Merge branch 'develop' into feature/support-readfirstlane-for-object-types

ae8b307a · Po Yen Chen · GitHub · ad8bc60b · ac9e01e2 · ad8bc60b
Unverified Commit ae8b307a authored May 29, 2023 by Po Yen Chen Committed by GitHub May 29, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r3.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r3.hpp
--- a/include/ck/utility/amd_llvm_intrinsic.hpp
+++ b/include/ck/utility/amd_llvm_intrinsic.hpp
-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
-
-#ifndef CK_AMD_LLVM_INTRINSIC_HPP
-#define CK_AMD_LLVM_INTRINSIC_HPP
-
-#include "data_type.hpp"
-
-namespace ck {
-
-__device__ int32_t llvm_amdgcn_readfirstlane_i32(int32_t i) __asm("llvm.amdgcn.readfirstlane");
-
-} // namespace ck
-#endif
--- a/include/ck/utility/print.hpp
+++ b/include/ck/utility/print.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_2d.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_2d.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_activation.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_activation.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_activation_add.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_bias_activation_add.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_pool_fwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_add_relu_gemm_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_softmax_gemm_permute.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/contraction_bilinear.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/contraction_scale.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/convolution_backward_data.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/convolution_forward.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/device_elementwise_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_mean_squaremean_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_add_fastgelu.hpp