update

library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_streamk.hpp

@@ -924,7 +924,7 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGemm_S
         }
 #endif
 
-// Emin @Added
+
 #ifdef CK_ENABLE_BF16
         if constexpr(is_same_v<ADataType, bhalf_t> && is_same_v<BDataType, bhalf_t> &&
                      is_same_v<CDataType, bhalf_t>)
@@ -1027,7 +1027,7 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGemm_S
             }
         }
 #endif
-        // EMin @Added
+
 
 #if(defined(CK_ENABLE_FP8))
         if constexpr(is_same_v<ADataType, half_t> && is_same_v<BDataType, f8_t> &&

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_default_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
-                                                      Col,
-                                                      Row,
-                                                      BF16,
-                                                      BF16,
-                                                      BF16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_nk_mn_comp_instances<GemmDefault>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

profiler/src/profile_gemm_universal_streamk.cpp

@@ -91,9 +91,7 @@ int profile_gemm_universal_streamk(int argc, char* argv[])
     using F8 = ck::f8_t;
 #endif
 
-#if defined(CK_USE_GFX94)
-    using BF16 = ck::bf16_t;
-#endif
+
 
     using Row = ck::tensor_layout::gemm::RowMajor;
     using Col = ck::tensor_layout::gemm::ColumnMajor;