From f210626e4d7f42df9c517eb0b1d725ae8d3fb951 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke@igalia.com>
Date: Wed, 22 Apr 2026 15:31:47 +0100
Subject: [PATCH] [VPlan] Fold lhs | (headermask && rhs) -> vp.merge rhs, true,
 lhs, evl

This is a combine on mask vectors that can show up with EVL tail folding.

Split off from #190196
---
 llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp         | 8 ++++++++
 llvm/test/Transforms/LoopVectorize/RISCV/iv-select-cmp.ll | 3 +--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index d1ff014907dc9..0a71daba46a48 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -3161,6 +3161,14 @@ static VPRecipeBase *optimizeMaskToEVL(VPValue *HeaderMask,
         VPIRFlags::getDefaultFlags(Instruction::Sub), {}, DL);
   }
 
+  // lhs | (headermask && rhs) -> vp.merge rhs, true, lhs, evl
+  if (match(&CurRecipe,
+            m_c_BinaryOr(m_VPValue(LHS),
+                         m_LogicalAnd(m_Specific(HeaderMask), m_VPValue(RHS)))))
+    return new VPWidenIntrinsicRecipe(
+        Intrinsic::vp_merge, {RHS, Plan->getTrue(), LHS, &EVL},
+        TypeInfo.inferScalarType(LHS), {}, {}, DL);
+
   return nullptr;
 }
 
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/RISCV/iv-select-cmp.ll
index 7feb0d8322868..f4d3030dd74be 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/iv-select-cmp.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/iv-select-cmp.ll
@@ -97,9 +97,8 @@ define i64 @select_decreasing_induction_icmp_non_const_start(ptr %a, ptr %b, i64
 ; CHECK-NEXT:    [[VP_OP_LOAD4:%.*]] = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0(ptr align 8 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP4]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call <vscale x 4 x i64> @llvm.experimental.vp.reverse.nxv4i64(<vscale x 4 x i64> [[VP_OP_LOAD4]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP4]])
 ; CHECK-NEXT:    [[TMP16:%.*]] = icmp sgt <vscale x 4 x i64> [[TMP12]], [[TMP15]]
-; CHECK-NEXT:    [[TMP17:%.*]] = call <vscale x 4 x i1> @llvm.vp.merge.nxv4i1(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i1> [[TMP16]], <vscale x 4 x i1> zeroinitializer, i32 [[TMP4]])
 ; CHECK-NEXT:    [[TMP18]] = call <vscale x 4 x i64> @llvm.vp.merge.nxv4i64(<vscale x 4 x i1> [[TMP16]], <vscale x 4 x i64> [[VEC_IND]], <vscale x 4 x i64> [[VEC_PHI]], i32 [[TMP4]])
-; CHECK-NEXT:    [[TMP19]] = or <vscale x 4 x i1> [[VEC_PHI1]], [[TMP17]]
+; CHECK-NEXT:    [[TMP19]] = call <vscale x 4 x i1> @llvm.vp.merge.nxv4i1(<vscale x 4 x i1> [[TMP16]], <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i1> [[VEC_PHI1]], i32 [[TMP4]])
 ; CHECK-NEXT:    [[CURRENT_ITERATION_NEXT]] = add i64 [[TMP5]], [[INDEX]]
 ; CHECK-NEXT:    [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP5]]
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nsw <vscale x 4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT3]]