Merge pull request #295 from ROCm/gfx950

Merge gfx950 changes into develop branch.

Merge pull request #295 from ROCm/gfx950
Merge gfx950 changes into develop branch.
fd7600ce · Illia Silin · GitHub · 5063a39f · 2ad07a88 · fd7600ce
Unverified Commit fd7600ce authored Feb 03, 2025 by Illia Silin Committed by GitHub Feb 03, 2025
17 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn.hpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_irregular_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_splitk_f16_f8_f16_mk_kn_mn_irregular_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_tile_loop/device_grouped_gemm_xdl_tile_loop_multiply_bf16_i8_bf16_mk_kn_mn.hpp
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
--- a/test/data_type/CMakeLists.txt
+++ b/test/data_type/CMakeLists.txt
--- a/test/data_type/test_bf6.cpp
+++ b/test/data_type/test_bf6.cpp
--- a/test/data_type/test_e8m0.cpp
+++ b/test/data_type/test_e8m0.cpp
--- a/test/data_type/test_fp4.cpp
+++ b/test/data_type/test_fp4.cpp
--- a/test/data_type/test_fp6.cpp
+++ b/test/data_type/test_fp6.cpp
--- a/test/data_type/test_fp8_ocp.cpp
+++ b/test/data_type/test_fp8_ocp.cpp
--- a/test/data_type/test_mx_bf8.cpp
+++ b/test/data_type/test_mx_bf8.cpp
--- a/test/data_type/test_mx_fp8.cpp
+++ b/test/data_type/test_mx_fp8.cpp
--- a/test/mx_mfma_op/CMakeLists.txt
+++ b/test/mx_mfma_op/CMakeLists.txt
--- a/test/mx_mfma_op/mx_mfma_op.cpp
+++ b/test/mx_mfma_op/mx_mfma_op.cpp
--- a/test/mx_mfma_op/mx_mfma_op.hpp
+++ b/test/mx_mfma_op/mx_mfma_op.hpp
--- a/test/smfmac_op/smfmac_op_xdl.cpp
+++ b/test/smfmac_op/smfmac_op_xdl.cpp