[llvm] 65c0e45 - [AArch64] Vector shifts cost 1
David Green via llvm-commits
llvm-commits at lists.llvm.org
Thu Mar 3 02:43:01 PST 2022
Author: David Green
Date: 2022-03-03T10:42:57Z
New Revision: 65c0e45a3790c391a0e87d9150c993dbb6537dee
URL: https://github.com/llvm/llvm-project/commit/65c0e45a3790c391a0e87d9150c993dbb6537dee
DIFF: https://github.com/llvm/llvm-project/commit/65c0e45a3790c391a0e87d9150c993dbb6537dee.diff
LOG: [AArch64] Vector shifts cost 1
The costs of vector shifts was 2 as opposed to 1, as the nodes are
marked custom. Fix this like the others and mark the nodes as cheap.
Differential Revision: https://reviews.llvm.org/D120773
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
llvm/test/Analysis/CostModel/AArch64/arith.ll
llvm/test/Analysis/CostModel/AArch64/div.ll
llvm/test/Analysis/CostModel/AArch64/div_cte.ll
llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 7429c1b920d27..e5b530db61bd7 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1824,6 +1824,9 @@ InstructionCost AArch64TTIImpl::getArithmeticInstrCost(
case ISD::XOR:
case ISD::OR:
case ISD::AND:
+ case ISD::SRL:
+ case ISD::SRA:
+ case ISD::SHL:
// These nodes are marked as 'custom' for combining purposes only.
// We know that they are legal. See LowerAdd in ISelLowering.
return (Cost + 1) * LT.first;
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll b/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
index 1dbfdb82d89bf..68a8ede330024 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll
@@ -353,21 +353,21 @@ declare {<64 x i8>, <64 x i1>} @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x
define i32 @smul(i32 %arg) {
; RECIP-LABEL: 'smul'
; RECIP-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 76 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'smul'
@@ -439,17 +439,17 @@ define i32 @umul(i32 %arg) {
; RECIP-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 100 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT: Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
; RECIP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; SIZE-LABEL: 'umul'
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith.ll b/llvm/test/Analysis/CostModel/AArch64/arith.ll
index 501ee6ef6271b..1eedb34ff184a 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith.ll
@@ -132,36 +132,36 @@ define void @vi8() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c8 = add <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d8 = sub <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e8 = mul <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f8 = ashr <8 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g8 = lshr <8 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h8 = shl <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i8 = and <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j8 = or <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k8 = xor <8 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c16 = add <16 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d16 = sub <16 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e16 = mul <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f16 = ashr <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g16 = lshr <16 x i8> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h16 = shl <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f16 = ashr <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g16 = lshr <16 x i8> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h16 = shl <16 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i16 = and <16 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j16 = or <16 x i8> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k16 = xor <16 x i8> undef, undef
@@ -211,36 +211,36 @@ define void @vi16() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c8 = add <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d8 = sub <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e8 = mul <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f8 = ashr <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g8 = lshr <8 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h8 = shl <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i8 = and <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j8 = or <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k8 = xor <8 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %c16 = add <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %d16 = sub <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %e16 = mul <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f16 = ashr <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %g16 = lshr <16 x i16> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %h16 = shl <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f16 = ashr <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g16 = lshr <16 x i16> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h16 = shl <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i16 = and <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %j16 = or <16 x i16> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %k16 = xor <16 x i16> undef, undef
@@ -290,36 +290,36 @@ define void @vi32() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e2 = mul <2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c4 = add <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d4 = sub <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %e4 = mul <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f4 = ashr <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g4 = lshr <4 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h4 = shl <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i4 = and <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j4 = or <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k4 = xor <4 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %c8 = add <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %d8 = sub <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %e8 = mul <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f8 = ashr <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %g8 = lshr <8 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %h8 = shl <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f8 = ashr <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g8 = lshr <8 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h8 = shl <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i8 = and <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %j8 = or <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %k8 = xor <8 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %c16 = add <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %d16 = sub <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %e16 = mul <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %f16 = ashr <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %g16 = lshr <16 x i32> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %h16 = shl <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f16 = ashr <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %g16 = lshr <16 x i32> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %h16 = shl <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i16 = and <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %j16 = or <16 x i32> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %k16 = xor <16 x i32> undef, undef
@@ -369,36 +369,36 @@ define void @vi64() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %c2 = add <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %d2 = sub <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %e2 = mul <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f2 = ashr <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g2 = lshr <2 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h2 = shl <2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %f2 = ashr <2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %g2 = lshr <2 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %h2 = shl <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = and <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %j2 = or <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %k2 = xor <2 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %c4 = add <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %d4 = sub <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %e4 = mul <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f4 = ashr <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %g4 = lshr <4 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %h4 = shl <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %f4 = ashr <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %g4 = lshr <4 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %h4 = shl <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = and <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %j4 = or <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %k4 = xor <4 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %c8 = add <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %d8 = sub <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %e8 = mul <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %f8 = ashr <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %g8 = lshr <8 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %h8 = shl <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %f8 = ashr <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %g8 = lshr <8 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %h8 = shl <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %i8 = and <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %j8 = or <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %k8 = xor <8 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %c16 = add <16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %d16 = sub <16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %e16 = mul <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %f16 = ashr <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %g16 = lshr <16 x i64> undef, undef
-; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %h16 = shl <16 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %f16 = ashr <16 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %g16 = lshr <16 x i64> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %h16 = shl <16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %i16 = and <16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %j16 = or <16 x i64> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %k16 = xor <16 x i64> undef, undef
diff --git a/llvm/test/Analysis/CostModel/AArch64/div.ll b/llvm/test/Analysis/CostModel/AArch64/div.ll
index e3d28117f01fe..6ffb34f6ac2a8 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div.ll
@@ -180,15 +180,15 @@ define i32 @sdiv_uniformconst() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -223,15 +223,15 @@ define i32 @udiv_uniformconst() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -348,21 +348,21 @@ define i32 @udiv_constpow2() {
define i32 @sdiv_uniformconstpow2() {
; CHECK-LABEL: 'sdiv_uniformconstpow2'
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I64 = sdiv i64 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 28 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 52 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I32 = sdiv i32 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 60 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 120 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 58 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 116 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I16 = sdiv i16 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 124 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 248 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 122 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 244 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %I8 = sdiv i8 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 252 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
-; CHECK-NEXT: Cost Model: Found an estimated cost of 504 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 125 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 250 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 500 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%I64 = sdiv i64 undef, 16
@@ -395,15 +395,15 @@ define i32 @udiv_uniformconstpow2() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -524,15 +524,15 @@ define i32 @sdiv_uniformconstnegpow2() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -567,15 +567,15 @@ define i32 @udiv_uniformconstnegpow2() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 192 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 104 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 208 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 216 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 432 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
-; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 440 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 880 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
diff --git a/llvm/test/Analysis/CostModel/AArch64/div_cte.ll b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
index 6151e25358e48..bb84d77bb128a 100644
--- a/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/div_cte.ll
@@ -4,42 +4,42 @@
define <16 x i8> @sdiv8xi16(<16 x i8> %x) {
; CHECK-LABEL: function 'sdiv8xi16'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <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>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <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>
%div = sdiv <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>
ret <16 x i8> %div
}
define <8 x i16> @sdiv16xi8(<8 x i16> %x) {
; CHECK-LABEL: function 'sdiv16xi8'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
%div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
ret <8 x i16> %div
}
define <4 x i32> @sdiv32xi4(<4 x i32> %x) {
; CHECK-LABEL: function 'sdiv32xi4'
-; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
%div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
ret <4 x i32> %div
}
define <16 x i8> @udiv8xi16(<16 x i8> %x) {
; CHECK-LABEL: function 'udiv8xi16'
-; CHECK: Found an estimated cost of 9 for instruction: %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>
+; CHECK: Found an estimated cost of 7 for instruction: %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>
%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>
ret <16 x i8> %div
}
define <8 x i16> @udiv16xi8(<8 x i16> %x) {
; CHECK-LABEL: function 'udiv16xi8'
-; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
%div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
ret <8 x i16> %div
}
define <4 x i32> @udiv32xi4(<4 x i32> %x) {
; CHECK-LABEL: function 'udiv32xi4'
-; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
+; CHECK: Found an estimated cost of 7 for instruction: %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
%div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
ret <4 x i32> %div
}
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
index c566ac0a2f297..ca33e5b0b7d2b 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/gather-cost.ll
@@ -10,7 +10,7 @@ target triple = "aarch64--linux-gnu"
; REMARK-LABEL: Function: gather_multiple_use
; REMARK: Args:
; REMARK-NEXT: - String: 'Vectorized horizontal reduction with cost '
-; REMARK-NEXT: - Cost: '-6'
+; REMARK-NEXT: - Cost: '-7'
;
; REMARK-NOT: Function: gather_load
More information about the llvm-commits
mailing list