mindspore-Ecosystem
/
mindspore
21
0
Fork 27
Code Issues Pull Requests 6 Projects Releases Wiki Activity

optimize common convolution kernel

This commit is contained in:
sunsuodong 2021-07-06 16:41:38 +08:00
parent 70d1344249
commit 49216e86b0
2 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp16/conv_fp16.c
View File

@ -42,7 +42,6 @@ void ConvFp16(float16_t *input_data, float16_t *packed_input, float16_t *packed_
float16_t *col_major_gemm_input = col_major_input + task_id * deep * tile_n;
size_t packed_input_size = deep * tile_n * sizeof(float16_t);
memset(gemm_input, 0, packed_input_size);
memset(col_major_gemm_input, 0, packed_input_size);
Im2ColPackUnitFp16(input_data + in_batch_offset, conv_param, gemm_input, real_cal_num, start_index);
int out_offset = thread_id * tile_n * out_channel + out_batch_offset;

1
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp32/conv_common_fp32.c
View File

@ -75,7 +75,6 @@ void ConvFp32(const float *input_data, float *packed_input, const float *packed_
float *col_major_gemm_input = col_major_input + task_id * deep * cal_num;
size_t packed_input_size = deep * cal_num * sizeof(float);
memset(gemm_input, 0, packed_input_size);
memset(col_major_gemm_input, 0, packed_input_size);
Im2ColPackUnitFp32(input_data + in_batch_offset, conv_param, gemm_input, real_cal_num, start_index);
int out_offset = thread_id * cal_num * out_channel + out_batch_offset;