[llvm] e6d992c - [AArch64] Adjust cost for min/max intrinsics using v2i8 and v2i16 (#212801)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 13 01:05:53 PDT 2026
Author: Jack Styles
Date: 2026-08-13T09:05:48+01:00
New Revision: e6d992cb5f9904f720e1df4aec09458777c0fb2d
URL: https://github.com/llvm/llvm-project/commit/e6d992cb5f9904f720e1df4aec09458777c0fb2d
DIFF: https://github.com/llvm/llvm-project/commit/e6d992cb5f9904f720e1df4aec09458777c0fb2d.diff
LOG: [AArch64] Adjust cost for min/max intrinsics using v2i8 and v2i16 (#212801)
When vectorizing min/max intrinsics with these types, using the changes
in #195823, the Type Promotion cost outweighs that of leaving the loop
as Scalar. The costs need to be adjusted to account for the promotion
costs to ensure loops of this kind will continue to be scalar.
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/min-max.ll
llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index d44b1afb3a1f0..1f4b1b69c0433 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -711,6 +711,14 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
MVT::nxv16i8, MVT::nxv8i16, MVT::nxv4i32,
MVT::nxv2i64};
auto LT = getTypeLegalizationCost(RetTy);
+ // Type promotion for v2i8 and v2i16 types have a heavy cost when
+ // vectorising. Account for this cost to avoid vectorising unprofitable
+ // examples when vectorising loops with low trip counts.
+ bool IsSigned =
+ ICA.getID() == Intrinsic::smin || ICA.getID() == Intrinsic::smax;
+ EVT VT = TLI->getValueType(DL, RetTy, /*AllowUnknown=*/true);
+ if (VT == MVT::v2i8 || VT == MVT::v2i16 || VT == MVT::v4i8)
+ return LT.first * (IsSigned ? 5 : 3);
// v2i64 types get converted to cmp+bif hence the cost of 2
if (LT.second == MVT::v2i64)
return LT.first * 2;
diff --git a/llvm/test/Analysis/CostModel/AArch64/min-max.ll b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
index 5e5026ccfa4df..75db5e8d4f2c0 100644
--- a/llvm/test/Analysis/CostModel/AArch64/min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/min-max.ll
@@ -79,12 +79,12 @@ define void @umin() {
; CHECK-BASE-LABEL: 'umin'
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 3 for: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 3 for: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -99,12 +99,12 @@ define void @umin() {
; CHECK-CSSC-LABEL: 'umin'
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 3 for: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 3 for: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -140,12 +140,12 @@ define void @umax() {
; CHECK-BASE-LABEL: 'umax'
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 3 for: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 3 for: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -160,12 +160,12 @@ define void @umax() {
; CHECK-CSSC-LABEL: 'umax'
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 3 for: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 3 for: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -201,12 +201,12 @@ define void @smin() {
; CHECK-BASE-LABEL: 'smin'
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 5 for: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 5 for: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -221,12 +221,12 @@ define void @smin() {
; CHECK-CSSC-LABEL: 'smin'
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 5 for: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 5 for: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -262,12 +262,12 @@ define void @smax() {
; CHECK-BASE-LABEL: 'smax'
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 5 for: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 5 for: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
@@ -282,12 +282,12 @@ define void @smax() {
; CHECK-CSSC-LABEL: 'smax'
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 5 for: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; CHECK-CSSC-NEXT: Cost Model: Found costs of 5 for: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
; CHECK-CSSC-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
index c5d7c6a09d872..07d6caa861f9d 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
@@ -128,8 +128,8 @@ while.end:
; CHECK-COST-LABEL: umin
; CHECK-COST: Found an estimated cost of 2 for VF 1 For instruction: %1 = tail call i8 @llvm.umin.i8(i8 %0, i8 %offset)
-; CHECK-COST: Cost of 1 for VF 2: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
-; CHECK-COST: Cost of 1 for VF 4: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
+; CHECK-COST: Cost of 3 for VF 2: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
+; CHECK-COST: Cost of 3 for VF 4: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
; CHECK-COST: Cost of 1 for VF 8: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
; CHECK-COST: Cost of 1 for VF 16: WIDEN-INTRINSIC ir<%1> = call llvm.umin(ir<%0>, ir<%offset>)
More information about the llvm-commits
mailing list