[llvm] [RISCV] Sink vector select splat operands (PR #91554)

[Luke Lau via llvm-commits]

https://github.com/lukel97 created https://github.com/llvm/llvm-project/pull/91554

vmerge.vxm allows us to splat the true operand of a select, so sink it where possible to reduce vector register pressure.


>From d7c1c47d17f6d08df2bc67c815832503105567cf Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Thu, 9 May 2024 11:38:43 +0800
Subject: [PATCH] [RISCV] Sink vector select splat operands

vmerge.vxm allows us to splat the true operand of a select, so sink it where possible to reduce vector register pressure.
---
 llvm/lib/Target/RISCV/RISCVISelLowering.cpp     |  1 +
 .../CodeGen/RISCV/rvv/sink-splat-operands.ll    | 17 ++++++++---------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 846768f6d631e..1a831a69d8cdb 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -2019,6 +2019,7 @@ bool RISCVTargetLowering::canSplatOperand(unsigned Opcode, int Operand) const {
   case Instruction::SDiv:
   case Instruction::URem:
   case Instruction::SRem:
+  case Instruction::Select:
     return Operand == 1;
   default:
     return false;
diff --git a/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll b/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
index 6e902e79896bf..618672344fe73 100644
--- a/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
@@ -5427,19 +5427,18 @@ for.cond.cleanup:                                 ; preds = %vector.body
 define void @sink_splat_select(ptr nocapture %a, i32 signext %x) {
 ; CHECK-LABEL: sink_splat_select:
 ; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lui a2, 1
+; CHECK-NEXT:    add a2, a0, a2
+; CHECK-NEXT:    li a3, 42
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v8, a1
-; CHECK-NEXT:    lui a1, 1
-; CHECK-NEXT:    add a1, a0, a1
-; CHECK-NEXT:    li a2, 42
 ; CHECK-NEXT:  .LBB117_1: # %vector.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vle32.v v9, (a0)
-; CHECK-NEXT:    vmseq.vx v0, v9, a2
-; CHECK-NEXT:    vmerge.vvm v9, v9, v8, v0
-; CHECK-NEXT:    vse32.v v9, (a0)
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vmseq.vx v0, v8, a3
+; CHECK-NEXT:    vmerge.vxm v8, v8, a1, v0
+; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    addi a0, a0, 16
-; CHECK-NEXT:    bne a0, a1, .LBB117_1
+; CHECK-NEXT:    bne a0, a2, .LBB117_1
 ; CHECK-NEXT:  # %bb.2: # %for.cond.cleanup
 ; CHECK-NEXT:    ret
 entry: