[llvm] 15fadeb - [RISCV] Add cost for @llvm.experimental.vp.splat (#117313)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 25 02:28:50 PST 2024
Author: Luke Lau
Date: 2024-11-25T11:28:46+01:00
New Revision: 15fadeb2aa8b9f27a5a45f15832e73ef79cfe407
URL: https://github.com/llvm/llvm-project/commit/15fadeb2aa8b9f27a5a45f15832e73ef79cfe407
DIFF: https://github.com/llvm/llvm-project/commit/15fadeb2aa8b9f27a5a45f15832e73ef79cfe407.diff
LOG: [RISCV] Add cost for @llvm.experimental.vp.splat (#117313)
This is split off from #115274. There doesn't seem to be an easy way to
share this with getShuffleCost since that requires passing in a real
insert_element operand to get it to recognise it's a scalar splat.
For i1 vectors we can't currently lower them so it returns an invalid
cost.
---------
Co-authored-by: Shih-Po Hung <shihpo.hung at sifive.com>
Added:
Modified:
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 76671641c2cdca..017264fbd46e01 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1159,6 +1159,16 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
return getCmpSelInstrCost(Instruction::Select, ICA.getReturnType(),
ICA.getArgTypes()[0], CmpInst::BAD_ICMP_PREDICATE,
CostKind);
+ case Intrinsic::experimental_vp_splat: {
+ auto LT = getTypeLegalizationCost(RetTy);
+ // TODO: Lower i1 experimental_vp_splat
+ if (!ST->hasVInstructions() || LT.second.getScalarType() == MVT::i1)
+ return InstructionCost::getInvalid();
+ return LT.first * getRISCVInstructionCost(LT.second.isFloatingPoint()
+ ? RISCV::VFMV_V_F
+ : RISCV::VMV_V_X,
+ LT.second, CostKind);
+ }
case Intrinsic::vp_reduce_add:
case Intrinsic::vp_reduce_fadd:
case Intrinsic::vp_reduce_mul:
diff --git a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
index 3fc08a0149e059..c7cd845a0a03f8 100644
--- a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v | FileCheck %s
-; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v --type-based-intrinsic-cost=true | FileCheck %s --check-prefixes=TYPEBASED
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+zvfhmin,+zvfbfmin | FileCheck %s
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+zvfhmin,+zvfbfmin --type-based-intrinsic-cost=true | FileCheck %s --check-prefixes=TYPEBASED
define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
; CHECK-LABEL: 'unsupported_fp_ops'
@@ -2125,6 +2125,232 @@ define void @vp_fdiv(){
ret void
}
+define void @splat() {
+; CHECK-LABEL: 'splat'
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %1 = call <2 x i1> @llvm.experimental.vp.splat.v2i1(i1 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %2 = call <4 x i1> @llvm.experimental.vp.splat.v4i1(i1 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %3 = call <8 x i1> @llvm.experimental.vp.splat.v8i1(i1 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %4 = call <16 x i1> @llvm.experimental.vp.splat.v16i1(i1 undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <2 x i8> @llvm.experimental.vp.splat.v2i8(i8 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <4 x i8> @llvm.experimental.vp.splat.v4i8(i8 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <8 x i8> @llvm.experimental.vp.splat.v8i8(i8 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <16 x i8> @llvm.experimental.vp.splat.v16i8(i8 undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <2 x i16> @llvm.experimental.vp.splat.v2i16(i16 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <4 x i16> @llvm.experimental.vp.splat.v4i16(i16 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <8 x i16> @llvm.experimental.vp.splat.v8i16(i16 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <16 x i16> @llvm.experimental.vp.splat.v16i16(i16 undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <2 x i32> @llvm.experimental.vp.splat.v2i32(i32 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <4 x i32> @llvm.experimental.vp.splat.v4i32(i32 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <8 x i32> @llvm.experimental.vp.splat.v8i32(i32 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %16 = call <16 x i32> @llvm.experimental.vp.splat.v16i32(i32 undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <2 x i64> @llvm.experimental.vp.splat.v2i64(i64 undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <4 x i64> @llvm.experimental.vp.splat.v4i64(i64 undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %19 = call <8 x i64> @llvm.experimental.vp.splat.v8i64(i64 undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <16 x i64> @llvm.experimental.vp.splat.v16i64(i64 undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x bfloat> @llvm.experimental.vp.splat.v2bf16(bfloat undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x bfloat> @llvm.experimental.vp.splat.v4bf16(bfloat undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x bfloat> @llvm.experimental.vp.splat.v8bf16(bfloat undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <16 x bfloat> @llvm.experimental.vp.splat.v16bf16(bfloat undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <2 x half> @llvm.experimental.vp.splat.v2f16(half undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <4 x half> @llvm.experimental.vp.splat.v4f16(half undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <8 x half> @llvm.experimental.vp.splat.v8f16(half undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <16 x half> @llvm.experimental.vp.splat.v16f16(half undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x float> @llvm.experimental.vp.splat.v2f32(float undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x float> @llvm.experimental.vp.splat.v4f32(float undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call <8 x float> @llvm.experimental.vp.splat.v8f32(float undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %32 = call <16 x float> @llvm.experimental.vp.splat.v16f32(float undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <2 x double> @llvm.experimental.vp.splat.v2f64(double undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <4 x double> @llvm.experimental.vp.splat.v4f64(double undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %35 = call <8 x double> @llvm.experimental.vp.splat.v8f64(double undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %36 = call <16 x double> @llvm.experimental.vp.splat.v16f64(double undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %37 = call <vscale x 2 x i1> @llvm.experimental.vp.splat.nxv2i1(i1 undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %38 = call <vscale x 4 x i1> @llvm.experimental.vp.splat.nxv4i1(i1 undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %39 = call <vscale x 8 x i1> @llvm.experimental.vp.splat.nxv8i1(i1 undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %40 = call <vscale x 16 x i1> @llvm.experimental.vp.splat.nxv16i1(i1 undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = call <vscale x 2 x i8> @llvm.experimental.vp.splat.nxv2i8(i8 undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %42 = call <vscale x 4 x i8> @llvm.experimental.vp.splat.nxv4i8(i8 undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %43 = call <vscale x 8 x i8> @llvm.experimental.vp.splat.nxv8i8(i8 undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %44 = call <vscale x 16 x i8> @llvm.experimental.vp.splat.nxv16i8(i8 undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = call <vscale x 2 x i16> @llvm.experimental.vp.splat.nxv2i16(i16 undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = call <vscale x 4 x i16> @llvm.experimental.vp.splat.nxv4i16(i16 undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %47 = call <vscale x 8 x i16> @llvm.experimental.vp.splat.nxv8i16(i16 undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %48 = call <vscale x 16 x i16> @llvm.experimental.vp.splat.nxv16i16(i16 undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %49 = call <vscale x 2 x i32> @llvm.experimental.vp.splat.nxv2i32(i32 undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %50 = call <vscale x 4 x i32> @llvm.experimental.vp.splat.nxv4i32(i32 undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %51 = call <vscale x 8 x i32> @llvm.experimental.vp.splat.nxv8i32(i32 undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %52 = call <vscale x 16 x i32> @llvm.experimental.vp.splat.nxv16i32(i32 undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %53 = call <vscale x 2 x i64> @llvm.experimental.vp.splat.nxv2i64(i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %54 = call <vscale x 4 x i64> @llvm.experimental.vp.splat.nxv4i64(i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %55 = call <vscale x 8 x i64> @llvm.experimental.vp.splat.nxv8i64(i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %56 = call <vscale x 16 x i64> @llvm.experimental.vp.splat.nxv16i64(i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %57 = call <vscale x 2 x bfloat> @llvm.experimental.vp.splat.nxv2bf16(bfloat undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %58 = call <vscale x 4 x bfloat> @llvm.experimental.vp.splat.nxv4bf16(bfloat undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %59 = call <vscale x 8 x bfloat> @llvm.experimental.vp.splat.nxv8bf16(bfloat undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %60 = call <vscale x 16 x bfloat> @llvm.experimental.vp.splat.nxv16bf16(bfloat undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %61 = call <vscale x 2 x half> @llvm.experimental.vp.splat.nxv2f16(half undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %62 = call <vscale x 4 x half> @llvm.experimental.vp.splat.nxv4f16(half undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %63 = call <vscale x 8 x half> @llvm.experimental.vp.splat.nxv8f16(half undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %64 = call <vscale x 16 x half> @llvm.experimental.vp.splat.nxv16f16(half undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %65 = call <vscale x 2 x float> @llvm.experimental.vp.splat.nxv2f32(float undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %66 = call <vscale x 4 x float> @llvm.experimental.vp.splat.nxv4f32(float undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %67 = call <vscale x 8 x float> @llvm.experimental.vp.splat.nxv8f32(float undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %68 = call <vscale x 16 x float> @llvm.experimental.vp.splat.nxv16f32(float undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %69 = call <vscale x 2 x double> @llvm.experimental.vp.splat.nxv2f64(double undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %70 = call <vscale x 4 x double> @llvm.experimental.vp.splat.nxv4f64(double undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %71 = call <vscale x 8 x double> @llvm.experimental.vp.splat.nxv8f64(double undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %72 = call <vscale x 16 x double> @llvm.experimental.vp.splat.nxv16f64(double undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'splat'
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %1 = call <2 x i1> @llvm.experimental.vp.splat.v2i1(i1 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %2 = call <4 x i1> @llvm.experimental.vp.splat.v4i1(i1 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %3 = call <8 x i1> @llvm.experimental.vp.splat.v8i1(i1 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %4 = call <16 x i1> @llvm.experimental.vp.splat.v16i1(i1 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <2 x i8> @llvm.experimental.vp.splat.v2i8(i8 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <4 x i8> @llvm.experimental.vp.splat.v4i8(i8 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <8 x i8> @llvm.experimental.vp.splat.v8i8(i8 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <16 x i8> @llvm.experimental.vp.splat.v16i8(i8 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <2 x i16> @llvm.experimental.vp.splat.v2i16(i16 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <4 x i16> @llvm.experimental.vp.splat.v4i16(i16 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <8 x i16> @llvm.experimental.vp.splat.v8i16(i16 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <16 x i16> @llvm.experimental.vp.splat.v16i16(i16 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <2 x i32> @llvm.experimental.vp.splat.v2i32(i32 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <4 x i32> @llvm.experimental.vp.splat.v4i32(i32 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <8 x i32> @llvm.experimental.vp.splat.v8i32(i32 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %16 = call <16 x i32> @llvm.experimental.vp.splat.v16i32(i32 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <2 x i64> @llvm.experimental.vp.splat.v2i64(i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %18 = call <4 x i64> @llvm.experimental.vp.splat.v4i64(i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %19 = call <8 x i64> @llvm.experimental.vp.splat.v8i64(i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <16 x i64> @llvm.experimental.vp.splat.v16i64(i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <2 x bfloat> @llvm.experimental.vp.splat.v2bf16(bfloat undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <4 x bfloat> @llvm.experimental.vp.splat.v4bf16(bfloat undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <8 x bfloat> @llvm.experimental.vp.splat.v8bf16(bfloat undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %24 = call <16 x bfloat> @llvm.experimental.vp.splat.v16bf16(bfloat undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <2 x half> @llvm.experimental.vp.splat.v2f16(half undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <4 x half> @llvm.experimental.vp.splat.v4f16(half undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <8 x half> @llvm.experimental.vp.splat.v8f16(half undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %28 = call <16 x half> @llvm.experimental.vp.splat.v16f16(half undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <2 x float> @llvm.experimental.vp.splat.v2f32(float undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <4 x float> @llvm.experimental.vp.splat.v4f32(float undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call <8 x float> @llvm.experimental.vp.splat.v8f32(float undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %32 = call <16 x float> @llvm.experimental.vp.splat.v16f32(float undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <2 x double> @llvm.experimental.vp.splat.v2f64(double undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %34 = call <4 x double> @llvm.experimental.vp.splat.v4f64(double undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %35 = call <8 x double> @llvm.experimental.vp.splat.v8f64(double undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %36 = call <16 x double> @llvm.experimental.vp.splat.v16f64(double undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %37 = call <vscale x 2 x i1> @llvm.experimental.vp.splat.nxv2i1(i1 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %38 = call <vscale x 4 x i1> @llvm.experimental.vp.splat.nxv4i1(i1 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %39 = call <vscale x 8 x i1> @llvm.experimental.vp.splat.nxv8i1(i1 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %40 = call <vscale x 16 x i1> @llvm.experimental.vp.splat.nxv16i1(i1 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %41 = call <vscale x 2 x i8> @llvm.experimental.vp.splat.nxv2i8(i8 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %42 = call <vscale x 4 x i8> @llvm.experimental.vp.splat.nxv4i8(i8 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %43 = call <vscale x 8 x i8> @llvm.experimental.vp.splat.nxv8i8(i8 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %44 = call <vscale x 16 x i8> @llvm.experimental.vp.splat.nxv16i8(i8 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %45 = call <vscale x 2 x i16> @llvm.experimental.vp.splat.nxv2i16(i16 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %46 = call <vscale x 4 x i16> @llvm.experimental.vp.splat.nxv4i16(i16 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %47 = call <vscale x 8 x i16> @llvm.experimental.vp.splat.nxv8i16(i16 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %48 = call <vscale x 16 x i16> @llvm.experimental.vp.splat.nxv16i16(i16 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %49 = call <vscale x 2 x i32> @llvm.experimental.vp.splat.nxv2i32(i32 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %50 = call <vscale x 4 x i32> @llvm.experimental.vp.splat.nxv4i32(i32 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %51 = call <vscale x 8 x i32> @llvm.experimental.vp.splat.nxv8i32(i32 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %52 = call <vscale x 16 x i32> @llvm.experimental.vp.splat.nxv16i32(i32 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %53 = call <vscale x 2 x i64> @llvm.experimental.vp.splat.nxv2i64(i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %54 = call <vscale x 4 x i64> @llvm.experimental.vp.splat.nxv4i64(i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %55 = call <vscale x 8 x i64> @llvm.experimental.vp.splat.nxv8i64(i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %56 = call <vscale x 16 x i64> @llvm.experimental.vp.splat.nxv16i64(i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %57 = call <vscale x 2 x bfloat> @llvm.experimental.vp.splat.nxv2bf16(bfloat undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %58 = call <vscale x 4 x bfloat> @llvm.experimental.vp.splat.nxv4bf16(bfloat undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %59 = call <vscale x 8 x bfloat> @llvm.experimental.vp.splat.nxv8bf16(bfloat undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %60 = call <vscale x 16 x bfloat> @llvm.experimental.vp.splat.nxv16bf16(bfloat undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %61 = call <vscale x 2 x half> @llvm.experimental.vp.splat.nxv2f16(half undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %62 = call <vscale x 4 x half> @llvm.experimental.vp.splat.nxv4f16(half undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %63 = call <vscale x 8 x half> @llvm.experimental.vp.splat.nxv8f16(half undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %64 = call <vscale x 16 x half> @llvm.experimental.vp.splat.nxv16f16(half undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %65 = call <vscale x 2 x float> @llvm.experimental.vp.splat.nxv2f32(float undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %66 = call <vscale x 4 x float> @llvm.experimental.vp.splat.nxv4f32(float undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %67 = call <vscale x 8 x float> @llvm.experimental.vp.splat.nxv8f32(float undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %68 = call <vscale x 16 x float> @llvm.experimental.vp.splat.nxv16f32(float undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %69 = call <vscale x 2 x double> @llvm.experimental.vp.splat.nxv2f64(double undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %70 = call <vscale x 4 x double> @llvm.experimental.vp.splat.nxv4f64(double undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %71 = call <vscale x 8 x double> @llvm.experimental.vp.splat.nxv8f64(double undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %72 = call <vscale x 16 x double> @llvm.experimental.vp.splat.nxv16f64(double undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+ call <2 x i1> @llvm.experimental.vp.splat.v2i1(i1 undef, <2 x i1> undef, i32 undef)
+ call <4 x i1> @llvm.experimental.vp.splat.v4i1(i1 undef, <4 x i1> undef, i32 undef)
+ call <8 x i1> @llvm.experimental.vp.splat.v8i1(i1 undef, <8 x i1> undef, i32 undef)
+ call <16 x i1> @llvm.experimental.vp.splat.v16i1(i1 undef, <16 x i1> undef, i32 undef)
+ call <2 x i8> @llvm.experimental.vp.splat.v2i8(i8 undef, <2 x i1> undef, i32 undef)
+ call <4 x i8> @llvm.experimental.vp.splat.v4i8(i8 undef, <4 x i1> undef, i32 undef)
+ call <8 x i8> @llvm.experimental.vp.splat.v8i8(i8 undef, <8 x i1> undef, i32 undef)
+ call <16 x i8> @llvm.experimental.vp.splat.v16i8(i8 undef, <16 x i1> undef, i32 undef)
+ call <2 x i16> @llvm.experimental.vp.splat.v2i16(i16 undef, <2 x i1> undef, i32 undef)
+ call <4 x i16> @llvm.experimental.vp.splat.v4i16(i16 undef, <4 x i1> undef, i32 undef)
+ call <8 x i16> @llvm.experimental.vp.splat.v8i16(i16 undef, <8 x i1> undef, i32 undef)
+ call <16 x i16> @llvm.experimental.vp.splat.v16i16(i16 undef, <16 x i1> undef, i32 undef)
+ call <2 x i32> @llvm.experimental.vp.splat.v2i32(i32 undef, <2 x i1> undef, i32 undef)
+ call <4 x i32> @llvm.experimental.vp.splat.v4i32(i32 undef, <4 x i1> undef, i32 undef)
+ call <8 x i32> @llvm.experimental.vp.splat.v8i32(i32 undef, <8 x i1> undef, i32 undef)
+ call <16 x i32> @llvm.experimental.vp.splat.v16i32(i32 undef, <16 x i1> undef, i32 undef)
+ call <2 x i64> @llvm.experimental.vp.splat.v2i64(i64 undef, <2 x i1> undef, i32 undef)
+ call <4 x i64> @llvm.experimental.vp.splat.v4i64(i64 undef, <4 x i1> undef, i32 undef)
+ call <8 x i64> @llvm.experimental.vp.splat.v8i64(i64 undef, <8 x i1> undef, i32 undef)
+ call <16 x i64> @llvm.experimental.vp.splat.v16i64(i64 undef, <16 x i1> undef, i32 undef)
+ call <2 x bfloat> @llvm.experimental.vp.splat.v2bf16(bfloat undef, <2 x i1> undef, i32 undef)
+ call <4 x bfloat> @llvm.experimental.vp.splat.v4bf16(bfloat undef, <4 x i1> undef, i32 undef)
+ call <8 x bfloat> @llvm.experimental.vp.splat.v8bf16(bfloat undef, <8 x i1> undef, i32 undef)
+ call <16 x bfloat> @llvm.experimental.vp.splat.v16bf16(bfloat undef, <16 x i1> undef, i32 undef)
+ call <2 x half> @llvm.experimental.vp.splat.v2f16(half undef, <2 x i1> undef, i32 undef)
+ call <4 x half> @llvm.experimental.vp.splat.v4f16(half undef, <4 x i1> undef, i32 undef)
+ call <8 x half> @llvm.experimental.vp.splat.v8f16(half undef, <8 x i1> undef, i32 undef)
+ call <16 x half> @llvm.experimental.vp.splat.v16f16(half undef, <16 x i1> undef, i32 undef)
+ call <2 x float> @llvm.experimental.vp.splat.v2f32(float undef, <2 x i1> undef, i32 undef)
+ call <4 x float> @llvm.experimental.vp.splat.v4f32(float undef, <4 x i1> undef, i32 undef)
+ call <8 x float> @llvm.experimental.vp.splat.v8f32(float undef, <8 x i1> undef, i32 undef)
+ call <16 x float> @llvm.experimental.vp.splat.v16f32(float undef, <16 x i1> undef, i32 undef)
+ call <2 x double> @llvm.experimental.vp.splat.v2f64(double undef, <2 x i1> undef, i32 undef)
+ call <4 x double> @llvm.experimental.vp.splat.v4f64(double undef, <4 x i1> undef, i32 undef)
+ call <8 x double> @llvm.experimental.vp.splat.v8f64(double undef, <8 x i1> undef, i32 undef)
+ call <16 x double> @llvm.experimental.vp.splat.v16f64(double undef, <16 x i1> undef, i32 undef)
+ call <vscale x 2 x i1> @llvm.experimental.vp.splat.nxv2i1(i1 undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x i1> @llvm.experimental.vp.splat.nxv4i1(i1 undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x i1> @llvm.experimental.vp.splat.nxv8i1(i1 undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x i1> @llvm.experimental.vp.splat.nxv16i1(i1 undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x i8> @llvm.experimental.vp.splat.nxv2i8(i8 undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x i8> @llvm.experimental.vp.splat.nxv4i8(i8 undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x i8> @llvm.experimental.vp.splat.nxv8i8(i8 undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x i8> @llvm.experimental.vp.splat.nxv16i8(i8 undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x i16> @llvm.experimental.vp.splat.nxv2i16(i16 undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x i16> @llvm.experimental.vp.splat.nxv4i16(i16 undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x i16> @llvm.experimental.vp.splat.nxv8i16(i16 undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x i16> @llvm.experimental.vp.splat.nxv16i16(i16 undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x i32> @llvm.experimental.vp.splat.nxv2i32(i32 undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x i32> @llvm.experimental.vp.splat.nxv4i32(i32 undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x i32> @llvm.experimental.vp.splat.nxv8i32(i32 undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x i32> @llvm.experimental.vp.splat.nxv16i32(i32 undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x i64> @llvm.experimental.vp.splat.nxv2i64(i64 undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x i64> @llvm.experimental.vp.splat.nxv4i64(i64 undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x i64> @llvm.experimental.vp.splat.nxv8i64(i64 undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x i64> @llvm.experimental.vp.splat.nxv16i64(i64 undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x bfloat> @llvm.experimental.vp.splat.nxv2bf16(bfloat undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x bfloat> @llvm.experimental.vp.splat.nxv4bf16(bfloat undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x bfloat> @llvm.experimental.vp.splat.nxv8bf16(bfloat undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x bfloat> @llvm.experimental.vp.splat.nxv16bf16(bfloat undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x half> @llvm.experimental.vp.splat.nxv2f16(half undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x half> @llvm.experimental.vp.splat.nxv4f16(half undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x half> @llvm.experimental.vp.splat.nxv8f16(half undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x half> @llvm.experimental.vp.splat.nxv16f16(half undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x float> @llvm.experimental.vp.splat.nxv2f32(float undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x float> @llvm.experimental.vp.splat.nxv4f32(float undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x float> @llvm.experimental.vp.splat.nxv8f32(float undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x float> @llvm.experimental.vp.splat.nxv16f32(float undef, <vscale x 16 x i1> undef, i32 undef)
+ call <vscale x 2 x double> @llvm.experimental.vp.splat.nxv2f64(double undef, <vscale x 2 x i1> undef, i32 undef)
+ call <vscale x 4 x double> @llvm.experimental.vp.splat.nxv4f64(double undef, <vscale x 4 x i1> undef, i32 undef)
+ call <vscale x 8 x double> @llvm.experimental.vp.splat.nxv8f64(double undef, <vscale x 8 x i1> undef, i32 undef)
+ call <vscale x 16 x double> @llvm.experimental.vp.splat.nxv16f64(double undef, <vscale x 16 x i1> undef, i32 undef)
+ ret void
+}
+
declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)
declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)
More information about the llvm-commits
mailing list