Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into wmma_gemm

289f15de · aska-0096 · 9bd44685 · d58b7f51 · 289f15de · 289f15de
Commit 289f15de authored Dec 09, 2022 by aska-0096
20 changed files
--- a/example/44_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
+++ b/example/44_conv2d_fwd_quantization/conv2d_fwd_xdl_bias_relu_perchannel_quantization_int8.cpp
--- a/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
+++ b/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_bias_relu_perlayer_quantization_int8.cpp
--- a/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
+++ b/example/44_conv2d_fwd_quant/conv2d_fwd_xdl_perlayer_quantization_int8.cpp
--- a/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
+++ b/example/44_elementwise_permute/elementwise_permute_4D_fp16.cpp
--- a/example/CMakeLists.txt
+++ b/example/CMakeLists.txt
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_bwd_weight.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_bwd_weight.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_dl_multiple_d_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp