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/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_f64_f64_f64_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias2d/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_bias_relu_add/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_reduce/device_gemm_reduce_xdl_cshuffle_f16_f16_f16_f32_f32_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp