2 files changed, 27 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
index 3944fdbd31e..a6e662cf65e 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
@@ -172,6 +172,12 @@ class HasOneUseBinOp<SDPatternOperator op> : PatFrag<
   [{ return N->hasOneUse(); }]
 >;
 
+class HasOneUseTernaryOp<SDPatternOperator op> : PatFrag<
+  (ops node:$src0, node:$src1, node:$src2),
+  (op $src0, $src1, $src2),
+  [{ return N->hasOneUse(); }]
+>;
+
 //===----------------------------------------------------------------------===//
 // Load/Store Pattern Fragments
 //===----------------------------------------------------------------------===//
@@ -618,8 +624,10 @@ def smax_oneuse : HasOneUseBinOp<smax>;
 def smin_oneuse : HasOneUseBinOp<smin>;
 def umax_oneuse : HasOneUseBinOp<umax>;
 def umin_oneuse : HasOneUseBinOp<umin>;
+def sub_oneuse : HasOneUseBinOp<sub>;
 } // Properties = [SDNPCommutative, SDNPAssociative]
 
+def select_oneuse : HasOneUseTernaryOp<select>;
 
 // 24-bit arithmetic patterns
 def umul24 : PatFrag <(ops node:$x, node:$y), (mul node:$x, node:$y)>;
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 4b3a6ed751d..8e0fc856109 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -3309,6 +3309,25 @@ defm : SI_INDIRECT_Pattern <v8i32, i32, "V8">;
 defm : SI_INDIRECT_Pattern <v16i32, i32, "V16">;
 
 //===----------------------------------------------------------------------===//
+// SAD Patterns
+//===----------------------------------------------------------------------===//
+
+def : Pat <
+  (add (sub_oneuse (umax i32:$src0, i32:$src1),
+                   (umin i32:$src0, i32:$src1)),
+       i32:$src2),
+  (V_SAD_U32 $src0, $src1, $src2)
+>;
+
+def : Pat <
+  (add (select_oneuse (i1 (setugt i32:$src0, i32:$src1)),
+                      (sub i32:$src0, i32:$src1),
+                      (sub i32:$src1, i32:$src0)),
+       i32:$src2),
+  (V_SAD_U32 $src0, $src1, $src2)
+>;
+
+//===----------------------------------------------------------------------===//
 // Conversion Patterns
 //===----------------------------------------------------------------------===//