mirror of
https://github.com/Dr-Noob/cpufetch.git
synced 2026-03-25 07:50:40 +01:00
Compare commits
25 Commits
i261
...
fix-accura
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
14cee5be6b | ||
|
|
b6eb450eb3 | ||
|
|
4ccafdc4fa | ||
|
|
dc9b111e85 | ||
|
|
5093575f11 | ||
|
|
dc251a457e | ||
|
|
ee69cffdbb | ||
|
|
de4f47a400 | ||
|
|
5833601178 | ||
|
|
eb8fad2843 | ||
|
|
bd38951439 | ||
|
|
057a36efd5 | ||
|
|
56901d70ab | ||
|
|
5bd507e4b6 | ||
|
|
9192ba3eb8 | ||
|
|
807a13d29e | ||
|
|
15a803dae5 | ||
|
|
0507355372 | ||
|
|
9f66a137c5 | ||
|
|
324d0fbe94 | ||
|
|
af8bb16302 | ||
|
|
40374121b8 | ||
|
|
025e28c516 | ||
|
|
7ad19d113c | ||
|
|
13605ed0ce |
4
Makefile
4
Makefile
@@ -120,9 +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"
|
||||
|
||||
@@ -176,7 +176,9 @@ struct features* get_features_info(void) {
|
||||
printWarn("Unable to retrieve AT_HWCAP2 using getauxval");
|
||||
}
|
||||
else {
|
||||
feat->SVE2 = hwcaps & HWCAP2_SVE2;
|
||||
#ifdef HWCAP2_SVE2
|
||||
feat->SVE2 = hwcaps & HWCAP2_SVE2;
|
||||
#endif
|
||||
}
|
||||
}
|
||||
#else
|
||||
@@ -412,6 +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);
|
||||
|
||||
135
src/arm/soc.c
135
src/arm/soc.c
@@ -18,6 +18,11 @@
|
||||
#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",
|
||||
@@ -28,8 +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]);
|
||||
@@ -102,7 +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++;
|
||||
@@ -128,24 +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
|
||||
}
|
||||
|
||||
@@ -156,7 +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)
|
||||
@@ -175,7 +179,7 @@ bool match_hisilicon(char* soc_name, struct system_on_chip* soc) {
|
||||
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)
|
||||
@@ -217,7 +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
|
||||
@@ -277,7 +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 //
|
||||
@@ -460,7 +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 //
|
||||
@@ -613,7 +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
|
||||
@@ -737,7 +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);
|
||||
}
|
||||
|
||||
@@ -745,34 +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;
|
||||
}
|
||||
|
||||
// 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);
|
||||
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.soc.model: %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.product.board", (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.product.board: %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("ro.board.platform", (char *) &tmp);
|
||||
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->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_BOARD_PLATFORM, tmp);
|
||||
else return soc;
|
||||
}
|
||||
|
||||
@@ -838,7 +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++;
|
||||
@@ -885,7 +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++;
|
||||
@@ -943,6 +947,7 @@ bool match_dt(struct system_on_chip* soc, char* dt, int filelen, char* expected_
|
||||
// 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);
|
||||
@@ -966,9 +971,21 @@ struct system_on_chip* guess_soc_from_devtree(struct system_on_chip* soc) {
|
||||
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)
|
||||
// https://github.com/Dr-Noob/cpufetch/issues/261
|
||||
// https://www.nxp.com/docs/en/fact-sheet/IMX8MPLUSFS.pdf
|
||||
DT_EQ(dt, len, soc, "imx8mp-nitrogen8mp", "i.MX 8M Plus", SOC_NXP_IMX8MP, 14)
|
||||
// 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)
|
||||
DT_END(dt, len)
|
||||
}
|
||||
|
||||
@@ -999,7 +1016,7 @@ struct system_on_chip* guess_soc_from_pci(struct system_on_chip* soc, struct cpu
|
||||
|
||||
if (socFromPCI[index].vendor_id == dev->vendor_id &&
|
||||
socFromPCI[index].device_id == dev->device_id) {
|
||||
fill_soc(soc, socFromPCI[index].soc.soc_name, socFromPCI[index].soc.soc_model, socFromPCI[index].soc.process);
|
||||
fill_soc(soc, socFromPCI[index].soc.name, socFromPCI[index].soc.model, socFromPCI[index].soc.process);
|
||||
return soc;
|
||||
}
|
||||
}
|
||||
@@ -1083,12 +1100,12 @@ 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) {
|
||||
@@ -1110,19 +1127,21 @@ 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) {
|
||||
@@ -1133,12 +1152,12 @@ 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;
|
||||
}
|
||||
@@ -1147,15 +1166,15 @@ 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 {
|
||||
@@ -1164,7 +1183,7 @@ 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);
|
||||
}
|
||||
@@ -1176,30 +1195,30 @@ 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 previous steps failed, try with the device tree
|
||||
if (soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
|
||||
if (soc->vendor == SOC_VENDOR_UNKNOWN) {
|
||||
soc = guess_soc_from_devtree(soc);
|
||||
}
|
||||
// If previous steps failed, try with nvmem
|
||||
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
|
||||
if(soc->vendor == SOC_VENDOR_UNKNOWN) {
|
||||
soc = guess_soc_from_nvmem(soc);
|
||||
}
|
||||
// If previous steps failed, try infering it from the microarchitecture
|
||||
if(soc->soc_vendor == SOC_VENDOR_UNKNOWN) {
|
||||
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->soc_vendor == SOC_VENDOR_UNKNOWN) {
|
||||
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 {
|
||||
@@ -1207,7 +1226,7 @@ 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));
|
||||
|
||||
@@ -383,7 +383,16 @@ enum {
|
||||
// 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,
|
||||
// UNKNOWN
|
||||
SOC_MODEL_UNKNOWN
|
||||
};
|
||||
@@ -401,7 +410,8 @@ inline static VENDOR get_soc_vendor_from_soc(SOC soc) {
|
||||
else if(soc >= SOC_GOOGLE_TENSOR && soc <= SOC_GOOGLE_TENSOR_G3) return SOC_VENDOR_GOOGLE;
|
||||
else if(soc >= SOC_TEGRA_X1 && soc <= SOC_TEGRA_X1) return SOC_VENDOR_NVIDIA;
|
||||
else if(soc >= SOC_AMPERE_ALTRA && soc <= SOC_AMPERE_ALTRA) return SOC_VENDOR_AMPERE;
|
||||
else if(soc >= SOC_NXP_IMX8MP && soc <= SOC_NXP_IMX8MP) return SOC_VENDOR_NXP;
|
||||
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;
|
||||
return SOC_VENDOR_UNKNOWN;
|
||||
}
|
||||
|
||||
|
||||
@@ -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[] = {
|
||||
@@ -61,15 +63,26 @@ 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,
|
||||
@@ -93,8 +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,
|
||||
};
|
||||
@@ -112,7 +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) {}
|
||||
@@ -184,13 +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, "Cortex‑A510", UARCH_CORTEX_A510, CPU_VENDOR_ARM)
|
||||
CHECK_UARCH(arch, cpu, 'A', 0xD47, NA, NA, "Cortex‑A710", 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)
|
||||
@@ -264,14 +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) {
|
||||
@@ -284,32 +305,26 @@ 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->SVE && cpu->feat->cntb > 0) {
|
||||
return cpu->feat->cntb * 8;
|
||||
}
|
||||
else if (cpu->feat->NEON) {
|
||||
if(is_ARMv8_or_newer(cpu)) {
|
||||
return 128;
|
||||
}
|
||||
else {
|
||||
return 64;
|
||||
}
|
||||
}
|
||||
else {
|
||||
return 32;
|
||||
}
|
||||
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;
|
||||
}
|
||||
else {
|
||||
return 64;
|
||||
}
|
||||
}
|
||||
else {
|
||||
return 32;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -317,13 +332,19 @@ 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]
|
||||
@@ -342,16 +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
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -225,8 +225,7 @@ 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%c",
|
||||
|
||||
@@ -423,6 +423,16 @@ $C1##### ######### $C2############## $C3############### \
|
||||
$C1##### ###### $C2###### ###### $C3#### \
|
||||
$C1##### ## $C2###### ###### $C3## "
|
||||
|
||||
#define ASCII_AMLOGIC \
|
||||
"$C1 .#####. ### ### \
|
||||
$C1 ######## ### \
|
||||
$C1 ####..### ########## ### ### ##### ### ### \
|
||||
$C1 .## #. ### ## ## ## ### ## ## ## ## ### ## \
|
||||
$C1 #### #.# ### ## ## ## ### ## ## ## ## ### ## \
|
||||
$C1#########.### ## ## ## ## ### ###### ## ### \
|
||||
$C1 ### \
|
||||
$C1 ### "
|
||||
|
||||
// --------------------- LONG LOGOS ------------------------- //
|
||||
#define ASCII_AMD_L \
|
||||
"$C1 \
|
||||
@@ -600,6 +610,7 @@ asciiL logo_sipeed = { ASCII_SIPEED, 41, 16, true, {C_BG_RED, C_BG_WH
|
||||
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} };
|
||||
|
||||
// Long variants | ----------------------------------------------------------------------------------------------------------------|
|
||||
asciiL logo_amd_l = { ASCII_AMD_L, 62, 19, true, {C_BG_WHITE, C_BG_GREEN}, {C_FG_WHITE, C_FG_GREEN} };
|
||||
|
||||
@@ -34,6 +34,12 @@ int64_t get_freq(struct frequency* freq) {
|
||||
return freq->max;
|
||||
}
|
||||
|
||||
#ifdef ARCH_X86
|
||||
int64_t get_freq_pp(struct frequency* freq) {
|
||||
return freq->max_pp;
|
||||
}
|
||||
#endif
|
||||
|
||||
#if defined(ARCH_X86) || defined(ARCH_PPC)
|
||||
char* get_str_cpu_name(struct cpuInfo* cpu, bool fcpuname) {
|
||||
#ifdef ARCH_X86
|
||||
|
||||
@@ -60,6 +60,11 @@ struct frequency {
|
||||
int32_t max;
|
||||
// Indicates if max frequency was measured
|
||||
bool measured;
|
||||
#ifdef ARCH_X86
|
||||
// Max frequency when running vectorized code.
|
||||
// Used only for peak performance computation.
|
||||
int32_t max_pp;
|
||||
#endif
|
||||
};
|
||||
|
||||
struct hypervisor {
|
||||
@@ -188,6 +193,8 @@ struct cpuInfo {
|
||||
#ifdef ARCH_X86
|
||||
// The index of the first core in the module
|
||||
uint32_t first_core_id;
|
||||
// The index of this module
|
||||
uint32_t module_id;
|
||||
#endif
|
||||
#endif
|
||||
};
|
||||
@@ -200,6 +207,9 @@ uint32_t get_nsockets(struct topology* topo);
|
||||
|
||||
VENDOR get_cpu_vendor(struct cpuInfo* cpu);
|
||||
int64_t get_freq(struct frequency* freq);
|
||||
#ifdef ARCH_X86
|
||||
int64_t get_freq_pp(struct frequency* freq);
|
||||
#endif
|
||||
|
||||
char* get_str_aes(struct cpuInfo* cpu);
|
||||
char* get_str_sha(struct cpuInfo* cpu);
|
||||
|
||||
@@ -66,7 +66,7 @@ struct pci_devices * get_pci_paths(void) {
|
||||
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(sizeof(char), strLen);
|
||||
pci->devices[i]->path = ecalloc(strLen, sizeof(char));
|
||||
strncpy(pci->devices[i]->path, dp->d_name, strLen);
|
||||
i++;
|
||||
}
|
||||
|
||||
@@ -393,6 +393,8 @@ void choose_ascii_art(struct ascii* art, struct color** cs, struct terminal* ter
|
||||
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_NVIDIA)
|
||||
art->art = choose_ascii_art_aux(&logo_nvidia_l, &logo_nvidia, term, lf);
|
||||
else {
|
||||
|
||||
@@ -16,13 +16,14 @@ 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 ",
|
||||
// RISC-V
|
||||
[SOC_VENDOR_SIFIVE] = "SiFive ",
|
||||
[SOC_VENDOR_STARFIVE] = "StarFive ",
|
||||
@@ -32,7 +33,7 @@ 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) {
|
||||
@@ -43,39 +44,37 @@ 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);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -27,6 +27,7 @@ enum {
|
||||
SOC_VENDOR_NVIDIA,
|
||||
SOC_VENDOR_AMPERE,
|
||||
SOC_VENDOR_NXP,
|
||||
SOC_VENDOR_AMLOGIC,
|
||||
// RISC-V
|
||||
SOC_VENDOR_SIFIVE,
|
||||
SOC_VENDOR_STARFIVE,
|
||||
@@ -36,10 +37,10 @@ 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;
|
||||
};
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -146,8 +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;
|
||||
|
||||
@@ -81,9 +81,13 @@ struct topology* get_topology_info(struct cache* cach) {
|
||||
if(!fill_package_ids_from_sys(package_ids, topo->total_cores)) {
|
||||
printWarn("fill_package_ids_from_sys failed, output may be incomplete/invalid");
|
||||
for(int i=0; i < topo->total_cores; i++) package_ids[i] = 0;
|
||||
// fill_package_ids_from_sys failed, use a
|
||||
// more sophisticated wat to find the number of sockets
|
||||
// fill_package_ids_from_sys failed, use udev to try
|
||||
// to find the number of sockets
|
||||
topo->sockets = get_num_sockets_package_cpus(topo);
|
||||
if (topo->sockets == UNKNOWN_DATA) {
|
||||
printWarn("get_num_sockets_package_cpus failed: assuming 1 socket");
|
||||
topo->sockets = 1;
|
||||
}
|
||||
}
|
||||
else {
|
||||
// fill_package_ids_from_sys succeeded, use the
|
||||
|
||||
@@ -25,6 +25,7 @@ enum {
|
||||
UARCH_PPC603,
|
||||
UARCH_PPC440,
|
||||
UARCH_PPC470,
|
||||
UARCH_ESPRESSO, // Not exactly an uarch, but the codename of Wii U
|
||||
UARCH_PPC970,
|
||||
UARCH_PPC970FX,
|
||||
UARCH_PPC970MP,
|
||||
@@ -75,6 +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), 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)
|
||||
@@ -234,6 +236,7 @@ struct uarch* get_uarch_from_pvr(uint32_t pvr) {
|
||||
CHECK_UARCH(arch, pvr, 0xffff0000, 0x7ff50000, UARCH_PPC470)
|
||||
CHECK_UARCH(arch, pvr, 0xffff0000, 0x00050000, UARCH_PPC470)
|
||||
CHECK_UARCH(arch, pvr, 0xffff0000, 0x11a50000, UARCH_PPC470)
|
||||
CHECK_UARCH(arch, pvr, 0xffffffff, 0x70010201, UARCH_ESPRESSO)
|
||||
UARCH_END
|
||||
|
||||
return arch;
|
||||
|
||||
@@ -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);
|
||||
|
||||
@@ -100,9 +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):
|
||||
|
||||
@@ -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));
|
||||
|
||||
@@ -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;
|
||||
}
|
||||
|
||||
@@ -234,15 +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;
|
||||
|
||||
@@ -91,8 +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;
|
||||
@@ -211,18 +210,14 @@ int64_t get_peak_performance(struct cpuInfo* cpu, bool accurate_pp) {
|
||||
|
||||
for(int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
|
||||
struct topology* topo = ptr->topo;
|
||||
int64_t max_freq = get_freq(ptr->freq);
|
||||
int64_t freq = get_freq(ptr->freq);
|
||||
|
||||
int64_t freq;
|
||||
#ifdef __linux__
|
||||
if(accurate_pp)
|
||||
freq = measure_frequency(ptr);
|
||||
else
|
||||
freq = max_freq;
|
||||
freq = get_freq_pp(ptr->freq);
|
||||
#else
|
||||
// Silence compiler warning
|
||||
(void)(accurate_pp);
|
||||
freq = max_freq;
|
||||
#endif
|
||||
|
||||
//First, check we have consistent data
|
||||
@@ -281,7 +276,7 @@ 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;
|
||||
@@ -451,6 +446,23 @@ int32_t get_core_type(void) {
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef __linux__
|
||||
// Gets the max frequency for estimating the peak performance
|
||||
// and fills in the passed cpuInfo parameter.
|
||||
void fill_frequency_info_pp(struct cpuInfo* cpu) {
|
||||
int32_t unused;
|
||||
int32_t *max_freq_pp_vec = malloc(sizeof(int32_t) * cpu->num_cpus);
|
||||
struct cpuInfo* ptr = cpu;
|
||||
|
||||
for (uint32_t i=0; i < cpu->num_cpus; i++) {
|
||||
set_cpu_module(i, cpu->num_cpus, &unused);
|
||||
|
||||
ptr->freq->max_pp = measure_frequency(ptr, max_freq_pp_vec);
|
||||
ptr = ptr->next_cpu;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
|
||||
struct cpuInfo* get_cpu_info(void) {
|
||||
struct cpuInfo* cpu = emalloc(sizeof(struct cpuInfo));
|
||||
cpu->peak_performance = -1;
|
||||
@@ -471,7 +483,7 @@ 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)
|
||||
@@ -547,6 +559,7 @@ struct cpuInfo* get_cpu_info(void) {
|
||||
ptr->core_type = get_core_type();
|
||||
}
|
||||
ptr->first_core_id = first_core;
|
||||
ptr->module_id = i;
|
||||
ptr->feat = get_features_info(ptr);
|
||||
|
||||
ptr->arch = get_cpu_uarch(ptr);
|
||||
@@ -571,6 +584,13 @@ struct cpuInfo* get_cpu_info(void) {
|
||||
if(ptr->topo == NULL) return cpu;
|
||||
}
|
||||
|
||||
#ifdef __linux__
|
||||
// If accurate_pp is requested, we need to get the max frequency
|
||||
// after fetching the topology for all CPU modules, since the topology
|
||||
// is required by fill_frequency_info_pp
|
||||
if (accurate_pp()) fill_frequency_info_pp(cpu);
|
||||
#endif
|
||||
|
||||
cpu->peak_performance = get_peak_performance(cpu, accurate_pp());
|
||||
|
||||
return cpu;
|
||||
@@ -1006,6 +1026,7 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
|
||||
}
|
||||
#endif
|
||||
|
||||
freq->max_pp = UNKNOWN_DATA;
|
||||
return freq;
|
||||
}
|
||||
|
||||
|
||||
@@ -21,9 +21,12 @@
|
||||
#define FREQ_VECTOR_SIZE 1<<16
|
||||
|
||||
struct freq_thread {
|
||||
// Inputs
|
||||
struct cpuInfo* cpu;
|
||||
bool end;
|
||||
bool measure;
|
||||
double freq;
|
||||
// Output
|
||||
int32_t *max_pp;
|
||||
};
|
||||
|
||||
double vector_average_harmonic(double* v, int len) {
|
||||
@@ -48,6 +51,7 @@ void* measure_freq(void *freq_ptr) {
|
||||
char* line = NULL;
|
||||
size_t len = 0;
|
||||
ssize_t read;
|
||||
struct cpuInfo* cpu = freq->cpu;
|
||||
|
||||
int v = 0;
|
||||
double* freq_vector = malloc(sizeof(double) * FREQ_VECTOR_SIZE);
|
||||
@@ -76,18 +80,43 @@ void* measure_freq(void *freq_ptr) {
|
||||
sleep_ms(500);
|
||||
}
|
||||
|
||||
freq->freq = vector_average_harmonic(freq_vector, v);
|
||||
printWarn("AVX2 measured freq=%f\n", freq->freq);
|
||||
if (cpu->hybrid_flag) {
|
||||
// We have an heterogeneous architecture. After measuring the
|
||||
// frequency for all cores, we now need to compute the average
|
||||
// independently for each CPU module.
|
||||
struct cpuInfo* ptr = cpu;
|
||||
double* freq_vector_ptr = freq_vector;
|
||||
|
||||
for (int i=0; i < cpu->num_cpus; ptr = ptr->next_cpu, i++) {
|
||||
freq->max_pp[i] = vector_average_harmonic(freq_vector_ptr, ptr->topo->total_cores_module);
|
||||
printWarn("AVX2 measured freq=%d (module %d)", freq->max_pp[i], i);
|
||||
|
||||
freq_vector_ptr = freq_vector_ptr + ptr->topo->total_cores_module;
|
||||
}
|
||||
}
|
||||
else {
|
||||
freq->max_pp[0] = vector_average_harmonic(freq_vector, v);
|
||||
printWarn("AVX2 measured freq=%d\n", freq->max_pp[0]);
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
int64_t measure_frequency(struct cpuInfo* cpu) {
|
||||
int32_t measure_frequency(struct cpuInfo* cpu, int32_t *max_freq_pp_vec) {
|
||||
if (cpu->hybrid_flag && cpu->module_id > 0) {
|
||||
// We have a hybrid architecture and we have already
|
||||
// measured the frequency for this module in a previous
|
||||
// call to this function, so now just return it.
|
||||
return max_freq_pp_vec[cpu->module_id];
|
||||
}
|
||||
|
||||
int ret;
|
||||
int num_spaces;
|
||||
struct freq_thread* freq_struct = malloc(sizeof(struct freq_thread));
|
||||
freq_struct->end = false;
|
||||
freq_struct->measure = false;
|
||||
freq_struct->cpu = cpu;
|
||||
freq_struct->max_pp = max_freq_pp_vec;
|
||||
|
||||
void* (*compute_function)(void*);
|
||||
|
||||
@@ -116,8 +145,25 @@ 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");
|
||||
@@ -142,5 +188,5 @@ int64_t measure_frequency(struct cpuInfo* cpu) {
|
||||
}
|
||||
|
||||
printf("\r%*c", num_spaces, ' ');
|
||||
return freq_struct->freq;
|
||||
return max_freq_pp_vec[0];
|
||||
}
|
||||
|
||||
@@ -8,6 +8,6 @@
|
||||
#define MEASURE_TIME_SECONDS 5
|
||||
#define LOOP_ITERS 100000000
|
||||
|
||||
int64_t measure_frequency(struct cpuInfo* cpu);
|
||||
int32_t measure_frequency(struct cpuInfo* cpu, int32_t *max_freq_pp_vec);
|
||||
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user