Merge branch 'develop' into normalization/splitK

97e851e5 · rocking5566 · GitHub · 9c42a83a · fc26d42a · 97e851e5
Unverified Commit 97e851e5 authored Apr 17, 2023 by rocking5566 Committed by GitHub Apr 17, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/element/quantization_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/quantization_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_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.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_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
--- a/include/ck/utility/amd_buffer_addressing.hpp
+++ b/include/ck/utility/amd_buffer_addressing.hpp
--- a/include/ck/utility/amd_inline_asm.hpp
+++ b/include/ck/utility/amd_inline_asm.hpp
--- a/include/ck/utility/amd_wmma.hpp
+++ b/include/ck/utility/amd_wmma.hpp
--- a/include/ck/utility/data_type.hpp
+++ b/include/ck/utility/data_type.hpp
--- a/include/ck/utility/inner_product.hpp
+++ b/include/ck/utility/inner_product.hpp
--- a/include/ck/utility/math.hpp
+++ b/include/ck/utility/math.hpp
--- a/include/ck/utility/math_v2.hpp
+++ b/include/ck/utility/math_v2.hpp
--- a/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
+++ b/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp