diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 32edfad5a5d97..8dacc770127a8 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3545,20 +3545,58 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
       return Cost;
     }
     [[fallthrough]];
-  case ISD::UDIV: {
+  case ISD::UDIV:
+  case ISD::UREM: {
     auto VT = TLI->getValueType(DL, Ty);
-    if (Op2Info.isConstant() && Op2Info.isUniform()) {
+    if (Op2Info.isConstant()) {
+      // If the operand is a power of 2 we can use the shift or and cost.
+      if (ISD == ISD::UDIV && Op2Info.isPowerOf2())
+        return getArithmeticInstrCost(Instruction::LShr, Ty, CostKind,
+                                      Op1Info.getNoProps(),
+                                      Op2Info.getNoProps());
+      if (ISD == ISD::UREM && Op2Info.isPowerOf2())
+        return getArithmeticInstrCost(Instruction::And, Ty, CostKind,
+                                      Op1Info.getNoProps(),
+                                      Op2Info.getNoProps());
+
+      if (ISD == ISD::UDIV || ISD == ISD::UREM) {
+        // Divides by a constant are expanded to MULHU + SUB + SRL + ADD + SRL.
+        // The MULHU will be expanded to UMULL for the types not listed below,
+        // and will become a pair of UMULL+MULL2 for 128bit vectors.
+        bool HasMULH = VT == MVT::i64 || LT.second == MVT::nxv2i64 ||
+                       LT.second == MVT::nxv4i32 || LT.second == MVT::nxv8i16 ||
+                       LT.second == MVT::nxv16i8;
+        bool Is128bit = LT.second.is128BitVector();
+
+        InstructionCost MulCost =
+            getArithmeticInstrCost(Instruction::Mul, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
+        InstructionCost AddCost =
+            getArithmeticInstrCost(Instruction::Add, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
+        InstructionCost ShrCost =
+            getArithmeticInstrCost(Instruction::AShr, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
+        InstructionCost DivCost = MulCost * (Is128bit ? 2 : 1) + // UMULL/UMULH
+                                  (HasMULH ? 0 : ShrCost) +      // UMULL shift
+                                  AddCost * 2 + ShrCost;
+        return DivCost + (ISD == ISD::UREM ? MulCost + AddCost : 0);
+      }
+
+      // TODO: Fix SDIV and SREM costs, similar to the above.
       if (TLI->isOperationLegalOrCustom(ISD::MULHU, VT) &&
-          !VT.isScalableVector()) {
+          Op2Info.isUniform() && !VT.isScalableVector()) {
         // Vector signed division by constant are expanded to the
-        // sequence MULHS + ADD/SUB + SRA + SRL + ADD, and unsigned division
-        // to MULHS + SUB + SRL + ADD + SRL.
-        InstructionCost MulCost = getArithmeticInstrCost(
-            Instruction::Mul, Ty, CostKind, Op1Info.getNoProps(), Op2Info.getNoProps());
-        InstructionCost AddCost = getArithmeticInstrCost(
-            Instruction::Add, Ty, CostKind, Op1Info.getNoProps(), Op2Info.getNoProps());
-        InstructionCost ShrCost = getArithmeticInstrCost(
-            Instruction::AShr, Ty, CostKind, Op1Info.getNoProps(), Op2Info.getNoProps());
+        // sequence MULHS + ADD/SUB + SRA + SRL + ADD.
+        InstructionCost MulCost =
+            getArithmeticInstrCost(Instruction::Mul, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
+        InstructionCost AddCost =
+            getArithmeticInstrCost(Instruction::Add, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
+        InstructionCost ShrCost =
+            getArithmeticInstrCost(Instruction::AShr, Ty, CostKind,
+                                   Op1Info.getNoProps(), Op2Info.getNoProps());
         return MulCost * 2 + AddCost * 2 + ShrCost * 2 + 1;
       }
     }
@@ -3571,7 +3609,7 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
 
     InstructionCost Cost = BaseT::getArithmeticInstrCost(
         Opcode, Ty, CostKind, Op1Info, Op2Info);
-    if (Ty->isVectorTy()) {
+    if (Ty->isVectorTy() && (ISD == ISD::SDIV || ISD == ISD::UDIV)) {
       if (TLI->isOperationLegalOrCustom(ISD, LT.second) && ST->hasSVE()) {
         // SDIV/UDIV operations are lowered using SVE, then we can have less
         // costs.
diff --git a/llvm/test/Analysis/CostModel/AArch64/div.ll b/llvm/test/Analysis/CostModel/AArch64/div.ll
index 50ed702d0339f..fba6d9ab31793 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div.ll
@@ -346,28 +346,28 @@ define void @sdiv_const() {
 define void @udiv_const() {
 ; CHECK-LABEL: 'udiv_const'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 7
-; 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 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
-; 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 28 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 4, i32 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
-; 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 28 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 4, i16 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; 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 28 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 4, i8 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I32 = udiv i32 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 4, i32 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = udiv i16 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 4, i16 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = udiv i8 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 4, i8 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 
@@ -463,28 +463,28 @@ define void @sdiv_uniformconst() {
 define void @udiv_uniformconst() {
 ; CHECK-LABEL: 'udiv_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 7
-; 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 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (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 10 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (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 10 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (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 10 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I32 = udiv i32 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = udiv i16 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = udiv i8 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = udiv i128 undef, 7
@@ -578,29 +578,29 @@ define void @sdiv_constpow2() {
 
 define void @udiv_constpow2() {
 ; CHECK-LABEL: 'udiv_constpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 16
-; 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 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I128 = udiv i128 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
 ; 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 28 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 2, i32 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 2, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
 ; 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 28 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 2, i16 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 2, i16 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
 ; 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 28 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 2, i8 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 2, i8 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = udiv i128 undef, 16
@@ -694,29 +694,29 @@ define void @sdiv_uniformconstpow2() {
 
 define void @udiv_uniformconstpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, 16
-; 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 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I128 = udiv i128 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, splat (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 10 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, splat (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 10 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, splat (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 10 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = udiv i128 undef, 16
@@ -811,28 +811,28 @@ define void @sdiv_constnegpow2() {
 define void @udiv_constnegpow2() {
 ; CHECK-LABEL: 'udiv_constnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, -16
-; 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 28 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
-; 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 28 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 -2, i32 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; 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 28 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 -2, i16 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 176 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 352 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; 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 28 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 -2, i8 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 168 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 336 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 672 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I32 = udiv i32 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, <i32 -2, i32 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = udiv i16 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, <i16 -2, i16 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = udiv i8 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, <i8 -2, i8 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = udiv i128 undef, -16
@@ -927,28 +927,28 @@ define void @sdiv_uniformconstnegpow2() {
 define void @udiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = udiv i128 undef, -16
-; 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 10 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i64 = udiv <8 x i64> undef, splat (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 10 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i32 = udiv <16 x i32> undef, splat (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 10 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i16 = udiv <32 x i16> undef, splat (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 10 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I32 = udiv i32 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = udiv i16 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = udiv i8 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = udiv i128 undef, -16
diff --git a/llvm/test/Analysis/CostModel/AArch64/div_cte.ll b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
index dd93aed53c0f2..68e287477042d 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
@@ -34,7 +34,7 @@ define <4 x i32> @sdiv32xi4(<4 x i32> %x) {
 
 define <16 x i8> @udiv8xi16(<16 x i8> %x) {
 ; CHECK-LABEL: 'udiv8xi16'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %div = udiv <16 x i8> %x, splat (i8 9)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %div = udiv <16 x i8> %x, splat (i8 9)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %div
 ;
   %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
@@ -43,7 +43,7 @@ define <16 x i8> @udiv8xi16(<16 x i8> %x) {
 
 define <8 x i16> @udiv16xi8(<8 x i16> %x) {
 ; CHECK-LABEL: 'udiv16xi8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %div = udiv <8 x i16> %x, splat (i16 9)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %div = udiv <8 x i16> %x, splat (i16 9)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %div
 ;
   %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
@@ -52,7 +52,7 @@ define <8 x i16> @udiv16xi8(<8 x i16> %x) {
 
 define <4 x i32> @udiv32xi4(<4 x i32> %x) {
 ; CHECK-LABEL: 'udiv32xi4'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %div = udiv <4 x i32> %x, splat (i32 9)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %div = udiv <4 x i32> %x, splat (i32 9)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %div
 ;
   %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
diff --git a/llvm/test/Analysis/CostModel/AArch64/fshl.ll b/llvm/test/Analysis/CostModel/AArch64/fshl.ll
index 317adc96a74b6..1ddc995366bcc 100644
--- a/llvm/test/Analysis/CostModel/AArch64/fshl.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/fshl.ll
@@ -224,7 +224,7 @@ declare <2 x i64> @llvm.fshl.v4i64(<2 x i64>, <2 x i64>, <2 x i64>)
 
 define <4 x i30> @fshl_v4i30_3rd_arg_var(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c) {
 ; CHECK-LABEL: 'fshl_v4i30_3rd_arg_var'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %fshl = tail call <4 x i30> @llvm.fshl.v4i30(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %fshl = tail call <4 x i30> @llvm.fshl.v4i30(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i30> %fshl
 ;
 entry:
diff --git a/llvm/test/Analysis/CostModel/AArch64/fshr.ll b/llvm/test/Analysis/CostModel/AArch64/fshr.ll
index 14f1f996fa174..438690f76f019 100644
--- a/llvm/test/Analysis/CostModel/AArch64/fshr.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/fshr.ll
@@ -224,7 +224,7 @@ declare <2 x i64> @llvm.fshr.v4i64(<2 x i64>, <2 x i64>, <2 x i64>)
 
 define <4 x i30> @fshr_v4i30_3rd_arg_var(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c) {
 ; CHECK-LABEL: 'fshr_v4i30_3rd_arg_var'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %fshr = tail call <4 x i30> @llvm.fshr.v4i30(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %fshr = tail call <4 x i30> @llvm.fshr.v4i30(<4 x i30> %a, <4 x i30> %b, <4 x i30> %c)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i30> %fshr
 ;
 entry:
diff --git a/llvm/test/Analysis/CostModel/AArch64/rem.ll b/llvm/test/Analysis/CostModel/AArch64/rem.ll
index ef40c9d7feb07..f17533b713611 100644
--- a/llvm/test/Analysis/CostModel/AArch64/rem.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/rem.ll
@@ -63,7 +63,7 @@ define void @srem() {
 
 define void @urem() {
 ; CHECK-LABEL: 'urem'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %I128 = urem i128 undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = urem i64 undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = urem <2 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = urem <4 x i64> undef, undef
@@ -346,28 +346,28 @@ define void @srem_const() {
 define void @urem_const() {
 ; CHECK-LABEL: 'urem_const'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, <i32 4, i32 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, <i16 4, i16 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, <i8 4, i8 5>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = urem i64 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = urem i32 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, <i32 4, i32 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = urem i16 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, <i16 4, i16 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, <i16 4, i16 5, i16 6, i16 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = urem i8 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, <i8 4, i8 5>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, <i8 4, i8 5, i8 6, i8 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 
@@ -463,28 +463,28 @@ define void @srem_uniformconst() {
 define void @urem_uniformconst() {
 ; CHECK-LABEL: 'urem_uniformconst'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, 7
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = urem i64 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = urem i32 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = urem i16 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = urem i8 undef, 7
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = urem i128 undef, 7
@@ -578,29 +578,29 @@ define void @srem_constpow2() {
 
 define void @urem_constpow2() {
 ; CHECK-LABEL: 'urem_constpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, <i32 2, i32 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, <i16 2, i16 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, <i8 2, i8 4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I128 = urem i128 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = urem i64 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = urem i32 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = urem <2 x i32> undef, <i32 2, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = urem <2 x i16> undef, <i16 2, i16 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = urem <4 x i16> undef, <i16 2, i16 4, i16 8, i16 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = urem <2 x i8> undef, <i8 2, i8 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = urem <4 x i8> undef, <i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = urem <8 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = urem i128 undef, 16
@@ -694,29 +694,29 @@ define void @srem_uniformconstpow2() {
 
 define void @urem_uniformconstpow2() {
 ; CHECK-LABEL: 'urem_uniformconstpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I128 = urem i128 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = urem i64 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = urem i32 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = urem i128 undef, 16
@@ -811,28 +811,28 @@ define void @srem_constnegpow2() {
 define void @urem_constnegpow2() {
 ; CHECK-LABEL: 'urem_constnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, <i32 -2, i32 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, <i16 -2, i16 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, <i8 -2, i8 -4>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = urem i64 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = urem i32 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, <i32 -2, i32 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = urem i16 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, <i16 -2, i16 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = urem i8 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, <i8 -2, i8 -4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = urem i128 undef, -16
@@ -927,28 +927,28 @@ define void @srem_uniformconstnegpow2() {
 define void @urem_uniformconstnegpow2() {
 ; CHECK-LABEL: 'urem_uniformconstnegpow2'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %I128 = urem i128 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %I64 = urem i64 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 52 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 104 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = urem i32 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I16 = urem i16 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I8 = urem i8 undef, -16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 448 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I64 = urem i64 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = urem i32 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I16 = urem i16 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I8 = urem i8 undef, -16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %I128 = urem i128 undef, -16
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-div.ll b/llvm/test/Analysis/CostModel/AArch64/sve-div.ll
index 33bc4ebe3c3ed..d20ebbf0ea9c1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-div.ll
@@ -242,42 +242,42 @@ define void @sdiv_uniformconst() {
 
 define void @udiv_uniformconst() {
 ; CHECK-LABEL: 'udiv_uniformconst'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = udiv <2 x i64> undef, splat (i64 7)
@@ -400,42 +400,42 @@ define void @sdiv_uniformconstpow2() {
 
 define void @udiv_uniformconstpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = udiv <2 x i64> undef, splat (i64 16)
@@ -558,42 +558,42 @@ define void @sdiv_uniformconstnegpow2() {
 
 define void @udiv_uniformconstnegpow2() {
 ; CHECK-LABEL: 'udiv_uniformconstnegpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4i64 = udiv <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8i64 = udiv <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i32 = udiv <2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4i32 = udiv <4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8i32 = udiv <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16i32 = udiv <16 x i32> undef, splat (i32 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i16 = udiv <2 x i16> undef, splat (i16 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i16 = udiv <4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8i16 = udiv <8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16i16 = udiv <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32i16 = udiv <32 x i16> undef, splat (i16 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2i8 = udiv <2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4i8 = udiv <4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8i8 = udiv <8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16i8 = udiv <16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32i8 = udiv <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V64i8 = udiv <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i64 = udiv <vscale x 2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV4i64 = udiv <vscale x 4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV8i64 = udiv <vscale x 8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i32 = udiv <vscale x 2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i32 = udiv <vscale x 4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i32 = udiv <vscale x 8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i32 = udiv <vscale x 16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i16 = udiv <vscale x 2 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i16 = udiv <vscale x 4 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i16 = udiv <vscale x 8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV16i16 = udiv <vscale x 16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV32i16 = udiv <vscale x 32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i8 = udiv <vscale x 2 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i8 = udiv <vscale x 4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i8 = udiv <vscale x 8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV16i8 = udiv <vscale x 16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV32i8 = udiv <vscale x 32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV64i8 = udiv <vscale x 64 x i8> undef, splat (i8 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = udiv <2 x i64> undef, splat (i64 -16)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-rem.ll b/llvm/test/Analysis/CostModel/AArch64/sve-rem.ll
index c1591fe5fde33..d18ed3296585b 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-rem.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-rem.ll
@@ -242,42 +242,42 @@ define void @srem_uniformconst() {
 
 define void @urem_uniformconst() {
 ; CHECK-LABEL: 'urem_uniformconst'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 7)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 7)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 7)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = urem <2 x i64> undef, splat (i64 7)
@@ -400,42 +400,42 @@ define void @srem_uniformconstpow2() {
 
 define void @urem_uniformconstpow2() {
 ; CHECK-LABEL: 'urem_uniformconstpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = urem <2 x i64> undef, splat (i64 16)
@@ -558,42 +558,42 @@ define void @srem_uniformconstnegpow2() {
 
 define void @urem_uniformconstnegpow2() {
 ; CHECK-LABEL: 'urem_uniformconstnegpow2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2i64 = urem <2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4i64 = urem <4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8i64 = urem <8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i32 = urem <2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4i32 = urem <4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8i32 = urem <8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16i32 = urem <16 x i32> undef, splat (i32 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i16 = urem <2 x i16> undef, splat (i16 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i16 = urem <4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8i16 = urem <8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16i16 = urem <16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32i16 = urem <32 x i16> undef, splat (i16 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2i8 = urem <2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 -16)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4i8 = urem <4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8i8 = urem <8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16i8 = urem <16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32i8 = urem <32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V64i8 = urem <64 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i64 = urem <vscale x 2 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV4i64 = urem <vscale x 4 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV8i64 = urem <vscale x 8 x i64> undef, splat (i64 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i32 = urem <vscale x 2 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i32 = urem <vscale x 4 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV8i32 = urem <vscale x 8 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV16i32 = urem <vscale x 16 x i32> undef, splat (i32 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i16 = urem <vscale x 2 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i16 = urem <vscale x 4 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV8i16 = urem <vscale x 8 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV16i16 = urem <vscale x 16 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV32i16 = urem <vscale x 32 x i16> undef, splat (i16 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV2i8 = urem <vscale x 2 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV4i8 = urem <vscale x 4 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV8i8 = urem <vscale x 8 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %NV16i8 = urem <vscale x 16 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %NV32i8 = urem <vscale x 32 x i8> undef, splat (i8 -16)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %NV64i8 = urem <vscale x 64 x i8> undef, splat (i8 -16)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V2i64 = urem <2 x i64> undef, splat (i64 -16)