Merge branch 'develop' into ck_tile/fa_asm_bwd

2a4c2316 · danyao12 · 1e01ee09 · 770d2b77 · 2a4c2316 · 2a4c2316
Commit 2a4c2316 authored Sep 23, 2024 by danyao12
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_inter_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_inter_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_intra_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f16_mem_intra_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_inter_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_inter_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_intra_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_f32_mem_intra_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/max_pool_bwd/max_pool_bwd_instance_common.hpp
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_f8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_i8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_avg_pool2d_fwd_nhwc_i8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_max_pool2d_fwd_nhwc_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool2d_fwd/device_max_pool2d_fwd_nhwc_bf16_instance.cpp