[llvm] e7fda46 - [RISCV] Correct costs for vector ceil/floor/trunc/round
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 19 10:43:58 PDT 2022
Author: Philip Reames
Date: 2022-08-19T10:37:39-07:00
New Revision: e7fda4630040127cf79249b80a0cd53642ab652d
URL: https://github.com/llvm/llvm-project/commit/e7fda4630040127cf79249b80a0cd53642ab652d
DIFF: https://github.com/llvm/llvm-project/commit/e7fda4630040127cf79249b80a0cd53642ab652d.diff
LOG: [RISCV] Correct costs for vector ceil/floor/trunc/round
Add vector costs for ceil/floor/trunc/round. As can be seen in the tests, the prior default costs were a significant under estimate of the actual code generated.
These costs are computed by simply generating code with the current backend, and then counting the number of instructions. I discount one vsetvli, and ignore the return.
Differential Revision: https://reviews.llvm.org/D131967
Added:
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
llvm/test/Analysis/CostModel/RISCV/fround.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 9b36ce6b1b141..3a5570c8858d6 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -10,6 +10,7 @@
#include "MCTargetDesc/RISCVMatInt.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
+#include "llvm/CodeGen/CostTable.h"
#include "llvm/CodeGen/TargetLowering.h"
#include <cmath>
using namespace llvm;
@@ -250,6 +251,77 @@ InstructionCost RISCVTTIImpl::getGatherScatterOpCost(
return NumLoads * MemOpCost;
}
+// Currently, these represent both throughput and codesize costs
+// for the respective intrinsics. The costs in this table are simply
+// instruction counts with the following adjustments made:
+// * One vsetvli is considered free.
+static const CostTblEntry VectorIntrinsicCostTable[]{
+ {Intrinsic::floor, MVT::v2f32, 15},
+ {Intrinsic::floor, MVT::v4f32, 15},
+ {Intrinsic::floor, MVT::v8f32, 15},
+ {Intrinsic::floor, MVT::v16f32, 15},
+ {Intrinsic::floor, MVT::nxv2f32, 15},
+ {Intrinsic::floor, MVT::nxv4f32, 15},
+ {Intrinsic::floor, MVT::nxv8f32, 15},
+ {Intrinsic::floor, MVT::nxv16f32, 15},
+ {Intrinsic::floor, MVT::v2f64, 15},
+ {Intrinsic::floor, MVT::v4f64, 15},
+ {Intrinsic::floor, MVT::v8f64, 15},
+ {Intrinsic::floor, MVT::v16f64, 15},
+ {Intrinsic::floor, MVT::nxv1f64, 15},
+ {Intrinsic::floor, MVT::nxv2f64, 15},
+ {Intrinsic::floor, MVT::nxv4f64, 15},
+ {Intrinsic::floor, MVT::nxv8f64, 15},
+ {Intrinsic::ceil, MVT::v2f32, 15},
+ {Intrinsic::ceil, MVT::v4f32, 15},
+ {Intrinsic::ceil, MVT::v8f32, 15},
+ {Intrinsic::ceil, MVT::v16f32, 15},
+ {Intrinsic::ceil, MVT::nxv2f32, 15},
+ {Intrinsic::ceil, MVT::nxv4f32, 15},
+ {Intrinsic::ceil, MVT::nxv8f32, 15},
+ {Intrinsic::ceil, MVT::nxv16f32, 15},
+ {Intrinsic::ceil, MVT::v2f64, 15},
+ {Intrinsic::ceil, MVT::v4f64, 15},
+ {Intrinsic::ceil, MVT::v8f64, 15},
+ {Intrinsic::ceil, MVT::v16f64, 15},
+ {Intrinsic::ceil, MVT::nxv1f64, 15},
+ {Intrinsic::ceil, MVT::nxv2f64, 15},
+ {Intrinsic::ceil, MVT::nxv4f64, 15},
+ {Intrinsic::ceil, MVT::nxv8f64, 15},
+ {Intrinsic::trunc, MVT::v2f32, 7},
+ {Intrinsic::trunc, MVT::v4f32, 7},
+ {Intrinsic::trunc, MVT::v8f32, 7},
+ {Intrinsic::trunc, MVT::v16f32, 7},
+ {Intrinsic::trunc, MVT::nxv2f32, 7},
+ {Intrinsic::trunc, MVT::nxv4f32, 7},
+ {Intrinsic::trunc, MVT::nxv8f32, 7},
+ {Intrinsic::trunc, MVT::nxv16f32, 7},
+ {Intrinsic::trunc, MVT::v2f64, 7},
+ {Intrinsic::trunc, MVT::v4f64, 7},
+ {Intrinsic::trunc, MVT::v8f64, 7},
+ {Intrinsic::trunc, MVT::v16f64, 7},
+ {Intrinsic::trunc, MVT::nxv1f64, 7},
+ {Intrinsic::trunc, MVT::nxv2f64, 7},
+ {Intrinsic::trunc, MVT::nxv4f64, 7},
+ {Intrinsic::trunc, MVT::nxv8f64, 7},
+ {Intrinsic::round, MVT::v2f32, 10},
+ {Intrinsic::round, MVT::v4f32, 10},
+ {Intrinsic::round, MVT::v8f32, 10},
+ {Intrinsic::round, MVT::v16f32, 10},
+ {Intrinsic::round, MVT::nxv2f32, 10},
+ {Intrinsic::round, MVT::nxv4f32, 10},
+ {Intrinsic::round, MVT::nxv8f32, 10},
+ {Intrinsic::round, MVT::nxv16f32, 10},
+ {Intrinsic::round, MVT::v2f64, 10},
+ {Intrinsic::round, MVT::v4f64, 10},
+ {Intrinsic::round, MVT::v8f64, 10},
+ {Intrinsic::round, MVT::v16f64, 10},
+ {Intrinsic::round, MVT::nxv1f64, 10},
+ {Intrinsic::round, MVT::nxv2f64, 10},
+ {Intrinsic::round, MVT::nxv4f64, 10},
+ {Intrinsic::round, MVT::nxv8f64, 10},
+};
+
InstructionCost
RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
TTI::TargetCostKind CostKind) {
@@ -262,6 +334,12 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
return Cost + (LT.first - 1);
}
default:
+ if (ST->hasVInstructions() && RetTy->isVectorTy()) {
+ auto LT = getTypeLegalizationCost(RetTy);
+ if (const auto *Entry = CostTableLookup(VectorIntrinsicCostTable,
+ ICA.getID(), LT.second))
+ return LT.first * Entry->Cost;
+ }
break;
}
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
diff --git a/llvm/test/Analysis/CostModel/RISCV/fround.ll b/llvm/test/Analysis/CostModel/RISCV/fround.ll
index 1138702405093..f19b2fd964080 100644
--- a/llvm/test/Analysis/CostModel/RISCV/fround.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/fround.ll
@@ -4,23 +4,23 @@
define void @floor() {
; CHECK-LABEL: 'floor'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.floor.f32(float undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.floor.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %2 = call <2 x float> @llvm.floor.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %3 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %4 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %5 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %6 = call <vscale x 2 x float> @llvm.floor.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %7 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %8 = call <vscale x 8 x float> @llvm.floor.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %9 = call <vscale x 16 x float> @llvm.floor.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.floor.f64(double undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %11 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %12 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %13 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %14 = call <16 x double> @llvm.floor.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %15 = call <vscale x 1 x double> @llvm.floor.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %16 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %17 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %18 = call <vscale x 8 x double> @llvm.floor.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call float @llvm.floor.f32(float undef)
@@ -47,23 +47,23 @@ define void @floor() {
define void @ceil() {
; CHECK-LABEL: 'ceil'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.ceil.f32(float undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.ceil.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %2 = call <2 x float> @llvm.ceil.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %3 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %4 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %5 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %6 = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %7 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %8 = call <vscale x 8 x float> @llvm.ceil.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %9 = call <vscale x 16 x float> @llvm.ceil.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.ceil.f64(double undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %11 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %12 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %13 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %14 = call <16 x double> @llvm.ceil.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %15 = call <vscale x 1 x double> @llvm.ceil.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %16 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %17 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %18 = call <vscale x 8 x double> @llvm.ceil.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call float @llvm.ceil.f32(float undef)
@@ -90,23 +90,23 @@ define void @ceil() {
define void @trunc() {
; CHECK-LABEL: 'trunc'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.trunc.f32(float undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.trunc.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %2 = call <2 x float> @llvm.trunc.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %3 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %4 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %5 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x float> @llvm.trunc.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x float> @llvm.trunc.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x float> @llvm.trunc.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.trunc.f64(double undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %11 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %12 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %13 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %14 = call <16 x double> @llvm.trunc.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %15 = call <vscale x 1 x double> @llvm.trunc.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 8 x double> @llvm.trunc.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call float @llvm.trunc.f32(float undef)
@@ -219,23 +219,23 @@ define void @nearbyint() {
define void @round() {
; CHECK-LABEL: 'round'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %1 = call float @llvm.round.f32(float undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %2 = call <2 x float> @llvm.round.v2f32(<2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %3 = call <4 x float> @llvm.round.v4f32(<4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %4 = call <8 x float> @llvm.round.v8f32(<8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %5 = call <16 x float> @llvm.round.v16f32(<16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %6 = call <vscale x 2 x float> @llvm.round.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %7 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %8 = call <vscale x 8 x float> @llvm.round.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %9 = call <vscale x 16 x float> @llvm.round.nxv16f32(<vscale x 16 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %10 = call double @llvm.round.f64(double undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %16 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %11 = call <2 x double> @llvm.round.v2f64(<2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %12 = call <4 x double> @llvm.round.v4f64(<4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %13 = call <8 x double> @llvm.round.v8f64(<8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %14 = call <16 x double> @llvm.round.v16f64(<16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %15 = call <vscale x 1 x double> @llvm.round.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %16 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %17 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %18 = call <vscale x 8 x double> @llvm.round.nxv8f64(<vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
;
call float @llvm.round.f32(float undef)
More information about the llvm-commits
mailing list