Add bfloat16 based dot and conversion with single/double
1. Added bfloat16 based dot as new API: shdot
2. Implemented generic kernel and cooperlake-specific (AVX512-BF16) kernel for shdot
3. Added 4 conversion APIs for bfloat16 data type <=> single/double: shstobf16 shdtobf16 sbf16tos dbf16tod
shstobf16 -- convert single float array to bfloat16 array
shdtobf16 -- convert double float array to bfloat16 array
sbf16tos -- convert bfloat16 array to single float array
dbf16tod -- convert bfloat16 array to double float array
4. Implemented generic kernels for all 4 conversion APIs, and cooperlake-specific kernel for shstobf16 and shdtobf16
5. Update level1 thread facilitate functions and macros to support multi-threading for these new APIs
6. Fix Cooperlake platform detection/specify issue when under dynamic-arch building
7. Change the typedef of bfloat16 from unsigned short to more strict uint16_t
Signed-off-by: Chen, Guobing <guobing.chen@intel.com>
This commit is contained in:
@@ -142,6 +142,29 @@ static __inline void cpuid(int op, int *eax, int *ebx, int *ecx, int *edx){
|
||||
#endif
|
||||
}
|
||||
|
||||
static __inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx, int *edx)
|
||||
{
|
||||
#ifdef C_MSVC
|
||||
int cpuInfo[4] = {-1};
|
||||
__cpuidex(cpuInfo, op, count);
|
||||
*eax = cpuInfo[0];
|
||||
*ebx = cpuInfo[1];
|
||||
*ecx = cpuInfo[2];
|
||||
*edx = cpuInfo[3];
|
||||
#else
|
||||
#if defined(__i386__) && defined(__PIC__)
|
||||
__asm__ __volatile__
|
||||
("mov %%ebx, %%edi;"
|
||||
"cpuid;"
|
||||
"xchgl %%ebx, %%edi;"
|
||||
: "=a" (*eax), "=D" (*ebx), "=c" (*ecx), "=d" (*edx) : "0" (op), "2" (count) : "cc");
|
||||
#else
|
||||
__asm__ __volatile__
|
||||
("cpuid": "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) : "0" (op), "2" (count) : "cc");
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
|
||||
/*
|
||||
#define WHEREAMI
|
||||
*/
|
||||
|
||||
Reference in New Issue
Block a user