Refactor device op implementations into `impl` subdirectory. (#420)

* Move kernel implementation files under impl directory. * Update examples paths. * Update device kernel impl include paths. * Update tensor operation instances include paths. * Update profiler and tests include paths. * Clang-format * Update include paths for batched gemm reduce * Refactor UnitTest ConvNDBwdWeight. * Refactor fwd and bwd data convND UT. * Fix used test macro. * Fix include path. * Fix include paths. * Fix include paths in profiler and tests. * Fix include paths. Co-authored-by: Adam Osewski <aosewski@amd.com>

Refactor device op implementations into `impl` subdirectory. (#420)
* Move kernel implementation files under impl directory. * Update examples paths. * Update device kernel impl include paths. * Update tensor operation instances include paths. * Update profiler and tests include paths. * Clang-format * Update include paths for batched gemm reduce * Refactor UnitTest ConvNDBwdWeight. * Refactor fwd and bwd data convND UT. * Fix used test macro. * Fix include path. * Fix include paths. * Fix include paths in profiler and tests. * Fix include paths. Co-authored-by: Adam Osewski <aosewski@amd.com>
30480288 · Adam Osewski · GitHub · 1b62bfaa · 30480288 · 30480288
Unverified Commit 30480288 authored Oct 13, 2022 by Adam Osewski Committed by GitHub Oct 13, 2022
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.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_softmax_gemm_permute_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_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_cgemm_4gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_cgemm_4gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d_xdl_cshuffle.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
--- a/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_naive_ndhwc_kzyxc_ndhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv3d_fwd_xdl_ndhwc_kzyxc_ndhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise.hpp