以下代码对于检查CPU是否支持SSE3指令集有效吗?
使用IsProcessorFeaturePresent()
函数显然在Windows XP上不起作用。
bool CheckSSE3()
{
int CPUInfo[4] = {-1};
//-- Get number of valid info ids
__cpuid(CPUInfo, 0);
int nIds = CPUInfo[0];
//-- Get info for id "1"
if (nIds >= 1)
{
__cpuid(CPUInfo, 1);
bool bSSE3NewInstructions = (CPUInfo[2] & 0x1) || false;
return bSSE3NewInstructions;
}
return false;
}
我创建了一个GitHub repro,它将检测CPU和操作系统对所有主要x86 ISA扩展的支持:https://github.com/Mysticial/FeatureDetector
这是一个较短的版本:
首先,您需要访问CPUID指令:
#ifdef _WIN32
// Windows
#define cpuid(info, x) __cpuidex(info, x, 0)
#else
// GCC Intrinsics
#include <cpuid.h>
void cpuid(int info[4], int InfoType){
__cpuid_count(InfoType, 0, info[0], info[1], info[2], info[3]);
}
#endif
然后你可以运行以下代码:
// Misc.
bool HW_MMX;
bool HW_x64;
bool HW_ABM; // Advanced Bit Manipulation
bool HW_RDRAND;
bool HW_BMI1;
bool HW_BMI2;
bool HW_ADX;
bool HW_PREFETCHWT1;
// SIMD: 128-bit
bool HW_SSE;
bool HW_SSE2;
bool HW_SSE3;
bool HW_SSSE3;
bool HW_SSE41;
bool HW_SSE42;
bool HW_SSE4a;
bool HW_AES;
bool HW_SHA;
// SIMD: 256-bit
bool HW_AVX;
bool HW_XOP;
bool HW_FMA3;
bool HW_FMA4;
bool HW_AVX2;
// SIMD: 512-bit
bool HW_AVX512F; // AVX512 Foundation
bool HW_AVX512CD; // AVX512 Conflict Detection
bool HW_AVX512PF; // AVX512 Prefetch
bool HW_AVX512ER; // AVX512 Exponential + Reciprocal
bool HW_AVX512VL; // AVX512 Vector Length Extensions
bool HW_AVX512BW; // AVX512 Byte + Word
bool HW_AVX512DQ; // AVX512 Doubleword + Quadword
bool HW_AVX512IFMA; // AVX512 Integer 52-bit Fused Multiply-Add
bool HW_AVX512VBMI; // AVX512 Vector Byte Manipulation Instructions
int info[4];
cpuid(info, 0);
int nIds = info[0];
cpuid(info, 0x80000000);
unsigned nExIds = info[0];
// Detect Features
if (nIds >= 0x00000001){
cpuid(info,0x00000001);
HW_MMX = (info[3] & ((int)1 << 23)) != 0;
HW_SSE = (info[3] & ((int)1 << 25)) != 0;
HW_SSE2 = (info[3] & ((int)1 << 26)) != 0;
HW_SSE3 = (info[2] & ((int)1 << 0)) != 0;
HW_SSSE3 = (info[2] & ((int)1 << 9)) != 0;
HW_SSE41 = (info[2] & ((int)1 << 19)) != 0;
HW_SSE42 = (info[2] & ((int)1 << 20)) != 0;
HW_AES = (info[2] & ((int)1 << 25)) != 0;
HW_AVX = (info[2] & ((int)1 << 28)) != 0;
HW_FMA3 = (info[2] & ((int)1 << 12)) != 0;
HW_RDRAND = (info[2] & ((int)1 << 30)) != 0;
}
if (nIds >= 0x00000007){
cpuid(info,0x00000007);
HW_AVX2 = (info[1] & ((int)1 << 5)) != 0;
HW_BMI1 = (info[1] & ((int)1 << 3)) != 0;
HW_BMI2 = (info[1] & ((int)1 << 8)) != 0;
HW_ADX = (info[1] & ((int)1 << 19)) != 0;
HW_SHA = (info[1] & ((int)1 << 29)) != 0;
HW_PREFETCHWT1 = (info[2] & ((int)1 << 0)) != 0;
HW_AVX512F = (info[1] & ((int)1 << 16)) != 0;
HW_AVX512CD = (info[1] & ((int)1 << 28)) != 0;
HW_AVX512PF = (info[1] & ((int)1 << 26)) != 0;
HW_AVX512ER = (info[1] & ((int)1 << 27)) != 0;
HW_AVX512VL = (info[1] & ((int)1 << 31)) != 0;
HW_AVX512BW = (info[1] & ((int)1 << 30)) != 0;
HW_AVX512DQ = (info[1] & ((int)1 << 17)) != 0;
HW_AVX512IFMA = (info[1] & ((int)1 << 21)) != 0;
HW_AVX512VBMI = (info[2] & ((int)1 << 1)) != 0;
}
if (nExIds >= 0x80000001){
cpuid(info,0x80000001);
HW_x64 = (info[3] & ((int)1 << 29)) != 0;
HW_ABM = (info[2] & ((int)1 << 5)) != 0;
HW_SSE4a = (info[2] & ((int)1 << 6)) != 0;
HW_FMA4 = (info[2] & ((int)1 << 16)) != 0;
HW_XOP = (info[2] & ((int)1 << 11)) != 0;
}
请注意,这仅检测CPU是否支持指令。要真正运行它们,还需要有操作系统支持。
具体而言,需要操作系统支持:
- x64指令。(您需要一个64位操作系统。)
- 使用(AVX)256位
ymm
寄存器的指令。请参阅Andy Lutomirski的答案,了解如何检测到这一点 - 使用(AVX512)512位
zmm
和掩码寄存器的指令。检测操作系统对AVX512的支持与AVX相同,但使用标志0xe6
而不是0x6
bool avxSupported = false;
int cpuInfo[4];
__cpuid(cpuInfo, 1);
bool osUsesXSAVE_XRSTORE = cpuInfo[2] & (1 << 27) || false;
bool cpuAVXSuport = cpuInfo[2] & (1 << 28) || false;
if (osUsesXSAVE_XRSTORE && cpuAVXSuport)
{
unsigned long long xcrFeatureMask = _xgetbv(_XCR_XFEATURE_ENABLED_MASK);
avxSupported = (xcrFeatureMask & 0x6) == 0x6;
}
经过大量的谷歌搜索,我还找到了英特尔的解决方案:
链接:https://software.intel.com/en-us/articles/how-to-detect-new-instruction-support-in-the-4th-generation-intel-core-processor-family
void cpuid(uint32_t eax, uint32_t ecx, uint32_t* abcd) {
#if defined(_MSC_VER)
__cpuidex((int*)abcd, eax, ecx);
#else
uint32_t ebx, edx;
# if defined( __i386__ ) && defined ( __PIC__ )
/* in case of PIC under 32-bit EBX cannot be clobbered */
__asm__("movl %%ebx, %%edi nt cpuid nt xchgl %%ebx, %%edi" : "=D" (ebx),
# else
__asm__("cpuid" : "+b" (ebx),
# endif
"+a" (eax), "+c" (ecx), "=d" (edx));
abcd[0] = eax; abcd[1] = ebx; abcd[2] = ecx; abcd[3] = edx;
#endif
}
int check_xcr0_ymm()
{
uint32_t xcr0;
#if defined(_MSC_VER)
xcr0 = (uint32_t)_xgetbv(0); /* min VS2010 SP1 compiler is required */
#else
__asm__("xgetbv" : "=a" (xcr0) : "c" (0) : "%edx");
#endif
return ((xcr0 & 6) == 6); /* checking if xmm and ymm state are enabled in XCR0 */
}
还要注意,GCC有一些特殊的内部函数,您可以使用(请参阅:https://gcc.gnu.org/onlinedocs/gcc-4.9.2/gcc/X86-Built-in-Functions.html):
if (__builtin_cpu_supports("avx2"))
// ...
如果你把这些和上面的信息放在一起,一切都会好起来的。
要添加到Abhiroop的答案中:在linux上,您可以运行这个shell命令来查找CPU 支持的功能
cat /proc/cpuinfo | grep flags | uniq
在我的机器上,这会打印
标志:fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nontop_tsc aperfperf eagerpu pni pclmulqq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetc invpcid_single retpoline kaiserfsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx xsaveopt
在Mac操作系统上,这是有效的:
sysctl -a | grep machdep.cpu.features
在我的机器中,它输出的是:
machdep.cpu.功能:FPU VME DE PSE TSC MSR PAE MCE CX8 APIC SEP MTRR PGE MCA CMOV PAT PSE36 CLFSH DS ACPI MMX FXSRSSE SSE2SS HTT TM PBESSE3PCLMULQDQ DTES64 MON DSCPL VMX EST TM2 SSSE3 FMA CX16 TPR PDCMSSE 4.1SSE4.2x2APIC MOVBE POPCNT AES PCID XSAVE OSXSAVE SEGLIM64 TSCTMRAVX1.0RDRAND F16C
正如您所看到的,用粗体写的指令支持SSE3和其他一堆SIMD指令。
在linux或wsl2上,util linux存储库中的lscpu
命令将完成此任务。
例如:
lscpu | grep sse3
或者;POSIX方式":
cat /proc/cpuinfo |grep -i sse3 >/dev/null 2>&1 && echo "ESS3=TRUE" || echo "ESS3=FALSE"
结果:
ESS3=TRUE