From dd47f39a0a128f794c0cfec607e892d4cc7df4e0 Mon Sep 17 00:00:00 2001
From: Anca Hamuraru <anca@streamhpc.com>
Date: Wed, 14 May 2025 07:54:46 +0000
Subject: [PATCH] Added padding instances for f16xf16xf16

---
 ...16_f16_km_kn_mn_comp_kpadding_instance.cpp | 24 ++++++++++++++++++
 ..._f16_km_kn_mn_comp_mnkpadding_instance.cpp | 25 +++++++++++++++++++
 ...6_f16_km_kn_mn_comp_mnpadding_instance.cpp | 24 ++++++++++++++++++
 ...16_f16_km_nk_mn_comp_kpadding_instance.cpp | 24 ++++++++++++++++++
 ..._f16_km_nk_mn_comp_mnkpadding_instance.cpp | 25 +++++++++++++++++++
 ...6_f16_km_nk_mn_comp_mnpadding_instance.cpp | 24 ++++++++++++++++++
 ...16_f16_mk_kn_mn_comp_kpadding_instance.cpp | 24 ++++++++++++++++++
 ..._f16_mk_kn_mn_comp_mnkpadding_instance.cpp | 25 +++++++++++++++++++
 ...6_f16_mk_kn_mn_comp_mnpadding_instance.cpp | 24 ++++++++++++++++++
 ...16_f16_mk_nk_mn_comp_kpadding_instance.cpp | 24 ++++++++++++++++++
 ..._f16_mk_nk_mn_comp_mnkpadding_instance.cpp | 24 ++++++++++++++++++
 ...6_f16_mk_nk_mn_comp_mnpadding_instance.cpp | 24 ++++++++++++++++++
 12 files changed, 291 insertions(+)
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
 create mode 100644 library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp

diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..9c1f77d979
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..4847f8035b
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..28a443799d
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..74d05580dc
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..694b6cb788
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..af6d71edff
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..6774ffa40e
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..1e6f7a337c
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances,
+        device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..6897778c15
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..331ca8b2ff
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..331ca8b2ff
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..331ca8b2ff
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_instances<GemmDefault>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck