Merge remote-tracking branch 'origin/develop' into gemm_splitk_improve_kpad

01ee5e53 · Jing Zhang · 959ddcf8 · b0568b72 · 01ee5e53 · 01ee5e53
Commit 01ee5e53 authored Nov 05, 2023 by Jing Zhang
15 changed files
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_kkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_kkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_knn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_knn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_compute_f32_mnn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_kkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_knn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mkn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/contraction_scale/device_contraction_scale_m2_n2_k2_xdl_c_shuffle_f64_f64_f64_mnn_instance.cpp
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_contraction_impl.hpp
+++ b/profiler/include/profiler/profile_contraction_impl.hpp
--- a/profiler/include/profiler/profile_contraction_utils.hpp
+++ b/profiler/include/profiler/profile_contraction_utils.hpp
@@ -23,8 +23,18 @@ enum struct ContractionMatrixLayout

 enum struct ContractionDataType
 {
-    F32_F32_F32_F32, // 0
-    F64_F64_F64_F64, // 1
+    F32_F32_F32_F32,     // 0
+    F64_F64_F64_F64,     // 1
+    F16_F16_F16_F16,     // 2
+    BF16_BF16_BF16_BF16, // 3
+};
+
+enum struct ContractionComputeDataType
+{
+    F32 = 0,
+    F64,
+    F16,
+    BF16,
 };

 inline void collect_index_params(char* argv[],

--- a/profiler/src/profile_contraction_bilinear.cpp
+++ b/profiler/src/profile_contraction_bilinear.cpp
--- a/profiler/src/profile_contraction_scale.cpp
+++ b/profiler/src/profile_contraction_scale.cpp
--- a/test/contraction/test_contraction.cpp
+++ b/test/contraction/test_contraction.cpp
--- a/test/contraction/test_contraction_interface.cpp
+++ b/test/contraction/test_contraction_interface.cpp