[llvm] [RISCV][TTI] Scale the cost of intrinsic stepvector with LMUL (PR #87301)
Shih-Po Hung via llvm-commits
llvm-commits at lists.llvm.org
Tue Apr 2 00:56:51 PDT 2024
https://github.com/arcbbb updated https://github.com/llvm/llvm-project/pull/87301
>From 0700688d16a4498ba59777c4eb25d227a3e048dc Mon Sep 17 00:00:00 2001
From: ShihPo Hung <shihpo.hung at sifive.com>
Date: Mon, 1 Apr 2024 18:40:22 -0700
Subject: [PATCH 1/2] [RISCV][TTI] Scale the cost of intrinsic stepvector with
LMUL
Use the destination data type to measure the LMUL size for latency/throughput cost
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 12 ++--
.../Analysis/CostModel/RISCV/stepvector.ll | 62 +++++++++----------
2 files changed, 38 insertions(+), 36 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 38304ff90252f0..424e79ef26a83d 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -860,11 +860,13 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
break;
}
// TODO: add more intrinsic
- case Intrinsic::experimental_stepvector: {
- unsigned Cost = 1; // vid
- auto LT = getTypeLegalizationCost(RetTy);
- return Cost + (LT.first - 1);
- }
+ case Intrinsic::experimental_stepvector:
+ if (ST->hasVInstructions()) {
+ auto LT = getTypeLegalizationCost(RetTy);
+ return LT.first *
+ getRISCVInstructionCost(RISCV::VID_V, LT.second, CostKind);
+ }
+ break;
case Intrinsic::vp_rint: {
// RISC-V target uses at least 5 instructions to lower rounding intrinsics.
unsigned Cost = 5;
diff --git a/llvm/test/Analysis/CostModel/RISCV/stepvector.ll b/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
index 7d29d2c0cfa628..c540208df6ff39 100644
--- a/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/stepvector.ll
@@ -12,43 +12,43 @@ define void @stepvector() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 16 x i8> @llvm.experimental.stepvector.nxv16i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 32 x i8> @llvm.experimental.stepvector.nxv32i8()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %10 = call <vscale x 64 x i8> @llvm.experimental.stepvector.nxv64i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <vscale x 16 x i8> @llvm.experimental.stepvector.nxv16i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %9 = call <vscale x 32 x i8> @llvm.experimental.stepvector.nxv32i8()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %10 = call <vscale x 64 x i8> @llvm.experimental.stepvector.nxv64i8()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 1 x i16> @llvm.experimental.stepvector.nxv1i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <vscale x 2 x i16> @llvm.experimental.stepvector.nxv2i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <vscale x 4 x i16> @llvm.experimental.stepvector.nxv4i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 8 x i16> @llvm.experimental.stepvector.nxv8i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 32 x i16> @llvm.experimental.stepvector.nxv32i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <vscale x 8 x i16> @llvm.experimental.stepvector.nxv8i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %15 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %16 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %17 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %18 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %19 = call <vscale x 16 x i16> @llvm.experimental.stepvector.nxv16i16()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %20 = call <vscale x 32 x i16> @llvm.experimental.stepvector.nxv32i16()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 1 x i32> @llvm.experimental.stepvector.nxv1i32()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 2 x i32> @llvm.experimental.stepvector.nxv2i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 8 x i32> @llvm.experimental.stepvector.nxv8i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %24 = call <vscale x 8 x i32> @llvm.experimental.stepvector.nxv8i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %25 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %26 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %27 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %28 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %29 = call <vscale x 16 x i32> @llvm.experimental.stepvector.nxv16i32()
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %30 = call <vscale x 1 x i64> @llvm.experimental.stepvector.nxv1i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %31 = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %32 = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %33 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %34 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %35 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %36 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %37 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %38 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %39 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %40 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %41 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %42 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %43 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %44 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %31 = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %33 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %34 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %35 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %36 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %37 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %38 = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %39 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %40 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %41 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %42 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %43 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %44 = call <vscale x 16 x i64> @llvm.experimental.stepvector.nxv16i64()
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
%zero = call <vscale x 1 x i8> @llvm.experimental.stepvector.nxv1i8()
>From 34d79395887ba37998a1ca185868f1f7a73f7460 Mon Sep 17 00:00:00 2001
From: ShihPo Hung <shihpo.hung at sifive.com>
Date: Tue, 2 Apr 2024 00:51:40 -0700
Subject: [PATCH 2/2] keep scalar case when V is not supported
---
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 424e79ef26a83d..a03f1ac7056c3d 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -860,13 +860,13 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
break;
}
// TODO: add more intrinsic
- case Intrinsic::experimental_stepvector:
- if (ST->hasVInstructions()) {
- auto LT = getTypeLegalizationCost(RetTy);
+ case Intrinsic::experimental_stepvector: {
+ auto LT = getTypeLegalizationCost(RetTy);
+ if (ST->hasVInstructions())
return LT.first *
getRISCVInstructionCost(RISCV::VID_V, LT.second, CostKind);
- }
- break;
+ return 1 + (LT.first - 1);
+ }
case Intrinsic::vp_rint: {
// RISC-V target uses at least 5 instructions to lower rounding intrinsics.
unsigned Cost = 5;
More information about the llvm-commits
mailing list