universal streamk fp8 changes (#1665)

* universal streamk fp8 changes & ckprofiler instances

* revert strides to -1 and verification options

* fp8 exclusion on pre-gfx94 for universal_streamk

* PR review based revisions: permissions reverted,  removed hip err checks


---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_instances<Intrawave,
+                                                                            GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_default_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_instances<Interwave,
+                                                                            GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_kpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_instances<Interwave,
+                                                                            GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_kn_mn_mem_instances<Interwave,
+                                                                            GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_default_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_default_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Intrawave,
+                                                                            GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Intrawave,
+                                                                            GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Intrawave,
+                                                                            GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_default_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Interwave,
+                                                                            GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Interwave,
+                                                                            GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f8_f16_f16/device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_xdl_universal_streamk_f8_f16_f16_mk_nk_mn_mem_instances<Interwave,
+                                                                            GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/gemm_universal_streamk/CMakeLists.txt

-# ONLY XDL_KERNELS
-set(GEMM_UNIVERSAL_STREAMK_INSTANCES)
-
-list(APPEND GEMM_UNIVERSAL_STREAMK_INSTANCES 
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v1_mnkpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v1_mnkpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_default_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_kpadding_instance.cpp
-        device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_nk_mn_mem_v2_mnkpadding_instance.cpp)
-
-add_instance_library(device_gemm_universal_streamk_instance ${GEMM_UNIVERSAL_STREAMK_INSTANCES})

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_default_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
-                                                      Row,
-                                                      Row,
-                                                      F16,
-                                                      F16,
-                                                      F16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_instances<GemmDefault>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
-                                                      Row,
-                                                      Row,
-                                                      F16,
-                                                      F16,
-                                                      F16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_instances<GemmKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
-                                                      Row,
-                                                      Row,
-                                                      F16,
-                                                      F16,
-                                                      F16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_instances<GemmMNKPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/gemm_universal_streamk/device_gemm_xdl_universal_streamk_f16_f16_f16/device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp

-// SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
-
-#include "device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn.hpp"
-
-namespace ck {
-namespace tensor_operation {
-namespace device {
-namespace instance {
-
-void add_device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Row,
-                                                      Row,
-                                                      Row,
-                                                      F16,
-                                                      F16,
-                                                      F16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
-{
-    add_device_operation_instances(
-        instances,
-        device_gemm_xdl_universal_streamk_f16_f16_f16_mk_kn_mn_comp_instances<GemmMNPadding>{});
-}
-
-} // namespace instance
-} // namespace device
-} // namespace tensor_operation
-} // namespace ck