[llvm] [RISCV] Optimize vp.splice with 0 offset. (PR #145533)
Craig Topper via llvm-commits
llvm-commits at lists.llvm.org
Tue Jun 24 08:33:55 PDT 2025
https://github.com/topperc created https://github.com/llvm/llvm-project/pull/145533
We can skip the slidedown if the offset is 0.
>From 64f7544503c1b02ba50be61ee52736d08bb99eaf Mon Sep 17 00:00:00 2001
From: Craig Topper <craig.topper at sifive.com>
Date: Tue, 24 Jun 2025 08:32:03 -0700
Subject: [PATCH] [RISCV] Optimize vp.splice with 0 offset.
We can skip the slidedown if the offset is 0.
---
llvm/lib/Target/RISCV/RISCVISelLowering.cpp | 9 +++--
.../RISCV/rvv/fixed-vectors-vp-splice.ll | 11 ++++++
llvm/test/CodeGen/RISCV/rvv/vp-splice.ll | 38 ++++++++++++-------
3 files changed, 40 insertions(+), 18 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 13ee3ee63d1a6..3dc74ec802dbc 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -13297,10 +13297,11 @@ RISCVTargetLowering::lowerVPSpliceExperimental(SDValue Op,
DownOffset = DAG.getNode(ISD::SUB, DL, XLenVT, EVL1, UpOffset);
}
- SDValue SlideDown =
- getVSlidedown(DAG, Subtarget, DL, ContainerVT, DAG.getUNDEF(ContainerVT),
- Op1, DownOffset, Mask, UpOffset);
- SDValue Result = getVSlideup(DAG, Subtarget, DL, ContainerVT, SlideDown, Op2,
+ if (ImmValue != 0)
+ Op1 =
+ getVSlidedown(DAG, Subtarget, DL, ContainerVT, DAG.getUNDEF(ContainerVT),
+ Op1, DownOffset, Mask, UpOffset);
+ SDValue Result = getVSlideup(DAG, Subtarget, DL, ContainerVT, Op1, Op2,
UpOffset, Mask, EVL2, RISCVVType::TAIL_AGNOSTIC);
if (IsMaskVector) {
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-splice.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-splice.ll
index 7245d8a11f563..7bf22247093f7 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-splice.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vp-splice.ll
@@ -30,6 +30,17 @@ define <2 x i64> @test_vp_splice_v2i64_negative_offset(<2 x i64> %va, <2 x i64>
ret <2 x i64> %v
}
+define <2 x i64> @test_vp_splice_v2i64_zero_offset(<2 x i64> %va, <2 x i64> %vb, i32 zeroext %evla, i32 zeroext %evlb) {
+; CHECK-LABEL: test_vp_splice_v2i64_zero_offset:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v9, a0
+; CHECK-NEXT: ret
+
+ %v = call <2 x i64> @llvm.experimental.vp.splice.v2i64(<2 x i64> %va, <2 x i64> %vb, i32 0, <2 x i1> splat (i1 1), i32 %evla, i32 %evlb)
+ ret <2 x i64> %v
+}
+
define <2 x i64> @test_vp_splice_v2i64_masked(<2 x i64> %va, <2 x i64> %vb, <2 x i1> %mask, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_v2i64_masked:
; CHECK: # %bb.0:
diff --git a/llvm/test/CodeGen/RISCV/rvv/vp-splice.ll b/llvm/test/CodeGen/RISCV/rvv/vp-splice.ll
index ffeb493989103..2a59cf2c12f01 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vp-splice.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vp-splice.ll
@@ -40,6 +40,16 @@ define <vscale x 2 x i64> @test_vp_splice_nxv2i64_negative_offset(<vscale x 2 x
ret <vscale x 2 x i64> %v
}
+define <vscale x 2 x i64> @test_vp_splice_nxv2i64_zero_offset(<vscale x 2 x i64> %va, <vscale x 2 x i64> %vb, i32 zeroext %evla, i32 zeroext %evlb) {
+; CHECK-LABEL: test_vp_splice_nxv2i64_zero_offset:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli zero, a1, e64, m2, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v10, a0
+; CHECK-NEXT: ret
+ %v = call <vscale x 2 x i64> @llvm.experimental.vp.splice.nxv2i64(<vscale x 2 x i64> %va, <vscale x 2 x i64> %vb, i32 0, <vscale x 2 x i1> splat (i1 1), i32 %evla, i32 %evlb)
+ ret <vscale x 2 x i64> %v
+}
+
define <vscale x 2 x i64> @test_vp_splice_nxv2i64_masked(<vscale x 2 x i64> %va, <vscale x 2 x i64> %vb, <vscale x 2 x i1> %mask, i32 zeroext %evla, i32 zeroext %evlb) {
; CHECK-LABEL: test_vp_splice_nxv2i64_masked:
; CHECK: # %bb.0:
@@ -295,10 +305,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64(<vscale x 16 x i64> %va, <vs
; CHECK-NEXT: addi a5, a5, -1
; CHECK-NEXT: slli a1, a4, 3
; CHECK-NEXT: mv a7, a2
-; CHECK-NEXT: bltu a2, a5, .LBB21_2
+; CHECK-NEXT: bltu a2, a5, .LBB22_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a7, a5
-; CHECK-NEXT: .LBB21_2:
+; CHECK-NEXT: .LBB22_2:
; CHECK-NEXT: addi sp, sp, -80
; CHECK-NEXT: sd ra, 72(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 64(sp) # 8-byte Folded Spill
@@ -311,10 +321,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64(<vscale x 16 x i64> %va, <vs
; CHECK-NEXT: slli a7, a7, 3
; CHECK-NEXT: addi a6, sp, 64
; CHECK-NEXT: mv t0, a2
-; CHECK-NEXT: bltu a2, a4, .LBB21_4
+; CHECK-NEXT: bltu a2, a4, .LBB22_4
; CHECK-NEXT: # %bb.3:
; CHECK-NEXT: mv t0, a4
-; CHECK-NEXT: .LBB21_4:
+; CHECK-NEXT: .LBB22_4:
; CHECK-NEXT: vl8re64.v v24, (a5)
; CHECK-NEXT: add a5, a6, a7
; CHECK-NEXT: vl8re64.v v0, (a0)
@@ -328,10 +338,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64(<vscale x 16 x i64> %va, <vs
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vse64.v v16, (a6)
; CHECK-NEXT: mv a0, a3
-; CHECK-NEXT: bltu a3, a4, .LBB21_6
+; CHECK-NEXT: bltu a3, a4, .LBB22_6
; CHECK-NEXT: # %bb.5:
; CHECK-NEXT: mv a0, a4
-; CHECK-NEXT: .LBB21_6:
+; CHECK-NEXT: .LBB22_6:
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vse64.v v0, (a5)
; CHECK-NEXT: sub a2, a3, a4
@@ -363,10 +373,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64_negative_offset(<vscale x 16
; CHECK-NEXT: addi a6, a6, -1
; CHECK-NEXT: slli a1, a5, 3
; CHECK-NEXT: mv a4, a2
-; CHECK-NEXT: bltu a2, a6, .LBB22_2
+; CHECK-NEXT: bltu a2, a6, .LBB23_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a4, a6
-; CHECK-NEXT: .LBB22_2:
+; CHECK-NEXT: .LBB23_2:
; CHECK-NEXT: addi sp, sp, -80
; CHECK-NEXT: sd ra, 72(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 64(sp) # 8-byte Folded Spill
@@ -379,10 +389,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64_negative_offset(<vscale x 16
; CHECK-NEXT: slli a4, a4, 3
; CHECK-NEXT: addi a7, sp, 64
; CHECK-NEXT: mv t0, a2
-; CHECK-NEXT: bltu a2, a5, .LBB22_4
+; CHECK-NEXT: bltu a2, a5, .LBB23_4
; CHECK-NEXT: # %bb.3:
; CHECK-NEXT: mv t0, a5
-; CHECK-NEXT: .LBB22_4:
+; CHECK-NEXT: .LBB23_4:
; CHECK-NEXT: vl8re64.v v24, (a6)
; CHECK-NEXT: add a6, a7, a4
; CHECK-NEXT: vl8re64.v v0, (a0)
@@ -396,10 +406,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64_negative_offset(<vscale x 16
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vse64.v v16, (a7)
; CHECK-NEXT: mv a0, a3
-; CHECK-NEXT: bltu a3, a5, .LBB22_6
+; CHECK-NEXT: bltu a3, a5, .LBB23_6
; CHECK-NEXT: # %bb.5:
; CHECK-NEXT: mv a0, a5
-; CHECK-NEXT: .LBB22_6:
+; CHECK-NEXT: .LBB23_6:
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vse64.v v0, (a6)
; CHECK-NEXT: sub a2, a3, a5
@@ -410,10 +420,10 @@ define <vscale x 16 x i64> @test_vp_splice_nxv16i64_negative_offset(<vscale x 16
; CHECK-NEXT: li a3, 8
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT: vse64.v v24, (a5)
-; CHECK-NEXT: bltu a4, a3, .LBB22_8
+; CHECK-NEXT: bltu a4, a3, .LBB23_8
; CHECK-NEXT: # %bb.7:
; CHECK-NEXT: li a4, 8
-; CHECK-NEXT: .LBB22_8:
+; CHECK-NEXT: .LBB23_8:
; CHECK-NEXT: sub a2, a6, a4
; CHECK-NEXT: add a1, a2, a1
; CHECK-NEXT: vle64.v v16, (a1)
More information about the llvm-commits
mailing list