fixed block_sync_lds

ae3d6cb6 · Jing Zhang · 760b0c75 · b62926dc · ae3d6cb6 · ae3d6cb6
Commit ae3d6cb6 authored Feb 27, 2024 by Jing Zhang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_bwd_data_bilinear/xdl/device_grouped_conv3d_bwd_data_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_bilinear/xdl/device_grouped_conv3d_fwd_xdl_bilinear_ndhwgc_gkzyxc_ndhwgk_int8_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/device_grouped_gemm_xdl_fixed_nk_bf16_i8_bf16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp