fix triagle name

example/32_batched_gemm_scale_softmax_gemm/batched_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp

@@ -59,7 +59,7 @@ using CElementOp    = PassThrough;
 
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 
 static constexpr auto TensorSpecA  = ck::tensor_operation::device::TensorSpecialization::Default;
 static constexpr auto TensorSpecB0 = ck::tensor_operation::device::TensorSpecialization::Default;

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_v1.cpp

@@ -85,7 +85,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_v2.cpp

@@ -85,7 +85,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromBottomRight;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromBottomRight;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_train_v1.cpp

@@ -94,7 +94,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_train_v2.cpp

@@ -94,7 +94,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16.cpp

@@ -58,7 +58,7 @@ using CElementOp    = PassThrough;
 
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 
 static constexpr auto TensorSpecA  = ck::tensor_operation::device::TensorSpecialization::Default;
 static constexpr auto TensorSpecB0 = ck::tensor_operation::device::TensorSpecialization::Default;

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_backward_v1.cpp

@@ -84,7 +84,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_backward_v2.cpp

@@ -84,7 +84,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_train_v1.cpp

@@ -93,7 +93,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

example/32_batched_gemm_scale_softmax_gemm/grouped_multihead_attention_train_v2.cpp

@@ -93,7 +93,7 @@ static constexpr ck::index_t CShuffleBlockTransferScalarPerVector_NPerBlock = 8;
 static constexpr auto GemmSpec = ck::tensor_operation::device::GemmSpecialization::MNKOPadding;
 #if USING_MASK
 static constexpr auto MaskingSpec =
-    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTringleFromTopLeft;
+    ck::tensor_operation::device::MaskingSpecialization::MaskUpperTriangleFromTopLeft;
 #else
 static constexpr auto MaskingSpec =
     ck::tensor_operation::device::MaskingSpecialization::MaskDisabled;

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp

@@ -319,13 +319,13 @@ struct DeviceBatchedGemmSoftmaxGemmPermute_Xdl_CShuffle
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_xdl_cshuffle.hpp

@@ -364,7 +364,7 @@ struct DeviceBatchedGemmSoftmaxGemm_Xdl_CShuffle
     using CGridDesc_M_N        = decltype(MakeCGridDescriptor_M_N(1, 1, 1));
 
     using C0MatrixMask = conditional_t<MaskOutUpperTriangle,
-                                       C0MatrixMask_impl<MaskUpperTringleFromTopLeftPredicate>,
+                                       C0MatrixMask_impl<MaskUpperTriangleFromTopLeftPredicate>,
                                        C0MatrixMask_impl<MaskDisabledPredicate>>;
 
     // GridwiseGemm

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v1.hpp

@@ -564,13 +564,13 @@ struct DeviceBatchedMultiheadAttentionBackward_Kloop_Xdl_CShuffle_V1
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_kloop_v2.hpp

@@ -570,13 +570,13 @@ struct DeviceBatchedMultiheadAttentionBackward_Kloop_Xdl_CShuffle_V2
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v1.hpp

@@ -559,13 +559,13 @@ struct DeviceBatchedMultiheadAttentionBackward_Qloop_Xdl_CShuffle_V1
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_bwd_xdl_cshuffle_qloop_v2.hpp

@@ -565,13 +565,13 @@ struct DeviceBatchedMultiheadAttentionBackward_Qloop_Xdl_CShuffle_V2
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v1.hpp

@@ -386,13 +386,13 @@ struct DeviceBatchedMultiheadAttentionForward_Xdl_CShuffle_V1
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_batched_mha_fwd_xdl_cshuffle_v2.hpp

@@ -394,13 +394,13 @@ struct DeviceBatchedMultiheadAttentionForward_Xdl_CShuffle_V2
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp

@@ -291,13 +291,13 @@ struct DeviceGroupedGemmSoftmaxGemmPermute_Xdl_CShuffle
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;

include/ck/tensor_operation/gpu/device/impl/device_grouped_mha_bwd_xdl_cshuffle_kloop_v1.hpp

@@ -500,13 +500,13 @@ struct DeviceGroupedMultiheadAttentionBackward_Kloop_Xdl_CShuffle_V1
         {
             return MaskDisabledPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromTopLeft)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromTopLeft)
         {
-            return MaskUpperTringleFromTopLeftPredicate{};
+            return MaskUpperTriangleFromTopLeftPredicate{};
         }
-        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTringleFromBottomRight)
+        else if constexpr(MaskingSpec == MaskingSpecialization::MaskUpperTriangleFromBottomRight)
         {
-            return MaskUpperTringleFromBottomRightPredicate{};
+            return MaskUpperTriangleFromBottomRightPredicate{};
         }
     }
     using C0MatrixMask = C0MatrixMask_impl<decltype(make_MaskOutPredicate())>;