Merge branch 'develop' into codegen-enable-hiprtc

2a30cfdd · arai713 · GitHub · 9533a172 · 78195ccc · 2a30cfdd
Unverified Commit 2a30cfdd authored Feb 12, 2025 by arai713 Committed by GitHub Feb 12, 2025
20 changed files
--- a/include/ck/config.h.in
+++ b/include/ck/config.h.in
--- a/include/ck/host_utility/device_prop.hpp
+++ b/include/ck/host_utility/device_prop.hpp
--- a/include/ck/library/utility/check_err.hpp
+++ b/include/ck/library/utility/check_err.hpp
--- 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/block/thread_group_tensor_slice_transfer_v7r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/device_base.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_base.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.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/device_grouped_conv_fwd_multiple_abd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
--- a/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp