Merge remote-tracking branch 'upstream/develop' into merge_upstream_1129

also fix regression

Merge remote-tracking branch 'upstream/develop' into merge_upstream_1129
also fix regression
d27e0691 · Chao Liu · 0a7174ad · a2969aa8 · d27e0691 · d27e0691
Commit d27e0691 authored Nov 30, 2023 by Chao Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_multi_d/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_reduce/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/batched_gemm_softmax_gemm_permute/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gndhwc_3d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gndhwc_3d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gnhwc_2d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gnhwc_2d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gnwc_1d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_gnwc_1d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_ndhwgc_3d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_ndhwgc_3d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwgc_2d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nhwgc_2d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nwgc_1d_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/column_to_image/device_column_to_image_nwgc_1d_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_kknn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_kknn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_knnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_knnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_mknn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_mknn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_mnnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_bf16_bf16_bf16_bf16_compute_f32_mnnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_kknn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_kknn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_knnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_knnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_mknn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_bilinear/device_contraction_bilinear_m2_n2_k2_xdl_c_shuffle_f16_f16_f16_f16_compute_f32_mknn_instance.cpp