mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 12:21:27 +01:00
9e14d86573
`kernel_micro_gemm` generated using BRGEMM:
```
template <bool accum>
inline void kernel_micro_gemm(
const half* __restrict__ A,
const half* __restrict__ B,
float* __restrict__ C,
int64_t M,
int64_t N,
int64_t K,
int64_t lda,
int64_t ldb,
int64_t ldc
) {
at::native::cpublas::brgemm(
M, N, K,
lda, ldb, ldc,
1.f, accum ? 1.f : 0.f,
A,
B,
C);
}
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/136255
Approved by: https://github.com/jgong5, https://github.com/jansel
15 lines
476 B
Python
15 lines
476 B
Python
from torch.types import _bool, _int
|
|
|
|
# Defined in torch/csrc/cpu/Module.cpp
|
|
|
|
def _is_avx2_supported() -> _bool: ...
|
|
def _is_avx512_supported() -> _bool: ...
|
|
def _is_avx512_vnni_supported() -> _bool: ...
|
|
def _is_avx512_bf16_supported() -> _bool: ...
|
|
def _is_amx_tile_supported() -> _bool: ...
|
|
def _is_amx_fp16_supported() -> _bool: ...
|
|
def _init_amx() -> _bool: ...
|
|
def _is_arm_sve_supported() -> _bool: ...
|
|
def _L1d_cache_size() -> _int: ...
|
|
def _L2_cache_size() -> _int: ...
|