[AArch64] Fix cost model for `udiv` instruction when one of the operands is a uniform...

Currently the model over estimates the cost of a udiv instruction with one constant. The correct cost for a udiv instruction is
insert_cost * extract_cost * num_elements

Reviewed By: dmgreen

Differential Revision: https://reviews.llvm.org/D135991

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index b76eb9a..9e45902 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -2171,6 +2171,18 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
           Cost *= 4;
         return Cost;
       } else {
+        // If one of the operands is a uniform constant then the cost for each
+        // element is Cost for insertion, extraction and division.
+        // Insertion cost = 2, Extraction Cost = 2, Division = cost for the
+        // operation with scalar type
+        if ((Op1Info.isConstant() && Op1Info.isUniform()) ||
+            (Op2Info.isConstant() && Op2Info.isUniform())) {
+          if (auto *VTy = dyn_cast<FixedVectorType>(Ty)) {
+            InstructionCost DivCost = BaseT::getArithmeticInstrCost(
+                Opcode, Ty->getScalarType(), CostKind, Op1Info, Op2Info);
+            return (4 + DivCost) * VTy->getNumElements();
+          }
+        }
         // On AArch64, without SVE, vector divisions are expanded
         // into scalar divisions of each pair of elements.
         Cost += getArithmeticInstrCost(Instruction::ExtractElement, Ty,

diff --git a/llvm/test/Analysis/CostModel/AArch64/div.ll b/llvm/test/Analysis/CostModel/AArch64/div.ll
index 42ded8b..7486851 100644 (file)
--- a/llvm/test/Analysis/CostModel/AArch64/div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div.ll
@@ -178,21 +178,21 @@ define i32 @udiv_const() {
 define i32 @sdiv_uniformconst() {
 ; CHECK-LABEL: 'sdiv_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = sdiv i64 undef, 7
@@ -221,21 +221,21 @@ define i32 @sdiv_uniformconst() {
 define i32 @udiv_uniformconst() {
 ; CHECK-LABEL: 'udiv_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, 7
@@ -393,21 +393,21 @@ define i32 @sdiv_uniformconstpow2() {
 define i32 @udiv_uniformconstpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, 16
@@ -522,21 +522,21 @@ define i32 @udiv_constnegpow2() {
 define i32 @sdiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'sdiv_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = sdiv i64 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = sdiv i64 undef, -16
@@ -565,21 +565,21 @@ define i32 @sdiv_uniformconstnegpow2() {
 define i32 @udiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I64 = udiv i64 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = udiv i64 undef, -16