ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-20 12:59:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

layernorm & groupnorm bwd gamma beta (#1133)

Browse Source 
* Add layernorm bwd gamma beta external api

* Add groupnorm external api

* Add layernorm bwd gamma beta profiler

* Add groupnorm bwd gamma beta ckProfiler

* Add layernorm & groupnorm bwd gamma beta test

* Fix groupnorm bwd gamma beta profiler bug

* Layernorm bwd weight client example

* Groupnorm bwd weight client example

* clang format

* Remove useless header

* Let inv_std be positive

* Rename to num_bytes and move this calculation outside the loop

[ROCm/composable_kernel commit: 28f68a5a99]
This commit is contained in:
rocking
2024-01-25 19:53:15 +08:00
committed by GitHub
parent b5a3426d89
commit 133d8e762f
17 changed files with 1362 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
library/src/tensor_operation_instance/gpu/normalization_bwd_gamma_beta/device_layernorm2d_bwd_gamma_beta_f16_instance.cpp
View File

@@ -8,7 +8,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_layernorm2d_bwd_gamma_beta_rank_2_1_f16_instances(
void add_device_layernorm2d_bwd_gamma_beta_f16_instances(
std::vector<std::unique_ptr<DeviceNormalizationBwdGammaBeta<F16, F16, F16, F16, F16, 2, 1>>>&
instances)
{

2
library/src/tensor_operation_instance/gpu/normalization_bwd_gamma_beta/device_layernorm2d_bwd_gamma_beta_f32_instance.cpp
View File

@@ -8,7 +8,7 @@ namespace tensor_operation {
namespace device {
namespace instance {
void add_device_layernorm2d_bwd_gamma_beta_rank_2_1_f32_instances(
void add_device_layernorm2d_bwd_gamma_beta_f32_instances(
std::vector<std::unique_ptr<DeviceNormalizationBwdGammaBeta<F32, F32, F32, F32, F32, 2, 1>>>&
instances)
{