Merge branch 'gfx950' into lwpck-2619

efab74a3 · Rostyslav Geyyer · 86950b3a · bcef33c1 · efab74a3 · efab74a3
Commit efab74a3 authored Jan 24, 2025 by Rostyslav Geyyer
20 changed files
--- a/example/ck_tile/16_batched_gemm/batched_gemm.cpp
+++ b/example/ck_tile/16_batched_gemm/batched_gemm.cpp
--- a/example/ck_tile/16_batched_gemm/batched_gemm.hpp
+++ b/example/ck_tile/16_batched_gemm/batched_gemm.hpp
--- a/example/ck_tile/16_batched_gemm/run_batched_gemm_example.inc
+++ b/example/ck_tile/16_batched_gemm/run_batched_gemm_example.inc
--- a/example/ck_tile/17_grouped_gemm/grouped_gemm.hpp
+++ b/example/ck_tile/17_grouped_gemm/grouped_gemm.hpp
--- a/example/ck_tile/17_grouped_gemm/run_grouped_gemm_example.inc
+++ b/example/ck_tile/17_grouped_gemm/run_grouped_gemm_example.inc
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/config.h.in
+++ b/include/ck/config.h.in
--- a/include/ck/library/utility/host_tensor.hpp
+++ b/include/ck/library/utility/host_tensor.hpp
--- a/include/ck/library/utility/host_tensor_generator.hpp
+++ b/include/ck/library/utility/host_tensor_generator.hpp
--- a/include/ck/tensor/static_tensor.hpp
+++ b/include/ck/tensor/static_tensor.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_b_scale_selector.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_b_scale_selector.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v1_b_scale.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v1_b_scale.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v2_b_scale.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v2_b_scale.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v3_b_scale.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v3_b_scale.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v4_b_scale.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops_v4_b_scale.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_v2.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_v2.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_streamk_v3.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_streamk_v3.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_b_scale.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_b_scale.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_two_stage_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_two_stage_xdl_cshuffle.hpp