[llvm] [RISCV] Add cost for @llvm.experimental.vp.splat (PR #117313)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 22 02:21:01 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Luke Lau (lukel97)
<details>
<summary>Changes</summary>
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.
There's no tests for i1 vectors, since we can't lower vp splats of them yet and currently crash.
---
Full diff: https://github.com/llvm/llvm-project/pull/117313.diff
2 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp (+5)
- (modified) llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll (+106)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 2b16dcbcd8695b..ecdecd7edff07c 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1155,6 +1155,11 @@ 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);
+ return LT.first *
+ getRISCVInstructionCost(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 800ea223850d31..a7ce6f660ca4af 100644
--- a/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/vp-intrinsics.ll
@@ -2125,6 +2125,112 @@ define void @vp_fdiv(){
ret void
}
+define void @splat() {
+; CHECK-LABEL: 'splat'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = 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: %2 = 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: %3 = 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: %4 = 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: %5 = 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: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = 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: %11 = 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: %12 = 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: %13 = 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: %14 = 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: %15 = 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: %16 = 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: %17 = 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: %18 = 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: %19 = 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: %20 = 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: %21 = 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: %22 = 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: %23 = 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: %24 = 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: %25 = 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: %26 = 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: %27 = 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: %28 = 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: %29 = 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: %30 = 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: %31 = 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: %32 = 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 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'splat'
+; TYPEBASED-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = 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: %2 = 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: %3 = 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: %4 = 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: %5 = 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: %6 = 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: %7 = 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: %8 = 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: %9 = 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: %10 = 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: %11 = 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: %12 = 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: %13 = 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: %14 = 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: %15 = 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: %16 = 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: %17 = 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: %18 = 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: %19 = 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: %20 = 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: %21 = 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: %22 = 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: %23 = 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: %24 = 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: %25 = 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: %26 = 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: %27 = 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: %28 = 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: %29 = 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: %30 = 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: %31 = 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: %32 = 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 0 for instruction: ret void
+;
+ 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 <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)
+ 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)
``````````
</details>
https://github.com/llvm/llvm-project/pull/117313
More information about the llvm-commits
mailing list