pytorch  1.8.2
About: PyTorch provides Tensor computation (like NumPy) with strong GPU acceleration and Deep Neural Networks (in Python) built on a tape-based autograd system. LTS (Long Term Support) release.
  Fossies Dox: pytorch-1.8.2.tar.gz  ("unofficial" and yet experimental doxygen-generated source code documentation)  

4x4c2-sse2.c File Reference
#include <immintrin.h>
#include <qnnpack/q8gemm.h>
#include <requantization/runtime-sse2.h>
Include dependency graph for 4x4c2-sse2.c:

Go to the source code of this file.


void pytorch_q8gemm_ukernel_4x4c2__sse2 (size_t mr, size_t nr, size_t k, const uint8_t *restrict a, size_t a_stride, const void *restrict w, uint8_t *restrict c, size_t c_stride, size_t output_channel_index, const union pytorch_qnnp_conv_quantization_params quantization_params[RESTRICT_STATIC 1])

Function Documentation

◆ pytorch_q8gemm_ukernel_4x4c2__sse2()

void pytorch_q8gemm_ukernel_4x4c2__sse2 ( size_t  mr,
size_t  nr,
size_t  k,
const uint8_t *restrict  a,
size_t  a_stride,
const void *restrict  w,
uint8_t *restrict  c,
size_t  c_stride,
size_t  output_channel_index,
const union pytorch_qnnp_conv_quantization_params  quantization_params[RESTRICT_STATIC 1] 

Definition at line 14 of file 4x4c2-sse2.c.

References, c, sub_zero_point(), and at::native::metal::mpscnn::w.

Referenced by init().