[llvm] [RISCV][TTI] Add instruction cost for vp.load/store. (PR #109245)
Elvis Wang via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 18 23:40:01 PDT 2024
https://github.com/ElvisWang123 created https://github.com/llvm/llvm-project/pull/109245
This patch makes the instruction cost of vp.load/store same as their non-vp counterpart.
>From eda981517c628e4b345abc4a876e4ac4289a77e4 Mon Sep 17 00:00:00 2001
From: Elvis Wang <elvis.wang at sifive.com>
Date: Wed, 18 Sep 2024 23:34:47 -0700
Subject: [PATCH] [RISCV][TTI] Add instruction cost for vp.load/store.
This patch makes the instruction cost of vp.load/store same as their
non-vp counterpart.
---
.../Target/RISCV/RISCVTargetTransformInfo.cpp | 18 ++++++
.../CostModel/RISCV/rvv-intrinsics.ll | 64 +++++++++----------
2 files changed, 50 insertions(+), 32 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 5d280b44630aef..2c4aad68e1abd0 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1048,6 +1048,24 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
return getCmpSelInstrCost(*FOp, ICA.getArgTypes()[0], ICA.getReturnType(),
UI->getPredicate(), CostKind);
}
+ // vp load/store
+ case Intrinsic::vp_load:
+ case Intrinsic::vp_store: {
+ Intrinsic::ID IID = ICA.getID();
+ std::optional<unsigned> FOp = VPIntrinsic::getFunctionalOpcodeForVP(IID);
+ auto *UI = dyn_cast<VPIntrinsic>(ICA.getInst());
+
+ if (!UI)
+ break;
+ assert(FOp.has_value());
+ if (ICA.getID() == Intrinsic::vp_load)
+ return getMemoryOpCost(
+ *FOp, ICA.getReturnType(), UI->getPointerAlignment(),
+ UI->getOperand(0)->getType()->getPointerAddressSpace(), CostKind);
+ return getMemoryOpCost(
+ *FOp, ICA.getArgTypes()[0], UI->getPointerAlignment(),
+ UI->getOperand(1)->getType()->getPointerAddressSpace(), CostKind);
+ }
}
if (ST->hasVInstructions() && RetTy->isVectorTy()) {
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index 40aad95e715afd..6fe65d97d7448f 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -852,37 +852,37 @@ define void @load() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'load'
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %t0 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr undef, <2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t1 = load <2 x i8>, ptr undef, align 2
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %t2 = call <4 x i8> @llvm.vp.load.v4i8.p0(ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.load.v4i8.p0(ptr undef, <4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t3 = load <4 x i8>, ptr undef, align 4
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %t4 = call <8 x i8> @llvm.vp.load.v8i8.p0(ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.load.v8i8.p0(ptr undef, <8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t5 = load <8 x i8>, ptr undef, align 8
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 110 for instruction: %t6 = call <16 x i8> @llvm.vp.load.v16i8.p0(ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.load.v16i8.p0(ptr undef, <16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t7 = load <16 x i8>, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %t8 = call <2 x i64> @llvm.vp.load.v2i64.p0(ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i64> @llvm.vp.load.v2i64.p0(ptr undef, <2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t9 = load <2 x i64>, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %t10 = call <4 x i64> @llvm.vp.load.v4i64.p0(ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x i64> @llvm.vp.load.v4i64.p0(ptr undef, <4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t12 = load <4 x i64>, ptr undef, align 32
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 54 for instruction: %t13 = call <8 x i64> @llvm.vp.load.v8i64.p0(ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t13 = call <8 x i64> @llvm.vp.load.v8i64.p0(ptr undef, <8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t14 = load <8 x i64>, ptr undef, align 64
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 110 for instruction: %t15 = call <16 x i64> @llvm.vp.load.v16i64.p0(ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t15 = call <16 x i64> @llvm.vp.load.v16i64.p0(ptr undef, <16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t16 = load <16 x i64>, ptr undef, align 128
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t18 = load <vscale x 2 x i8>, ptr undef, align 2
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t20 = load <vscale x 4 x i8>, ptr undef, align 4
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %t22 = load <vscale x 8 x i8>, ptr undef, align 8
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t24 = load <vscale x 16 x i8>, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t26 = load <vscale x 2 x i64>, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %t28 = load <vscale x 4 x i64>, ptr undef, align 32
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %t30 = load <vscale x 8 x i64>, ptr undef, align 64
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.load.nxv16i64.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.load.nxv16i64.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %t32 = load <vscale x 16 x i64>, ptr undef, align 128
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
@@ -958,37 +958,37 @@ define void @store() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; TYPEBASED-LABEL: 'store'
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr undef, align 2
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.vp.store.v4i8.p0(<4 x i8> undef, ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v4i8.p0(<4 x i8> undef, ptr undef, <4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr undef, align 4
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.vp.store.v8i8.p0(<8 x i8> undef, ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v8i8.p0(<8 x i8> undef, ptr undef, <8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr undef, align 8
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.vp.store.v16i8.p0(<16 x i8> undef, ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v16i8.p0(<16 x i8> undef, ptr undef, <16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i64.p0(<2 x i64> undef, ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.v2i64.p0(<2 x i64> undef, ptr undef, <2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.vp.store.v4i64.p0(<4 x i64> undef, ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.v4i64.p0(<4 x i64> undef, ptr undef, <4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr undef, align 32
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.vp.store.v8i64.p0(<8 x i64> undef, ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.vp.store.v8i64.p0(<8 x i64> undef, ptr undef, <8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr undef, align 64
-; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.vp.store.v16i64.p0(<16 x i64> undef, ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.vp.store.v16i64.p0(<16 x i64> undef, ptr undef, <16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr undef, align 128
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr undef, align 2
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr undef, align 4
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr undef, align 8
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i8> undef, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 2 x i64> undef, ptr undef, align 16
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 4 x i64> undef, ptr undef, align 32
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 8 x i64> undef, ptr undef, align 64
-; TYPEBASED-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv16i64.p0(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.vp.store.nxv16i64.p0(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x i64> undef, ptr undef, align 128
; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
More information about the llvm-commits
mailing list