Compare commits

..

2 Commits
v1.06 ... hygon

Author SHA1 Message Date
Dr-Noob
7e9d308bea [v1.05][X86] Hygon logo and uarch detection (#244) 2024-07-07 11:46:42 +01:00
Dr-Noob
9018a3b98e [v1.05][X86] Very preeliminary support for Hygon CPUs 2024-07-03 21:29:52 +01:00
27 changed files with 164 additions and 652 deletions

View File

@@ -13,23 +13,17 @@ COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_C
ifneq ($(OS),Windows_NT) ifneq ($(OS),Windows_NT)
GIT_VERSION := "$(shell git describe --abbrev=4 --dirty --always --tags)" GIT_VERSION := "$(shell git describe --abbrev=4 --dirty --always --tags)"
arch := $(shell uname -m) 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 $(arch), x86_64 amd64 i386 i486 i586 i686)) ifeq ($(arch), $(filter $(arch), x86_64 amd64 i386 i486 i586 i686))
SRC_DIR=src/x86/ SRC_DIR=src/x86/
SOURCE += $(COMMON_SRC) $(SRC_DIR)cpuid.c $(SRC_DIR)apic.c $(SRC_DIR)cpuid_asm.c $(SRC_DIR)uarch.c 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 HEADERS += $(COMMON_HDR) $(SRC_DIR)cpuid.h $(SRC_DIR)apic.h $(SRC_DIR)cpuid_asm.h $(SRC_DIR)uarch.h $(SRC_DIR)freq/freq.h
ifeq ($(os), Linux) os := $(shell uname -s)
ifeq ($(os), Linux)
SOURCE += $(SRC_DIR)freq/freq.c freq_nov.o freq_avx.o freq_avx512.o SOURCE += $(SRC_DIR)freq/freq.c freq_nov.o freq_avx.o freq_avx512.o
HEADERS += $(SRC_DIR)freq/freq.h HEADERS += $(SRC_DIR)freq/freq.h
CFLAGS += -pthread CFLAGS += -pthread
endif endif
CFLAGS += -DARCH_X86 -std=c99 -fstack-protector-all CFLAGS += -DARCH_X86 -std=c99 -fstack-protector-all
else ifeq ($(arch), $(filter $(arch), ppc64le ppc64 ppcle ppc)) else ifeq ($(arch), $(filter $(arch), ppc64le ppc64 ppcle ppc))
SRC_DIR=src/ppc/ SRC_DIR=src/ppc/
@@ -38,25 +32,20 @@ ifneq ($(OS),Windows_NT)
CFLAGS += -DARCH_PPC -std=gnu99 -fstack-protector-all -Wno-language-extension-token CFLAGS += -DARCH_PPC -std=gnu99 -fstack-protector-all -Wno-language-extension-token
else ifeq ($(arch), $(filter $(arch), arm aarch64_be aarch64 arm64 armv8b armv8l armv7l armv6l)) else ifeq ($(arch), $(filter $(arch), arm aarch64_be aarch64 arm64 armv8b armv8l armv7l armv6l))
SRC_DIR=src/arm/ SRC_DIR=src/arm/
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 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
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 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 CFLAGS += -DARCH_ARM -Wno-unused-parameter -std=c99 -fstack-protector-all
# Check if the compiler supports -march=armv8-a+sve. We will use it (if supported) to compile SVE detection code later os := $(shell uname -s)
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 ($(os), Darwin) ifeq ($(os), Darwin)
SOURCE += $(SRC_COMMON)sysctl.c SOURCE += $(SRC_DIR)sysctl.c
HEADERS += $(SRC_COMMON)sysctl.h HEADERS += $(SRC_DIR)sysctl.h
endif endif
else ifeq ($(arch), $(filter $(arch), riscv64 riscv32)) else ifeq ($(arch), $(filter $(arch), riscv64 riscv32))
SRC_DIR=src/riscv/ SRC_DIR=src/riscv/
SOURCE += $(COMMON_SRC) $(SRC_DIR)riscv.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_DIR)udev.c SOURCE += $(COMMON_SRC) $(SRC_DIR)riscv.c $(SRC_DIR)uarch.c $(SRC_COMMON)soc.c $(SRC_DIR)soc.c $(SRC_DIR)udev.c
HEADERS += $(COMMON_HDR) $(SRC_DIR)riscv.h $(SRC_DIR)uarch.h $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_DIR)udev.h $(SRC_DIR)socs.h HEADERS += $(COMMON_HDR) $(SRC_DIR)riscv.h $(SRC_DIR)uarch.h $(SRC_COMMON)soc.h $(SRC_DIR)soc.h $(SRC_DIR)udev.h $(SRC_DIR)socs.h
CFLAGS += -DARCH_RISCV -Wno-unused-parameter -std=c99 -fstack-protector-all CFLAGS += -DARCH_RISCV -Wno-unused-parameter -std=c99 -fstack-protector-all
else else
# Error lines should not be tabulated because Makefile complains about it # Error lines should not be tabulated because Makefile complains about it
$(warning Unsupported arch detected: $(arch). See https://github.com/Dr-Noob/cpufetch#1-support) $(warning Unsupported arch detected: $(arch). See https://github.com/Dr-Noob/cpufetch#1-support)
@@ -97,9 +86,6 @@ 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 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 $@ $(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) $(OUTPUT): Makefile $(SOURCE) $(HEADERS)
ifeq ($(GIT_VERSION),"") ifeq ($(GIT_VERSION),"")
$(CC) $(CFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT) $(CC) $(CFLAGS) $(SANITY_FLAGS) $(SOURCE) -o $(OUTPUT)

View File

@@ -45,7 +45,6 @@ cpufetch is a command-line tool written in C that displays the CPU information i
- [3.1 x86_64](#31-x86_64) - [3.1 x86_64](#31-x86_64)
- [3.2 ARM](#32-arm) - [3.2 ARM](#32-arm)
- [3.3 PowerPC](#33-powerpc) - [3.3 PowerPC](#33-powerpc)
- [3.4 RISC-V](#34-risc-v)
- [4. Colors](#4-colors) - [4. Colors](#4-colors)
- [4.1 Specifying a name](#41-specifying-a-name) - [4.1 Specifying a name](#41-specifying-a-name)
- [4.2 Specifying the colors in RGB format](#42-specifying-the-colors-in-rgb-format) - [4.2 Specifying the colors in RGB format](#42-specifying-the-colors-in-rgb-format)
@@ -121,11 +120,6 @@ make
<p align="center"><img width=90% src="pictures/ibm.png"></p> <p align="center"><img width=90% src="pictures/ibm.png"></p>
<p align="center">Talos II</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 ## 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: By default, `cpufetch` will print the CPU logo with the system colorscheme. However, you can set a custom color scheme in two different ways:
@@ -181,7 +175,6 @@ 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. - [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. - [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). - [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) ## 8. cpufetch for GPUs (gpufetch)
See [gpufetch](https://github.com/Dr-Noob/gpufetch) project! See [gpufetch](https://github.com/Dr-Noob/gpufetch) project!

Binary file not shown.

Before

Width:  |  Height:  |  Size: 42 KiB

View File

@@ -8,18 +8,15 @@
#ifdef __linux__ #ifdef __linux__
#include <sys/auxv.h> #include <sys/auxv.h>
#include <asm/hwcap.h> #include <asm/hwcap.h>
#include "../common/freq.h"
#elif defined __APPLE__ || __MACH__ #elif defined __APPLE__ || __MACH__
#include "../common/sysctl.h" #include "sysctl.h"
#endif #endif
#include "../common/global.h" #include "../common/global.h"
#include "../common/soc.h" #include "../common/soc.h"
#include "../common/args.h"
#include "udev.h" #include "udev.h"
#include "midr.h" #include "midr.h"
#include "uarch.h" #include "uarch.h"
#include "sve.h"
bool cores_are_equal(int c1pos, int c2pos, uint32_t* midr_array, int32_t* freq_array) { 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]; return midr_array[c1pos] == midr_array[c2pos] && freq_array[c1pos] == freq_array[c2pos];
@@ -42,17 +39,8 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(uint32_t core) { struct frequency* get_frequency_info(uint32_t core) {
struct frequency* freq = emalloc(sizeof(struct frequency)); struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->base = UNKNOWN_DATA; freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(core); 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; return freq;
} }
@@ -169,15 +157,6 @@ struct features* get_features_info(void) {
feat->SHA1 = hwcaps & HWCAP_SHA1; feat->SHA1 = hwcaps & HWCAP_SHA1;
feat->SHA2 = hwcaps & HWCAP_SHA2; feat->SHA2 = hwcaps & HWCAP_SHA2;
feat->NEON = hwcaps & HWCAP_ASIMD; 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 {
feat->SVE2 = hwcaps & HWCAP2_SVE2;
}
} }
#else #else
else { else {
@@ -193,8 +172,6 @@ struct features* get_features_info(void) {
feat->CRC32 = hwcaps & HWCAP2_CRC32; feat->CRC32 = hwcaps & HWCAP2_CRC32;
feat->SHA1 = hwcaps & HWCAP2_SHA1; feat->SHA1 = hwcaps & HWCAP2_SHA1;
feat->SHA2 = hwcaps & HWCAP2_SHA2; feat->SHA2 = hwcaps & HWCAP2_SHA2;
feat->SVE = false;
feat->SVE2 = false;
} }
#endif // ifdef __aarch64__ #endif // ifdef __aarch64__
#elif defined __APPLE__ || __MACH__ #elif defined __APPLE__ || __MACH__
@@ -204,14 +181,8 @@ struct features* get_features_info(void) {
feat->SHA1 = true; feat->SHA1 = true;
feat->SHA2 = true; feat->SHA2 = true;
feat->NEON = true; feat->NEON = true;
feat->SVE = false;
feat->SVE2 = false;
#endif // ifdef __linux__ #endif // ifdef __linux__
if (feat->SVE || feat->SVE2) {
feat->cntb = sve_cntb();
}
return feat; return feat;
} }
@@ -448,7 +419,7 @@ char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_soc
char* get_str_features(struct cpuInfo* cpu) { char* get_str_features(struct cpuInfo* cpu) {
struct features* feat = cpu->feat; struct features* feat = cpu->feat;
uint32_t max_len = strlen("NEON,SHA1,SHA2,AES,CRC32,SVE,SVE2") + 1; uint32_t max_len = strlen("NEON,SHA1,SHA2,AES,CRC32,") + 1;
uint32_t len = 0; uint32_t len = 0;
char* string = ecalloc(max_len, sizeof(char)); char* string = ecalloc(max_len, sizeof(char));
@@ -456,14 +427,6 @@ char* get_str_features(struct cpuInfo* cpu) {
strcat(string, "NEON,"); strcat(string, "NEON,");
len += 5; len += 5;
} }
if(feat->SVE) {
strcat(string, "SVE,");
len += 4;
}
if(feat->SVE2) {
strcat(string, "SVE2,");
len += 5;
}
if(feat->SHA1) { if(feat->SHA1) {
strcat(string, "SHA1,"); strcat(string, "SHA1,");
len += 5; len += 5;
@@ -513,10 +476,6 @@ 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__) #if defined(__APPLE__) || defined(__MACH__)
printf("hw.cpufamily: 0x%.8X\n", get_sys_info_by_name("hw.cpufamily")); 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")); printf("hw.cpusubfamily: 0x%.8X\n", get_sys_info_by_name("hw.cpusubfamily"));

View File

@@ -11,7 +11,7 @@
#include "../common/pci.h" #include "../common/pci.h"
#if defined(__APPLE__) || defined(__MACH__) #if defined(__APPLE__) || defined(__MACH__)
#include "../common/sysctl.h" #include "sysctl.h"
#endif #endif
#define NA -1 #define NA -1
@@ -167,13 +167,11 @@ bool match_google(char* soc_name, struct system_on_chip* soc) {
// https://www.techinsights.com/ // https://www.techinsights.com/
// https://datasheetspdf.com/pdf-file/1316605/HiSilicon/Hi3660/1 // 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) { bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
char* tmp; char* tmp;
if((tmp = strstr(soc_name, "hi")) != NULL); if((tmp = strstr(soc_name, "hi")) == NULL)
else if((tmp = strstr(soc_name, "kirin")) != NULL); return false;
else return false;
soc->soc_vendor = SOC_VENDOR_KIRIN; soc->soc_vendor = SOC_VENDOR_KIRIN;
@@ -206,7 +204,6 @@ bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
SOC_EQ(tmp, "hi3680", "980", SOC_HISILICON_3680, soc, 7) SOC_EQ(tmp, "hi3680", "980", SOC_HISILICON_3680, soc, 7)
//SOC_EQ(tmp, "?", "985", SOC_KIRIN, soc, 7) //SOC_EQ(tmp, "?", "985", SOC_KIRIN, soc, 7)
SOC_EQ(tmp, "hi3690", "990", SOC_HISILICON_3690, soc, 7) SOC_EQ(tmp, "hi3690", "990", SOC_HISILICON_3690, soc, 7)
SOC_EQ(tmp, "kirin9000s", "9000s", SOC_HISILICON_9000S,soc, 7)
SOC_END SOC_END
} }
@@ -424,9 +421,6 @@ 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 * APQ: Application Processor Qualcomm
* MSM: Mobile Station Modem * MSM: Mobile Station Modem
* In a APQXXXX or MSMXXXX, the second digit represents: * In a APQXXXX or MSMXXXX, the second digit represents:
@@ -584,25 +578,6 @@ 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, "SM8250-AB", "865+", SOC_SNAPD_SM8250_AB, soc, 7)
SOC_EQ(tmp, "SM8350", "888", SOC_SNAPD_SM8350, soc, 5) SOC_EQ(tmp, "SM8350", "888", SOC_SNAPD_SM8350, soc, 5)
SOC_EQ(tmp, "SM8350-AC", "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 SOC_END
} }
@@ -649,37 +624,12 @@ bool match_special(char* soc_name, struct system_on_chip* soc) {
return true; return true;
} }
// New Snapdragon SoCs codenames // Snapdragon 8 Gen 1 reported as "taro"
// 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) { if(strcmp(soc_name, "taro") == 0) {
fill_soc(soc, "8 Gen 1", SOC_SNAPD_SM8450, 4); fill_soc(soc, "8 Gen 1", SOC_SNAPD_SM8450, 4);
return true; 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 // Google Pixel 6
// https://github.com/Dr-Noob/cpufetch/issues/134 // https://github.com/Dr-Noob/cpufetch/issues/134
if(strcmp(soc_name, "oriole") == 0) { if(strcmp(soc_name, "oriole") == 0) {
@@ -752,16 +702,6 @@ struct system_on_chip* guess_soc_from_android(struct system_on_chip* soc) {
else return soc; else return soc;
} }
// 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("ro.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.soc.model: %s", tmp);
else return soc;
}
property_len = android_property_get("ro.product.board", (char *) &tmp); property_len = android_property_get("ro.product.board", (char *) &tmp);
if(property_len > 0) { if(property_len > 0) {
try_parse_soc_from_string(soc, property_len, tmp); try_parse_soc_from_string(soc, property_len, tmp);

View File

@@ -29,7 +29,6 @@ enum {
SOC_HISILICON_3670, SOC_HISILICON_3670,
SOC_HISILICON_3680, SOC_HISILICON_3680,
SOC_HISILICON_3690, SOC_HISILICON_3690,
SOC_HISILICON_9000S,
// Kunpeng // // Kunpeng //
SOC_KUNPENG_920, SOC_KUNPENG_920,
SOC_KUNPENG_930, SOC_KUNPENG_930,
@@ -271,16 +270,11 @@ enum {
SOC_SNAPD_SDM660, SOC_SNAPD_SDM660,
SOC_SNAPD_SM6115, SOC_SNAPD_SM6115,
SOC_SNAPD_SM6125, SOC_SNAPD_SM6125,
SOC_SNAPD_SM6375_AC,
SOC_SNAPD_SM6450,
SOC_SNAPD_SDM670, SOC_SNAPD_SDM670,
SOC_SNAPD_SM6150, SOC_SNAPD_SM6150,
SOC_SNAPD_SM6350, SOC_SNAPD_SM6350,
SOC_SNAPD_SDM710, SOC_SNAPD_SDM710,
SOC_SNAPD_SDM712, SOC_SNAPD_SDM712,
SOC_SNAPD_SM4375,
SOC_SNAPD_SM4450,
SOC_SNAPD_SM4635,
SOC_SNAPD_SM7125, SOC_SNAPD_SM7125,
SOC_SNAPD_SM7150_AA, SOC_SNAPD_SM7150_AA,
SOC_SNAPD_SM7150_AB, SOC_SNAPD_SM7150_AB,
@@ -289,11 +283,6 @@ enum {
SOC_SNAPD_SM7250_AA, SOC_SNAPD_SM7250_AA,
SOC_SNAPD_SM7250_AB, SOC_SNAPD_SM7250_AB,
SOC_SNAPD_SM7250_AC, 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_MSM8974AA,
SOC_SNAPD_MSM8974AB, SOC_SNAPD_MSM8974AB,
SOC_SNAPD_MSM8974AC, SOC_SNAPD_MSM8974AC,
@@ -314,10 +303,6 @@ enum {
SOC_SNAPD_SM8250_AB, SOC_SNAPD_SM8250_AB,
SOC_SNAPD_SM8350, SOC_SNAPD_SM8350,
SOC_SNAPD_SM8450, SOC_SNAPD_SM8450,
SOC_SNAPD_SM8475,
SOC_SNAPD_SM8550_AB,
SOC_SNAPD_SM8635,
SOC_SNAPD_SM8650_AB,
// APPLE // APPLE
SOC_APPLE_M1, SOC_APPLE_M1,
SOC_APPLE_M1_PRO, SOC_APPLE_M1_PRO,
@@ -386,11 +371,11 @@ enum {
inline static VENDOR get_soc_vendor_from_soc(SOC soc) { inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
if(soc >= SOC_BCM_2835 && soc <= SOC_BCM_2712) return SOC_VENDOR_BROADCOM; if(soc >= SOC_BCM_2835 && soc <= SOC_BCM_2712) return SOC_VENDOR_BROADCOM;
else if(soc >= SOC_HISILICON_3620 && soc <= SOC_HISILICON_9000S) return SOC_VENDOR_KIRIN; else if(soc >= SOC_HISILICON_3620 && soc <= SOC_HISILICON_3690) return SOC_VENDOR_KIRIN;
else if(soc >= SOC_KUNPENG_920 && soc <= SOC_KUNPENG_930) return SOC_VENDOR_KUNPENG; 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_EXYNOS_3475 && soc <= SOC_EXYNOS_880) return SOC_VENDOR_EXYNOS;
else if(soc >= SOC_MTK_MT6893 && soc <= SOC_MTK_MT8783) return SOC_VENDOR_MEDIATEK; else if(soc >= SOC_MTK_MT6893 && soc <= SOC_MTK_MT8783) return SOC_VENDOR_MEDIATEK;
else if(soc >= SOC_SNAPD_QSD8650 && soc <= SOC_SNAPD_SM8650_AB) return SOC_VENDOR_SNAPDRAGON; else if(soc >= SOC_SNAPD_QSD8650 && soc <= SOC_SNAPD_SM8450) return SOC_VENDOR_SNAPDRAGON;
else if(soc >= SOC_APPLE_M1 && soc <= SOC_APPLE_M3_MAX) return SOC_VENDOR_APPLE; 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_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_ROCKCHIP_3288 && soc <= SOC_ROCKCHIP_3588) return SOC_VENDOR_ROCKCHIP;

View File

@@ -1,15 +0,0 @@
#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
}

View File

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

View File

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

View File

@@ -75,7 +75,6 @@ static const ISA isas_uarch[] = {
[UARCH_THUNDERX] = ISA_ARMv8_A, [UARCH_THUNDERX] = ISA_ARMv8_A,
[UARCH_THUNDERX2] = ISA_ARMv8_1_A, [UARCH_THUNDERX2] = ISA_ARMv8_1_A,
[UARCH_TAISHAN_V110] = ISA_ARMv8_2_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_TAISHAN_V200] = ISA_ARMv8_2_A, // Not confirmed
[UARCH_DENVER] = ISA_ARMv8_A, [UARCH_DENVER] = ISA_ARMv8_A,
[UARCH_DENVER2] = ISA_ARMv8_A, [UARCH_DENVER2] = ISA_ARMv8_A,
@@ -203,10 +202,8 @@ 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, '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', 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', 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', 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', 0x000, NA, NA, "Denver", UARCH_DENVER, CPU_VENDOR_NVIDIA)
CHECK_UARCH(arch, cpu, 'N', 0x003, NA, NA, "Denver2", UARCH_DENVER2, CPU_VENDOR_NVIDIA) CHECK_UARCH(arch, cpu, 'N', 0x003, NA, NA, "Denver2", UARCH_DENVER2, CPU_VENDOR_NVIDIA)
@@ -294,10 +291,7 @@ int get_vpus_width(struct cpuInfo* cpu) {
case UARCH_NEOVERSE_V1: case UARCH_NEOVERSE_V1:
return 256; return 256;
default: default:
if (cpu->feat->SVE && cpu->feat->cntb > 0) { if(cpu->feat->NEON) {
return cpu->feat->cntb * 8;
}
else if (cpu->feat->NEON) {
if(is_ARMv8_or_newer(cpu)) { if(is_ARMv8_or_newer(cpu)) {
return 128; return 128;
} }
@@ -331,7 +325,6 @@ int get_number_of_vpus(struct cpuInfo* cpu) {
case UARCH_ICESTORM: // [https://dougallj.github.io/applecpu/icestorm-simd.html] 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_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_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_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_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] case UARCH_CORTEX_A72: // [https://www.anandtech.com/show/10347/arm-cortex-a73-artemis-unveiled/2]

View File

@@ -83,9 +83,7 @@ enum {
UARCH_BRAHMA_B15, UARCH_BRAHMA_B15,
UARCH_BRAHMA_B53, UARCH_BRAHMA_B53,
UARCH_XGENE, // Applied Micro X-Gene. UARCH_XGENE, // Applied Micro X-Gene.
// HUAWEI
UARCH_TAISHAN_V110, // HiSilicon TaiShan v110 UARCH_TAISHAN_V110, // HiSilicon TaiShan v110
UARCH_TAISHAN_V120, // HiSilicon TaiShan v120
UARCH_TAISHAN_V200, // HiSilicon TaiShan v200 UARCH_TAISHAN_V200, // HiSilicon TaiShan v200
// PHYTIUM // PHYTIUM
UARCH_XIAOMI, // Not to be confused with Xiaomi Inc UARCH_XIAOMI, // Not to be confused with Xiaomi Inc

View File

@@ -28,7 +28,6 @@ struct args_struct {
bool help_flag; bool help_flag;
bool raw_flag; bool raw_flag;
bool accurate_pp; bool accurate_pp;
bool measure_max_frequency_flag;
bool full_cpu_name_flag; bool full_cpu_name_flag;
bool logo_long; bool logo_long;
bool logo_short; bool logo_short;
@@ -41,37 +40,35 @@ struct args_struct {
}; };
const char args_chr[] = { const char args_chr[] = {
/* [ARG_STYLE] = */ 's', /* [ARG_STYLE] = */ 's',
/* [ARG_COLOR] = */ 'c', /* [ARG_COLOR] = */ 'c',
/* [ARG_HELP] = */ 'h', /* [ARG_HELP] = */ 'h',
/* [ARG_RAW] = */ 'r', /* [ARG_RAW] = */ 'r',
/* [ARG_FULLCPUNAME] = */ 'F', /* [ARG_FULLCPUNAME] = */ 'F',
/* [ARG_LOGO_LONG] = */ 1, /* [ARG_LOGO_LONG] = */ 1,
/* [ARG_LOGO_SHORT] = */ 2, /* [ARG_LOGO_SHORT] = */ 2,
/* [ARG_LOGO_INTEL_NEW] = */ 3, /* [ARG_LOGO_INTEL_NEW] = */ 3,
/* [ARG_LOGO_INTEL_OLD] = */ 4, /* [ARG_LOGO_INTEL_OLD] = */ 4,
/* [ARG_ACCURATE_PP] = */ 5, /* [ARG_ACCURATE_PP] = */ 5,
/* [ARG_MEASURE_MAX_FREQ] = */ 6, /* [ARG_DEBUG] = */ 'd',
/* [ARG_DEBUG] = */ 'd', /* [ARG_VERBOSE] = */ 'v',
/* [ARG_VERBOSE] = */ 'v', /* [ARG_VERSION] = */ 'V',
/* [ARG_VERSION] = */ 'V',
}; };
const char *args_str[] = { const char *args_str[] = {
/* [ARG_STYLE] = */ "style", /* [ARG_STYLE] = */ "style",
/* [ARG_COLOR] = */ "color", /* [ARG_COLOR] = */ "color",
/* [ARG_HELP] = */ "help", /* [ARG_HELP] = */ "help",
/* [ARG_RAW] = */ "raw", /* [ARG_RAW] = */ "raw",
/* [ARG_FULLCPUNAME] = */ "full-cpu-name", /* [ARG_FULLCPUNAME] = */ "full-cpu-name",
/* [ARG_LOGO_LONG] = */ "logo-long", /* [ARG_LOGO_LONG] = */ "logo-long",
/* [ARG_LOGO_SHORT] = */ "logo-short", /* [ARG_LOGO_SHORT] = */ "logo-short",
/* [ARG_LOGO_INTEL_NEW] = */ "logo-intel-new", /* [ARG_LOGO_INTEL_NEW] = */ "logo-intel-new",
/* [ARG_LOGO_INTEL_OLD] = */ "logo-intel-old", /* [ARG_LOGO_INTEL_OLD] = */ "logo-intel-old",
/* [ARG_ACCURATE_PP] = */ "accurate-pp", /* [ARG_ACCURATE_PP] = */ "accurate-pp",
/* [ARG_MEASURE_MAX_FREQ] = */ "measure-max-freq", /* [ARG_DEBUG] = */ "debug",
/* [ARG_DEBUG] = */ "debug", /* [ARG_VERBOSE] = */ "verbose",
/* [ARG_VERBOSE] = */ "verbose", /* [ARG_VERSION] = */ "version",
/* [ARG_VERSION] = */ "version",
}; };
static struct args_struct args; static struct args_struct args;
@@ -104,10 +101,6 @@ bool accurate_pp(void) {
return args.accurate_pp; return args.accurate_pp;
} }
bool measure_max_frequency_flag(void) {
return args.measure_max_frequency_flag;
}
bool show_full_cpu_name(void) { bool show_full_cpu_name(void) {
return args.full_cpu_name_flag; return args.full_cpu_name_flag;
} }
@@ -229,20 +222,12 @@ char* build_short_options(void) {
memset(str, 0, sizeof(char) * (len*2 + 1)); memset(str, 0, sizeof(char) * (len*2 + 1));
#ifdef ARCH_X86 #ifdef ARCH_X86
sprintf(str, "%c:%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[ARG_STYLE], c[ARG_COLOR], c[ARG_HELP], c[ARG_STYLE], c[ARG_COLOR], c[ARG_HELP],
c[ARG_RAW], c[ARG_FULLCPUNAME], c[ARG_RAW], c[ARG_FULLCPUNAME],
c[ARG_LOGO_SHORT], c[ARG_LOGO_LONG], c[ARG_LOGO_SHORT], c[ARG_LOGO_LONG],
c[ARG_LOGO_INTEL_NEW], c[ARG_LOGO_INTEL_OLD], c[ARG_LOGO_INTEL_NEW], c[ARG_LOGO_INTEL_OLD],
c[ARG_ACCURATE_PP], c[ARG_MEASURE_MAX_FREQ], c[ARG_ACCURATE_PP], c[ARG_DEBUG], c[ARG_VERBOSE],
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]); c[ARG_VERSION]);
#else #else
sprintf(str, "%c:%c:%c%c%c%c%c%c", sprintf(str, "%c:%c:%c%c%c%c%c%c",
@@ -278,24 +263,21 @@ bool parse_args(int argc, char* argv[]) {
set_log_level(true); set_log_level(true);
const struct option long_options[] = { const struct option long_options[] = {
{args_str[ARG_STYLE], required_argument, 0, args_chr[ARG_STYLE] }, {args_str[ARG_STYLE], required_argument, 0, args_chr[ARG_STYLE] },
{args_str[ARG_COLOR], required_argument, 0, args_chr[ARG_COLOR] }, {args_str[ARG_COLOR], required_argument, 0, args_chr[ARG_COLOR] },
{args_str[ARG_HELP], no_argument, 0, args_chr[ARG_HELP] }, {args_str[ARG_HELP], no_argument, 0, args_chr[ARG_HELP] },
#ifdef ARCH_X86 #ifdef ARCH_X86
{args_str[ARG_LOGO_INTEL_NEW], no_argument, 0, args_chr[ARG_LOGO_INTEL_NEW] }, {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_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_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_FULLCPUNAME], no_argument, 0, args_chr[ARG_FULLCPUNAME] }, {args_str[ARG_RAW], no_argument, 0, args_chr[ARG_RAW] },
{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 #endif
{args_str[ARG_LOGO_SHORT], no_argument, 0, args_chr[ARG_LOGO_SHORT] }, {args_str[ARG_LOGO_SHORT], no_argument, 0, args_chr[ARG_LOGO_SHORT] },
{args_str[ARG_LOGO_LONG], no_argument, 0, args_chr[ARG_LOGO_LONG] }, {args_str[ARG_LOGO_LONG], no_argument, 0, args_chr[ARG_LOGO_LONG] },
{args_str[ARG_DEBUG], no_argument, 0, args_chr[ARG_DEBUG] }, {args_str[ARG_DEBUG], no_argument, 0, args_chr[ARG_DEBUG] },
{args_str[ARG_VERBOSE], no_argument, 0, args_chr[ARG_VERBOSE] }, {args_str[ARG_VERBOSE], no_argument, 0, args_chr[ARG_VERBOSE] },
{args_str[ARG_VERSION], no_argument, 0, args_chr[ARG_VERSION] }, {args_str[ARG_VERSION], no_argument, 0, args_chr[ARG_VERSION] },
{0, 0, 0, 0} {0, 0, 0, 0}
}; };
@@ -331,9 +313,6 @@ bool parse_args(int argc, char* argv[]) {
else if(opt == args_chr[ARG_ACCURATE_PP]) { else if(opt == args_chr[ARG_ACCURATE_PP]) {
args.accurate_pp = true; 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]) { else if(opt == args_chr[ARG_FULLCPUNAME]) {
args.full_cpu_name_flag = true; args.full_cpu_name_flag = true;
} }

View File

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

View File

@@ -145,25 +145,17 @@ char* get_str_l3(struct cache* cach) {
char* get_str_freq(struct frequency* freq) { char* get_str_freq(struct frequency* freq) {
//Max 3 digits and 3 for '(M/G)Hz' plus 1 for '\0' //Max 3 digits and 3 for '(M/G)Hz' plus 1 for '\0'
uint32_t size = (1+5+1+3+1); uint32_t size = (5+1+3+1);
assert(strlen(STRING_UNKNOWN)+1 <= size); assert(strlen(STRING_UNKNOWN)+1 <= size);
char* string = ecalloc(size, sizeof(char)); char* string = emalloc(sizeof(char)*size);
memset(string, 0, sizeof(char)*size);
if(freq->max == UNKNOWN_DATA || freq->max < 0) { if(freq->max == UNKNOWN_DATA || freq->max < 0)
snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN); snprintf(string,strlen(STRING_UNKNOWN)+1,STRING_UNKNOWN);
} else if(freq->max >= 1000)
else if(freq->max >= 1000) { snprintf(string,size,"%.3f "STRING_GIGAHERZ,(float)(freq->max)/1000);
if (freq->measured) else
snprintf(string,size,"~%.3f "STRING_GIGAHERZ,(float)(freq->max)/1000); snprintf(string,size,"%d "STRING_MEGAHERZ,freq->max);
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; return string;
} }

View File

@@ -58,8 +58,6 @@ typedef int32_t VENDOR;
struct frequency { struct frequency {
int32_t base; int32_t base;
int32_t max; int32_t max;
// Indicates if max frequency was measured
bool measured;
}; };
struct hypervisor { struct hypervisor {
@@ -124,9 +122,6 @@ struct features {
bool SHA1; bool SHA1;
bool SHA2; bool SHA2;
bool CRC32; bool CRC32;
bool SVE;
bool SVE2;
uint64_t cntb;
#endif #endif
}; };

View File

@@ -1,195 +0,0 @@
#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__

View File

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

View File

@@ -1,14 +1,3 @@
#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 <stdarg.h>
#include <stdio.h> #include <stdio.h>
#include <stdlib.h> #include <stdlib.h>
@@ -62,7 +51,7 @@
#endif #endif
#ifndef GIT_FULL_VERSION #ifndef GIT_FULL_VERSION
static const char* VERSION = "1.06"; static const char* VERSION = "1.05";
#endif #endif
enum { enum {
@@ -210,34 +199,6 @@ void* erealloc(void *ptr, size_t size) {
return newptr; 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) { void print_version(FILE *restrict stream) {
#ifdef GIT_FULL_VERSION #ifdef GIT_FULL_VERSION
fprintf(stream, "cpufetch %s (%s %s)\n", GIT_FULL_VERSION, OS_STR, ARCH_STR); fprintf(stream, "cpufetch %s (%s %s)\n", GIT_FULL_VERSION, OS_STR, ARCH_STR);

View File

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

View File

@@ -30,17 +30,11 @@ void print_help(char *argv[]) {
#ifdef ARCH_X86 #ifdef ARCH_X86
#ifdef __linux__ #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])), ""); 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])), "");
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 // __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 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(" --%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 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])), ""); 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 #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 this help and exit\n", c[ARG_HELP], t[ARG_HELP], (int) (max_len-strlen(t[ARG_HELP])), "");
printf(" -%c, --%s %*s Print cpufetch version and exit\n", c[ARG_VERSION], t[ARG_VERSION], (int) (max_len-strlen(t[ARG_VERSION])), ""); printf(" -%c, --%s %*s Print cpufetch version and exit\n", c[ARG_VERSION], t[ARG_VERSION], (int) (max_len-strlen(t[ARG_VERSION])), "");
@@ -51,7 +45,7 @@ void print_help(char *argv[]) {
printf(" * \"amd\": Use AMD color scheme \n"); printf(" * \"amd\": Use AMD color scheme \n");
printf(" * \"ibm\", Use IBM color scheme \n"); printf(" * \"ibm\", Use IBM color scheme \n");
printf(" * \"arm\": Use ARM color scheme \n"); printf(" * \"arm\": Use ARM color scheme \n");
printf(" * \"rockchip\": Use Rockchip color scheme \n"); printf(" * \"rockchip\": Use ARM color scheme \n");
printf(" * \"sifive\": Use SiFive 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(" * custom: If the argument of --color does not match any of the previous strings, a custom scheme can be specified.\n");
printf(" 5 colors must be given in RGB with the format: R,G,B:R,G,B:...\n"); printf(" 5 colors must be given in RGB with the format: R,G,B:R,G,B:...\n");
@@ -86,11 +80,6 @@ void print_help(char *argv[]) {
printf(" --accurate-pp option, which will measure the AVX frequency and show a more precise estimation\n"); 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(" (this option is only available in x86 architectures).\n");
printf(" To precisely measure peak performance, see: https://github.com/Dr-Noob/peakperf\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[]) { int main(int argc, char* argv[]) {

View File

@@ -61,7 +61,6 @@ enum {
ATTRIBUTE_NCORES, ATTRIBUTE_NCORES,
ATTRIBUTE_NCORES_DUAL, ATTRIBUTE_NCORES_DUAL,
#ifdef ARCH_X86 #ifdef ARCH_X86
ATTRIBUTE_SSE,
ATTRIBUTE_AVX, ATTRIBUTE_AVX,
ATTRIBUTE_FMA, ATTRIBUTE_FMA,
#elif ARCH_PPC #elif ARCH_PPC
@@ -97,7 +96,6 @@ static const char* ATTRIBUTE_FIELDS [] = {
"Cores:", "Cores:",
"Cores (Total):", "Cores (Total):",
#ifdef ARCH_X86 #ifdef ARCH_X86
"SSE:",
"AVX:", "AVX:",
"FMA:", "FMA:",
#elif ARCH_PPC #elif ARCH_PPC
@@ -133,7 +131,6 @@ static const char* ATTRIBUTE_FIELDS_SHORT [] = {
"Cores:", "Cores:",
"Cores (Total):", "Cores (Total):",
#ifdef ARCH_X86 #ifdef ARCH_X86
"SSE:",
"AVX:", "AVX:",
"FMA:", "FMA:",
#elif ARCH_PPC #elif ARCH_PPC
@@ -597,7 +594,6 @@ 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++) { for(int i = 0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
char* max_frequency = get_str_freq(ptr->freq); char* max_frequency = get_str_freq(ptr->freq);
char* avx = get_str_avx(ptr); char* avx = get_str_avx(ptr);
char* sse = get_str_sse(ptr);
char* fma = get_str_fma(ptr); char* fma = get_str_fma(ptr);
char* cpu_num = emalloc(sizeof(char) * 9); char* cpu_num = emalloc(sizeof(char) * 9);
@@ -632,18 +628,8 @@ bool print_cpufetch_x86(struct cpuInfo* cpu, STYLE s, struct color** cs, struct
setAttribute(art, ATTRIBUTE_NCORES, n_cores); setAttribute(art, ATTRIBUTE_NCORES, n_cores);
} }
} }
setAttribute(art, ATTRIBUTE_AVX, avx);
// Show the most modern vector instructions. setAttribute(art, ATTRIBUTE_FMA, fma);
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(l1i != NULL) setAttribute(art, ATTRIBUTE_L1i, l1i);
if(l1d != NULL) setAttribute(art, ATTRIBUTE_L1d, l1d); if(l1d != NULL) setAttribute(art, ATTRIBUTE_L1d, l1d);
if(l2 != NULL) setAttribute(art, ATTRIBUTE_L2, l2); if(l2 != NULL) setAttribute(art, ATTRIBUTE_L2, l2);

View File

@@ -146,7 +146,6 @@ struct uarch* get_cpu_uarch(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(void) { struct frequency* get_frequency_info(void) {
struct frequency* freq = emalloc(sizeof(struct frequency)); struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->max = get_max_freq_from_file(0); freq->max = get_max_freq_from_file(0);
freq->base = get_min_freq_from_file(0); freq->base = get_min_freq_from_file(0);

View File

@@ -19,7 +19,6 @@
struct frequency* get_frequency_info(uint32_t core) { struct frequency* get_frequency_info(uint32_t core) {
struct frequency* freq = emalloc(sizeof(struct frequency)); struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
freq->base = UNKNOWN_DATA; freq->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(core); freq->max = get_max_freq_from_file(core);

View File

@@ -72,6 +72,34 @@ 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__ #ifdef __linux__
int get_total_cores_module(int total_cores, int module) { int get_total_cores_module(int total_cores, int module) {
int total_modules = 2; int total_modules = 2;
@@ -369,11 +397,6 @@ 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) { 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_id;
uint32_t* apic_ids = emalloc(sizeof(uint32_t) * topo->total_cores_module); uint32_t* apic_ids = emalloc(sizeof(uint32_t) * topo->total_cores_module);
uint32_t* apic_pkg = emalloc(sizeof(uint32_t) * topo->total_cores_module); uint32_t* apic_pkg = emalloc(sizeof(uint32_t) * topo->total_cores_module);

View File

@@ -17,6 +17,10 @@ struct apic {
bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo); bool get_topology_from_apic(struct cpuInfo* cpu, struct topology* topo);
uint32_t is_smt_enabled_amd(struct topology* topo); uint32_t is_smt_enabled_amd(struct topology* topo);
#ifndef __APPLE__
bool bind_to_cpu(int cpu_id);
#endif
#ifdef __linux__ #ifdef __linux__
int get_total_cores_module(int total_cores, int module); int get_total_cores_module(int total_cores, int module);
#endif #endif

View File

@@ -6,10 +6,6 @@
#include <unistd.h> #include <unistd.h>
#endif #endif
#ifdef __linux__
#include "../common/freq.h"
#endif
#include <stdio.h> #include <stdio.h>
#include <stdlib.h> #include <stdlib.h>
#include <string.h> #include <string.h>
@@ -223,7 +219,7 @@ int64_t get_peak_performance(struct cpuInfo* cpu, bool accurate_pp) {
#endif #endif
//First, check we have consistent data //First, check we have consistent data
if(freq == UNKNOWN_DATA || topo == NULL || topo->logical_cores == UNKNOWN_DATA) { if(freq == UNKNOWN_DATA || topo->logical_cores == UNKNOWN_DATA) {
return -1; return -1;
} }
@@ -456,7 +452,7 @@ struct cpuInfo* get_cpu_info(void) {
cpu->cach = NULL; cpu->cach = NULL;
cpu->feat = NULL; cpu->feat = NULL;
cpu->num_cpus = 1; uint32_t modules = 1;
uint32_t eax = 0; uint32_t eax = 0;
uint32_t ebx = 0; uint32_t ebx = 0;
uint32_t ecx = 0; uint32_t ecx = 0;
@@ -514,12 +510,12 @@ struct cpuInfo* get_cpu_info(void) {
cpu->hybrid_flag = (edx >> 15) & 0x1; cpu->hybrid_flag = (edx >> 15) & 0x1;
} }
if(cpu->hybrid_flag) cpu->num_cpus = 2; if(cpu->hybrid_flag) modules = 2;
struct cpuInfo* ptr = cpu; struct cpuInfo* ptr = cpu;
for(uint32_t i=0; i < cpu->num_cpus; i++) { for(uint32_t i=0; i < modules; i++) {
int32_t first_core; int32_t first_core;
set_cpu_module(i, cpu->num_cpus, &first_core); set_cpu_module(i, modules, &first_core);
if(i > 0) { if(i > 0) {
ptr->next_cpu = emalloc(sizeof(struct cpuInfo)); ptr->next_cpu = emalloc(sizeof(struct cpuInfo));
@@ -554,7 +550,11 @@ struct cpuInfo* get_cpu_info(void) {
cpu->cpu_name = infer_cpu_name_from_uarch(cpu->arch); 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); ptr->cach = get_cache_info(ptr);
if(ptr->cach == NULL) return cpu;
if(cpu->hybrid_flag) { if(cpu->hybrid_flag) {
ptr->topo = get_topology_info(ptr, ptr->cach, i); ptr->topo = get_topology_info(ptr, ptr->cach, i);
@@ -562,23 +562,16 @@ struct cpuInfo* get_cpu_info(void) {
else { else {
ptr->topo = get_topology_info(ptr, ptr->cach, -1); 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()); cpu->peak_performance = get_peak_performance(cpu, accurate_pp());
return cpu; return cpu;
} }
bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) { 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) { if(cpu->maxExtendedLevels >= 0x8000001D && cpu->topology_extensions) {
uint32_t i, eax, ebx, ecx, edx, num_sharing_cache, cache_type, cache_level; uint32_t i, eax, ebx, ecx, edx, num_sharing_cache, cache_type, cache_level;
@@ -654,17 +647,10 @@ bool get_cache_topology_amd(struct cpuInfo* cpu, struct topology* topo) {
#ifdef __linux__ #ifdef __linux__
void get_topology_from_udev(struct topology* topo) { void get_topology_from_udev(struct topology* topo) {
topo->total_cores = get_ncores_from_cpuinfo();
// TODO: To be improved in the future // TODO: To be improved in the future
if (topo->total_cores == 1) { topo->total_cores = get_ncores_from_cpuinfo();
// We can assume it's a single core CPU topo->logical_cores = topo->total_cores;
topo->logical_cores = topo->total_cores; topo->physical_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_available = 1;
topo->smt_supported = 1; topo->smt_supported = 1;
topo->sockets = 1; topo->sockets = 1;
@@ -709,27 +695,29 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, int
topo->total_cores_module = topo->total_cores; topo->total_cores_module = topo->total_cores;
} }
bool toporet = false;
switch(cpu->cpu_vendor) { switch(cpu->cpu_vendor) {
case CPU_VENDOR_INTEL: case CPU_VENDOR_INTEL:
if (cpu->maxLevels >= 0x00000004) { if (cpu->maxLevels >= 0x00000004) {
toporet = get_topology_from_apic(cpu, topo); bool toporet = get_topology_from_apic(cpu, topo);
if(!toporet) {
#ifdef __linux__
printWarn("Failed to retrieve topology from APIC, using udev...\n");
get_topology_from_udev(topo);
#else
printErr("Failed to retrieve topology from APIC, assumming default values...\n");
topo->logical_cores = UNKNOWN_DATA;
topo->physical_cores = UNKNOWN_DATA;
topo->smt_available = 1;
topo->smt_supported = 1;
#endif
}
} }
else { else {
printWarn("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000004, cpu->maxLevels); printWarn("Can't read topology information from cpuid (needed level is 0x%.8X, max is 0x%.8X)", 0x00000001, cpu->maxLevels);
} topo->physical_cores = 1;
if(!toporet) { topo->logical_cores = 1;
#ifdef __linux__ topo->smt_available = 1;
printWarn("Failed to retrieve topology from APIC, using udev..."); topo->smt_supported = 1;
get_topology_from_udev(topo);
#else
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
} }
break; break;
case CPU_VENDOR_AMD: case CPU_VENDOR_AMD:
@@ -750,15 +738,10 @@ struct topology* get_topology_info(struct cpuInfo* cpu, struct cache* cach, int
} }
} }
else { else {
#ifdef __linux__ printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X)", 0x80000008, cpu->maxExtendedLevels);
printWarn("Can't read topology information from cpuid (needed extended level is 0x%.8X, max is 0x%.8X), using udev...", 0x80000008, cpu->maxExtendedLevels); topo->physical_cores = 1;
get_topology_from_udev(topo); topo->logical_cores = 1;
#else topo->smt_supported = 1;
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) { if (cpu->maxLevels >= 0x00000001) {
@@ -935,7 +918,6 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
struct frequency* get_frequency_info(struct cpuInfo* cpu) { struct frequency* get_frequency_info(struct cpuInfo* cpu) {
struct frequency* freq = emalloc(sizeof(struct frequency)); struct frequency* freq = emalloc(sizeof(struct frequency));
freq->measured = false;
if(cpu->maxLevels < 0x00000016) { if(cpu->maxLevels < 0x00000016) {
#if defined (_WIN32) || defined (__APPLE__) #if defined (_WIN32) || defined (__APPLE__)
@@ -945,7 +927,7 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
#else #else
printWarn("Can't read frequency information from cpuid (needed level is 0x%.8X, max is 0x%.8X). Using udev", 0x00000016, cpu->maxLevels); 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->base = UNKNOWN_DATA;
freq->max = get_max_freq_from_file(cpu->first_core_id); freq->max = get_max_freq_from_file(0);
if(freq->max == 0) { if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz"); printWarn("Read max CPU frequency from udev and got 0 MHz");
@@ -972,7 +954,7 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
printWarn("Read max CPU frequency from CPUID and got 0 MHz"); printWarn("Read max CPU frequency from CPUID and got 0 MHz");
#ifdef __linux__ #ifdef __linux__
printWarn("Using udev to detect frequency"); printWarn("Using udev to detect frequency");
freq->max = get_max_freq_from_file(cpu->first_core_id); freq->max = get_max_freq_from_file(0);
if(freq->max == 0) { if(freq->max == 0) {
printWarn("Read max CPU frequency from udev and got 0 MHz"); printWarn("Read max CPU frequency from udev and got 0 MHz");
@@ -984,15 +966,6 @@ 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; return freq;
} }
@@ -1014,34 +987,25 @@ char* get_str_topology(struct cpuInfo* cpu, struct topology* topo, bool dual_soc
string = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1)); string = emalloc(sizeof(char) * (strlen(STRING_UNKNOWN) + 1));
strcpy(string, STRING_UNKNOWN); strcpy(string, STRING_UNKNOWN);
} }
else { else if(topo->smt_supported > 1) {
char cores_str[6]; // 4 for digits, 21 for ' cores (SMT disabled)' which is the longest possible output
memset(cores_str, 0, sizeof(char) * 6); uint32_t max_size = 4+21+1;
if (topo->physical_cores * topo_sockets > 1) string = emalloc(sizeof(char) * max_size);
strcpy(cores_str, "cores");
else
strcpy(cores_str, "core");
if(topo->smt_supported > 1) { if(topo->smt_available > 1)
// 4 for digits, 21 for ' cores (SMT disabled)' which is the longest possible output snprintf(string, max_size, "%d cores (%d threads)", topo->physical_cores * topo_sockets, topo->logical_cores * topo_sockets);
uint32_t max_size = 4+21+1;
string = emalloc(sizeof(char) * max_size);
if(topo->smt_available > 1)
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 %s (SMT disabled)", topo->physical_cores * topo_sockets, cores_str);
else
snprintf(string, max_size, "%d %s (HT disabled)", topo->physical_cores * topo_sockets, cores_str);
}
}
else { else {
uint32_t max_size = 4+7+1; if(cpu->cpu_vendor == CPU_VENDOR_AMD)
string = emalloc(sizeof(char) * max_size); snprintf(string, max_size, "%d cores (SMT disabled)", topo->physical_cores * topo_sockets);
snprintf(string, max_size, "%d %s",topo->physical_cores * topo_sockets, cores_str); else
snprintf(string, max_size, "%d cores (HT disabled)", topo->physical_cores * topo_sockets);
} }
} }
else {
uint32_t max_size = 4+7+1;
string = emalloc(sizeof(char) * max_size);
snprintf(string, max_size, "%d cores",topo->physical_cores * topo_sockets);
}
return string; return string;
} }
@@ -1101,14 +1065,8 @@ char* get_str_sse(struct cpuInfo* cpu) {
last+=SSE4_2_sl; last+=SSE4_2_sl;
} }
if (last == 0) { //Purge last comma
snprintf(string, 2+1, "No"); string[last-1] = '\0';
}
else {
//Purge last comma
string[last-1] = '\0';
}
return string; return string;
} }