fixed block_sync_lds

ae3d6cb6 · Jing Zhang · 760b0c75 · b62926dc · ae3d6cb6 · ae3d6cb6
Commit ae3d6cb6 authored Feb 27, 2024 by Jing Zhang
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data_bilinear.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_data_bilinear.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_bilinear.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_bilinear.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_fixed_nk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/permute_scale.hpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_wmma_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_kn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_km_nk_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_kn_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_bilinear/device_gemm_bilinear_wmma_c_shuffle_i8_i8_i8_i8_mk_nk_mn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_kpb128_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_kpb128_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_bwd_data/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt