AMDGPU : Add V_SAD_U32 instruction pattern.

Differential Revision: http://reviews.llvm.org/D23069

llvm-svn: 279629

3 files changed, 310 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
 //===----------------------------------------------------------------------===//
 
diff --git a/llvm/test/CodeGen/AMDGPU/sad.ll b/llvm/test/CodeGen/AMDGPU/sad.ll
new file mode 100644
index 00000000000..87362dc1b0f
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/sad.ll
@@ -0,0 +1,283 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}v_sad_u32_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %b
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_constant_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, 20
+define void @v_sad_u32_constant_pat1(i32 addrspace(1)* %out, i32 %a) {
+  %icmp0 = icmp ugt i32 %a, 90
+  %t0 = select i1 %icmp0, i32 %a, i32 90
+
+  %icmp1 = icmp ule i32 %a, 90
+  %t1 = select i1 %icmp1, i32 %a, i32 90
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, 20
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_pat2:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_pat2(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %sub0 = sub i32 %a, %b
+  %sub1 = sub i32 %b, %a
+  %ret0 = select i1 %icmp0, i32 %sub0, i32 %sub1
+
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_sub_pat1:
+; GCN: s_max_u32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: s_min_u32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: s_add_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+define void @v_sad_u32_multi_use_sub_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %b
+
+  %ret0 = sub i32 %t0, %t1
+  store volatile i32 %ret0, i32 *undef
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_add_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_multi_use_add_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %b
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, %c
+  store volatile i32 %ret, i32 *undef
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_max_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_multi_use_max_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+  store volatile i32 %t0, i32 *undef
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %b
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_min_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_multi_use_min_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %b
+
+  store volatile i32 %t1, i32 *undef
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_sub_pat2:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_multi_use_sub_pat2(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %sub0 = sub i32 %a, %b
+  store volatile i32 %sub0, i32 *undef
+  %sub1 = sub i32 %b, %a
+  %ret0 = select i1 %icmp0, i32 %sub0, i32 %sub1
+
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_multi_use_select_pat2:
+; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: v_cmp_gt_u32_e32 vcc, s{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_multi_use_select_pat2(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %sub0 = sub i32 %a, %b
+  %sub1 = sub i32 %b, %a
+  %ret0 = select i1 %icmp0, i32 %sub0, i32 %sub1
+  store volatile i32 %ret0, i32 *undef
+
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_vector_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_vector_pat1(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b, <4 x i32> %c) {
+  %icmp0 = icmp ugt <4 x i32> %a, %b
+  %t0 = select <4 x i1> %icmp0, <4 x i32> %a, <4 x i32> %b
+
+  %icmp1 = icmp ule <4 x i32> %a, %b
+  %t1 = select <4 x i1> %icmp1, <4 x i32> %a, <4 x i32> %b
+
+  %ret0 = sub <4 x i32> %t0, %t1
+  %ret = add <4 x i32> %ret0, %c
+
+  store <4 x i32> %ret, <4 x i32> addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_vector_pat2:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_vector_pat2(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b, <4 x i32> %c) {
+  %icmp0 = icmp ugt <4 x i32> %a, %b
+  %sub0 = sub <4 x i32> %a, %b
+  %sub1 = sub <4 x i32> %b, %a
+  %ret0 = select <4 x i1> %icmp0, <4 x i32> %sub0, <4 x i32> %sub1
+
+  %ret = add <4 x i32> %ret0, %c
+
+  store <4 x i32> %ret, <4 x i32> addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_i16_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_i16_pat1(i16 addrspace(1)* %out, i16 %a, i16 %b, i16 %c) {
+
+  %icmp0 = icmp ugt i16 %a, %b
+  %t0 = select i1 %icmp0, i16 %a, i16 %b
+
+  %icmp1 = icmp ule i16 %a, %b
+  %t1 = select i1 %icmp1, i16 %a, i16 %b
+
+  %ret0 = sub i16 %t0, %t1
+  %ret = add i16 %ret0, %c
+
+  store i16 %ret, i16 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_i16_pat2:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_i16_pat2(i16 addrspace(1)* %out, i16 zeroext %a, i16 zeroext %b, i16 zeroext %c) {
+  %icmp0 = icmp ugt i16 %a, %b
+  %sub0 = sub i16 %a, %b
+  %sub1 = sub i16 %b, %a
+  %ret0 = select i1 %icmp0, i16 %sub0, i16 %sub1
+
+  %ret = add i16 %ret0, %c
+
+  store i16 %ret, i16 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_i8_pat1:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_i8_pat1(i8 addrspace(1)* %out, i8 %a, i8 %b, i8 %c) {
+  %icmp0 = icmp ugt i8 %a, %b
+  %t0 = select i1 %icmp0, i8 %a, i8 %b
+
+  %icmp1 = icmp ule i8 %a, %b
+  %t1 = select i1 %icmp1, i8 %a, i8 %b
+
+  %ret0 = sub i8 %t0, %t1
+  %ret = add i8 %ret0, %c
+
+  store i8 %ret, i8 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_i8_pat2:
+; GCN: v_sad_u32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_i8_pat2(i8 addrspace(1)* %out, i8 zeroext %a, i8 zeroext %b, i8 zeroext %c) {
+  %icmp0 = icmp ugt i8 %a, %b
+  %sub0 = sub i8 %a, %b
+  %sub1 = sub i8 %b, %a
+  %ret0 = select i1 %icmp0, i8 %sub0, i8 %sub1
+
+  %ret = add i8 %ret0, %c
+
+  store i8 %ret, i8 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_mismatched_operands_pat1:
+; GCN: v_cmp_le_u32_e32 vcc, s{{[0-9]+}}, v{{[0-9]+}}
+; GCN: s_max_u32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: v_sub_i32_e32 v{{[0-9]+}}, vcc, s{{[0-9]+}}, v{{[0-9]+}}
+; GCN: v_add_i32_e32 v{{[0-9]+}}, vcc, s{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_mismatched_operands_pat1(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c, i32 %d) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %t0 = select i1 %icmp0, i32 %a, i32 %b
+
+  %icmp1 = icmp ule i32 %a, %b
+  %t1 = select i1 %icmp1, i32 %a, i32 %d
+
+  %ret0 = sub i32 %t0, %t1
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: {{^}}v_sad_u32_mismatched_operands_pat2:
+; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: s_sub_i32 s{{[0-9]+}}, s{{[0-9]+}}, s{{[0-9]+}}
+; GCN: v_add_i32_e32 v{{[0-9]+}}, vcc, s{{[0-9]+}}, v{{[0-9]+}}
+define void @v_sad_u32_mismatched_operands_pat2(i32 addrspace(1)* %out, i32 %a, i32 %b, i32 %c, i32 %d) {
+  %icmp0 = icmp ugt i32 %a, %b
+  %sub0 = sub i32 %a, %d
+  %sub1 = sub i32 %b, %a
+  %ret0 = select i1 %icmp0, i32 %sub0, i32 %sub1
+
+  %ret = add i32 %ret0, %c
+
+  store i32 %ret, i32 addrspace(1)* %out
+  ret void
+}
+