Merge remote-tracking branch 'origin' into aosewski/ggemm_multi_d2

ae20247a · Adam Osewski · d1f7a3cf · a776978c · ae20247a · ae20247a
Commit ae20247a authored Feb 29, 2024 by Adam Osewski
20 changed files
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_streamk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_i8_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_i8_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_bilinear_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_xdl_bilinear_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_bilinear_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_bilinear_instance.hpp
--- 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_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/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_default_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_default_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_interwave_default_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_interwave_default_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_interwave_padded_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_interwave_padded_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_padded_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_padded_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_default_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_default_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_padded_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_padded_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_add/CMakeLists.txt