[llvm] e36dd3e - [AArch64] Fix cost modelling for SVE Min/Max Intrinsics
David Green via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 11 23:46:16 PDT 2023
Author: Tuan Chuong Goh
Date: 2023-07-12T07:46:12+01:00
New Revision: e36dd3ea8a18b08617f7c7689746860c6cd76c57
URL: https://github.com/llvm/llvm-project/commit/e36dd3ea8a18b08617f7c7689746860c6cd76c57
DIFF: https://github.com/llvm/llvm-project/commit/e36dd3ea8a18b08617f7c7689746860c6cd76c57.diff
LOG: [AArch64] Fix cost modelling for SVE Min/Max Intrinsics
Add more legal types for SMIN, SMAX, UMIN, UMAX in cost modelling for AArch64
Differential Revision: https://reviews.llvm.org/D154622
Added:
Modified:
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 85c22b534944e4..1c591d4931a749 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -401,7 +401,9 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
case Intrinsic::smin:
case Intrinsic::smax: {
static const auto ValidMinMaxTys = {MVT::v8i8, MVT::v16i8, MVT::v4i16,
- MVT::v8i16, MVT::v2i32, MVT::v4i32};
+ MVT::v8i16, MVT::v2i32, MVT::v4i32,
+ MVT::nxv16i8, MVT::nxv8i16, MVT::nxv4i32,
+ MVT::nxv2i64};
auto LT = getTypeLegalizationCost(RetTy);
// v2i64 types get converted to cmp+bif hence the cost of 2
if (LT.second == MVT::v2i64)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 4d55bf326126b1..81f100beb316a9 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -44,13 +44,13 @@ define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
@@ -71,13 +71,13 @@ define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
-; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
+; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
; TYPE_BASED_ONLY-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
index 7cd765c63860eb..7a801db1f35faa 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-min-max.ll
@@ -5,20 +5,20 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define void @umin() {
; CHECK-LABEL: 'umin'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.umin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.umin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.umin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.umin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V4i8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
@@ -40,20 +40,20 @@ define void @umin() {
define void @umax() {
; CHECK-LABEL: 'umax'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.umax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.umax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.umax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.umax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V4i8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
@@ -75,20 +75,20 @@ define void @umax() {
define void @smin() {
; CHECK-LABEL: 'smin'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.smin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.smin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.smin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.smin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V4i8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
@@ -110,20 +110,20 @@ define void @smin() {
define void @smax() {
; CHECK-LABEL: 'smax'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.smax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.smax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V16i8 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32i8 = call <vscale x 32 x i8> @llvm.smax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = call <vscale x 64 x i8> @llvm.smax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i16 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V2i64 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4i64 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%V4i8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
More information about the llvm-commits
mailing list