Merge branch 'develop' into feature/simplify-karg-for-device-gemm-xdl-improved

6c8de278 · zjing14 · GitHub · ec408b41 · b94fd0b2 · 6c8de278
Unverified Commit 6c8de278 authored Jun 01, 2023 by zjing14 Committed by GitHub Jun 01, 2023
20 changed files
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd_bias_activation_add.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm_layernorm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm.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/reference_tensor_operation/cpu/reference_reduce.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_reduce.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_softmax.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_sparse_embedding3_forward_layernorm.hpp
--- a/library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/gpu/naive_conv_fwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/add_device_operation_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/add_device_operation_instance.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
--- 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_permute.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_bias_permute.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.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_softmax_gemm.hpp