Merge branch 'gfx950' into lwpck-2390

630042d8 · Rostyslav Geyyer · GitHub · 5f1a24a8 · 261d76c4 · 630042d8
Unverified Commit 630042d8 authored Nov 07, 2024 by Rostyslav Geyyer Committed by GitHub Nov 07, 2024
20 changed files
--- a/example/ck_tile/12_smoothquant/script/smoke_test.sh
+++ b/example/ck_tile/12_smoothquant/script/smoke_test.sh
--- a/example/ck_tile/12_smoothquant/smoothquant.cpp
+++ b/example/ck_tile/12_smoothquant/smoothquant.cpp
--- a/example/ck_tile/12_smoothquant/smoothquant.hpp
+++ b/example/ck_tile/12_smoothquant/smoothquant.hpp
--- a/example/ck_tile/CMakeLists.txt
+++ b/example/ck_tile/CMakeLists.txt
--- a/include/ck/host_utility/flush_cache.hpp
+++ b/include/ck/host_utility/flush_cache.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/device/device_cgemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_cgemm.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_cgemm_4gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.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
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
--- a/include/ck/utility/amd_buffer_addressing.hpp
+++ b/include/ck/utility/amd_buffer_addressing.hpp
--- a/include/ck/utility/amd_xdlops.hpp
+++ b/include/ck/utility/amd_xdlops.hpp
--- a/include/ck/utility/data_type.hpp
+++ b/include/ck/utility/data_type.hpp
--- a/include/ck/utility/math_v2.hpp
+++ b/include/ck/utility/math_v2.hpp