From 647024db6f554b4601fbf1258a71d2ed07e60f73 Mon Sep 17 00:00:00 2001
From: Anca Hamuraru <anca@streamhpc.com>
Date: Wed, 14 May 2025 09:41:19 +0000
Subject: [PATCH] Ammending changes for adding support for padding instances
 for f16xf16xf16

---
 .../gpu/gemm_universal.hpp                    | 24 ++++++++
 .../gpu/gemm_universal_wmma.inc               | 57 +++++++++++++++++++
 .../gpu/gemm_universal/CMakeLists.txt         | 36 +++++++++++-
 3 files changed, 114 insertions(+), 3 deletions(-)

diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
index 79212e16dd..94f442d63f 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
@@ -64,21 +64,45 @@ struct DeviceOperationInstanceFactory<
                          is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
         }
 #endif
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
index 1396437326..c4f52073ac 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
@@ -13,21 +13,78 @@ void add_device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
+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);
+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);
+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);
 
 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);
 
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
+void add_device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+
 void add_device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 
+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);
+
+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);
+
+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);
+
 void add_device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, F16, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
+
+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);
+
+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);
+
+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);
 #endif
 #ifdef CK_ENABLE_BF16
 void add_device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instances(
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
index 18eeefa522..4338cfb4f4 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
@@ -3,10 +3,25 @@ set(GEMM_UNIVERSAL_INSTANCES)
 
 list(APPEND GEMM_UNIVERSAL_INSTANCES
         device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp
-        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
-        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp
-        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
 
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
+
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
+
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
+        
         device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instance.cpp
         device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp
         device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_km_kn_mn_comp_default_instance.cpp
@@ -68,9 +83,24 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES
         )
 
 set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f16_f16_f16/device_gemm_wmma_universal_f16_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
 
 set_source_files_properties(device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
 set_source_files_properties(device_gemm_wmma_universal_bf16_bf16_bf16/device_gemm_wmma_universal_bf16_bf16_bf16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")