[AArch64] Adjust costs of i1 and/or/xor reductions

This expands the reduction cost of i1 and/or/xor, so that larger type sizes get
handled by the existing code. For i1 reductions - and will use maxv, or will use
minv and xor will use addv, plus the cost of legalizing the type for larger
vectors using and/or/xor. The i1 vectors will be legalized to higher width
integers (say v16i8), which this overrides the cost of. As with all i1 vectors
there is a chance that the types the i1 vector is created with and how it is
used will not match, introducing extra extends that are not necessarily
costmodelled.
https://godbolt.org/z/6Gc9K6b7T

Differential Revision: https://reviews.llvm.org/D151184

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 3b10a27..306c66f 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3208,8 +3208,7 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
     if (!Entry)
       break;
     auto *ValVTy = cast<FixedVectorType>(ValTy);
-    if (!ValVTy->getElementType()->isIntegerTy(1) &&
-        MTy.getVectorNumElements() <= ValVTy->getNumElements() &&
+    if (MTy.getVectorNumElements() <= ValVTy->getNumElements() &&
         isPowerOf2_32(ValVTy->getNumElements())) {
       InstructionCost ExtraCost = 0;
       if (LT.first != 1) {
@@ -3220,7 +3219,9 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
         ExtraCost = getArithmeticInstrCost(Opcode, Ty, CostKind);
         ExtraCost *= LT.first - 1;
       }
-      return Entry->Cost + ExtraCost;
+      // All and/or/xor of i1 will be lowered with maxv/minv/addv + fmov
+      auto Cost = ValVTy->getElementType()->isIntegerTy(1) ? 2 : Entry->Cost;
+      return Cost + ExtraCost;
     }
     break;
   }

diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
index 2ca3bf1..fd7539b 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-and.ll
@@ -10,9 +10,9 @@ define void @reduce() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.and.v4i1(<4 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.and.v8i1(<8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.and.v16i1(<16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.and.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i1 @llvm.vector.reduce.and.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i1 @llvm.vector.reduce.and.v128i1(<128 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.and.v1i8(<1 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.and.v3i8(<3 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> undef)

diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
index cb8f7c3..7215b6c 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-or.ll
@@ -10,9 +10,9 @@ define void @reduce() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 91 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 181 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 362 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.or.v1i8(<1 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.or.v3i8(<3 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.or.v4i8(<4 x i8> undef)

diff --git a/llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll b/llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll
index 736b218..eeb32d6 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/reduce-xor.ll
@@ -7,12 +7,12 @@ define void @reduce() {
 ; CHECK-LABEL: 'reduce'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1 = call i1 @llvm.vector.reduce.xor.v1i1(<1 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.xor.v2i1(<2 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4 = call i1 @llvm.vector.reduce.xor.v4i1(<4 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V8 = call i1 @llvm.vector.reduce.xor.v8i1(<8 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16 = call i1 @llvm.vector.reduce.xor.v16i1(<16 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 127 for instruction: %V32 = call i1 @llvm.vector.reduce.xor.v32i1(<32 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 309 for instruction: %V64 = call i1 @llvm.vector.reduce.xor.v64i1(<64 x i1> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 673 for instruction: %V128 = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.xor.v4i1(<4 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.xor.v8i1(<8 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.xor.v16i1(<16 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.xor.v32i1(<32 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i1 @llvm.vector.reduce.xor.v64i1(<64 x i1> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i1 @llvm.vector.reduce.xor.v128i1(<128 x i1> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V1i8 = call i8 @llvm.vector.reduce.xor.v1i8(<1 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V3i8 = call i8 @llvm.vector.reduce.xor.v3i8(<3 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = call i8 @llvm.vector.reduce.xor.v4i8(<4 x i8> undef)