Merge branch 'develop' into bmatrix_skip_lds

f9c478e2 · ltqin · 7d85d04a · 91d8b7d6 · f9c478e2 · f9c478e2
Commit f9c478e2 authored May 30, 2022 by ltqin
20 changed files
--- a/include/ck/stream_config.hpp
+++ b/include/ck/stream_config.hpp
--- a/include/ck/tensor_description/tensor_descriptor_helper.hpp
+++ b/include/ck/tensor_description/tensor_descriptor_helper.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v4r1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r2.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v6r3.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_backward_weight_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_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_binary_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_binary_elementwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_backward_weight_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_c_shuffle_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv2d_fwd_xdl_nhwc_kyxc_nhwk.hpp