p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!7230 [MSLITE][Develop] optimize arm cpu arithmetic: remove redundant code 

Merge pull request !7230 from yangruoqi713/lite
This commit is contained in:
mindspore-ci-bot 2020-10-14 10:18:31 +08:00 committed by Gitee
parent 2801429db0 43d0020564
commit b80fa15918
3 changed files with 1054 additions and 2109 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1822
mindspore/lite/nnacl/fp16/arithmetic_fp16.c
View File

File diff suppressed because it is too large Load Diff

1337
mindspore/lite/nnacl/fp32/arithmetic.c
View File

File diff suppressed because it is too large Load Diff

4
mindspore/lite/nnacl/fp32/lstm.c
View File

@ -42,7 +42,7 @@ void MatMulAcc(float *output, const float *input, const float *weight, int rows,
int index = 0;
#ifdef ENABLE_ARM
float32x4_t out = vdupq_n_f32(0.0f);
for (; index < inner_size - 4; index += 4) {
for (; index <= inner_size - 4; index += 4) {
float32x4_t in_0 = vld1q_f32(input_col + index);
float32x4_t in_1 = vld1q_f32(weight_col + index);
out = vmlaq_f32(out, in_1, in_0);
@ -66,7 +66,7 @@ void MatMulAcc(float *output, const float *input, const float *weight, int rows,
void ElementMulAcc(const float *input0, const float *input1, float *output, int element_size) {
int index = 0;
#ifdef ENABLE_ARM
for (; index < element_size - 4; index += 4) {
for (; index <= element_size - 4; index += 4) {
float32x4_t in_0 = vld1q_f32(input0 + index);
float32x4_t in_1 = vld1q_f32(input1 + index);
float32x4_t out = vld1q_f32(output + index);