Merge branch 'gridwise_2d' of github.com:ROCmSoftwarePlatform/composable_kernel into gridwise_2d

dab61372 · Astha Rai · b4abe4e2 · dc70e3e1 · dab61372 · b4abe4e2
Commit dab61372 authored Nov 03, 2022 by Astha Rai
20 changed files
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/device_batched_gemm_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gon_gmo_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/CMakeLists.txt
-add_instance_library(device_batched_gemm_masking_scale_softmax_gemm_permute_instance
-    device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
-)
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_masking_scale_softmax_gemm_permute/device_batched_gemm_masking_scale_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/device_batched_gemm_softmax_gemm_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle_f16_f16_f16_f16_gmk_gnk_gno_gmo_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/device_grouped_conv2d_fwd_dl_gnhwc_gkyxc_gnhwk_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
--- a/profiler/include/profile_batched_gemm_softmax_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_softmax_gemm_impl.hpp
--- a/profiler/include/profile_batched_gemm_masking_scale_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profile_batched_gemm_masking_scale_softmax_gemm_permute_impl.hpp
--- a/profiler/include/profile_grouped_conv_fwd_impl.hpp
+++ b/profiler/include/profile_grouped_conv_fwd_impl.hpp
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
--- a/test/batched_gemm/CMakeLists.txt
+++ b/test/batched_gemm/CMakeLists.txt
--- a/test/batched_gemm/batched_gemm_bf16.cpp
+++ b/test/batched_gemm/batched_gemm_bf16.cpp
--- a/test/batched_gemm/batched_gemm_fp32.cpp
+++ b/test/batched_gemm/batched_gemm_fp32.cpp
--- a/test/batched_gemm/batched_gemm_int8.cpp
+++ b/test/batched_gemm/batched_gemm_int8.cpp
--- a/test/batched_gemm_masking_scale_softmax_gemm_permute/CMakeLists.txt
+++ b/test/batched_gemm_masking_scale_softmax_gemm_permute/CMakeLists.txt