_t dump, uint32_t
}
return get_uarch_from_cpuid_intel(ef, f, em, m, s);
}
else
else if(cpu->cpu_vendor == CPU_VENDOR_AMD) {
return get_uarch_from_cpuid_amd(ef, f, em, m, s);
}
else if(cpu->cpu_vendor == CPU_VENDOR_HYGON) {
return get_uarch_from_cpuid_hygon(ef, f, em, m, s);
}
else {
printBug("Invalid CPU vendor: %d", cpu->cpu_vendor);
return NULL;
}
}
// If we cannot get the CPU name from CPUID, try to infer it from uarch
char* infer_cpu_name_from_uarch(struct uarch* arch) {
@@ -452,16 +510,42 @@ char* infer_cpu_name_from_uarch(struct uarch* arch) {
char *str = NULL;
if (arch->uarch == UARCH_P5)
switch (arch->uarch) {
// Intel
case UARCH_I486:
str = "Intel 486";
break;
case UARCH_P5:
str = "Intel Pentium";
else if (arch->uarch == UARCH_P5_MMX)
break;
case UARCH_P5_MMX:
str = "Intel Pentium MMX";
else if (arch->uarch == UARCH_P6_PENTIUM_II)
break;
case UARCH_P6_PRO:
str = "Intel Pentium Pro";
break;
case UARCH_P6_PENTIUM_II:
str = "Intel Pentium II";
else if (arch->uarch == UARCH_P6_PENTIUM_III)
break;
case UARCH_P6_PENTIUM_III:
str = "Intel Pentium III";
else
break;
// AMD
case UARCH_AM486:
str = "AMD 486";
break;
case UARCH_AM5X86:
str = "AMD 5x86";
break;
case UARCH_SSA5:
str = "AMD 5k86";
break;
default:
printErr("Unable to find name from uarch: %d", arch->uarch);
break;
}
if (str == NULL) {
cpu_name = ecalloc(strlen(STRING_UNKNOWN) + 1, sizeof(char));
@@ -476,6 +560,8 @@ char* infer_cpu_name_from_uarch(struct uarch* arch) {
}
bool vpus_are_AVX512(struct cpuInfo* cpu) {
// Zen5 actually has 2 x AVX512 units
// https://www.anandtech.com/show/21469/amd-details-ryzen-ai-300-series-for-mobile-strix-point-with-rdna-35-igpu-xdna-2-npu
return cpu->arch->uarch != UARCH_ICE_LAKE &&
cpu->arch->uarch != UARCH_TIGER_LAKE &&
cpu->arch->uarch != UARCH_ZEN4 &&
@@ -516,6 +602,8 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_ZEN3_PLUS:
case UARCH_ZEN4:
case UARCH_ZEN4C:
case UARCH_ZEN5:
case UARCH_ZEN5C:
return 2;
default:
return 1;