[llvm] [RISCV] Eagerly optimize scalar packing for buildvector lowering (PR #156062)

[Philip Reames via llvm-commits]

https://github.com/preames created https://github.com/llvm/llvm-project/pull/156062

Instead of relying on DAG to cleanup the redundant ANDs, go ahead actively try to prove them redundant at construction.

I noticed this because SimplifyDemandedBits was dropping the disjoint on the OR, but there's at least one other codegen diff in the tests as well.

>From 482102c02639acd6d46b6a9c4fa6fb2ed901e468 Mon Sep 17 00:00:00 2001
From: Philip Reames <preames at rivosinc.com>
Date: Fri, 29 Aug 2025 10:02:14 -0700
Subject: [PATCH] [RISCV] Eagerly optimize scalar packing for buildvector
 lowering

Instead of relying on DAG to cleanup the redundant ANDs, go ahead
actively try to prove them redundant at construction.

I noticed this because SimplifyDemandedBits was dropping the
disjoint on the OR, but there's at least one other codegen diff
in the tests as well.
---
 llvm/lib/Target/RISCV/RISCVISelLowering.cpp               | 7 +++++--
 llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 4c39bcf8494a4..80083f843f9af 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -4257,6 +4257,7 @@ static SDValue lowerBuildVectorViaPacking(SDValue Op, SelectionDAG &DAG,
   MVT XLenVT = Subtarget.getXLenVT();
   SDValue Mask = DAG.getConstant(
       APInt::getLowBitsSet(XLenVT.getSizeInBits(), ElemSizeInBits), DL, XLenVT);
+  unsigned ZeroPrefix = XLenVT.getSizeInBits() - ElemSizeInBits;
   auto pack = [&](SDValue A, SDValue B) {
     // Bias the scheduling of the inserted operations to near the
     // definition of the element - this tends to reduce register
@@ -4270,8 +4271,10 @@ static SDValue lowerBuildVectorViaPacking(SDValue Op, SelectionDAG &DAG,
                              ElemDL, XLenVT, A, B),
           0);
 
-    A = DAG.getNode(ISD::AND, SDLoc(A), XLenVT, A, Mask);
-    B = DAG.getNode(ISD::AND, SDLoc(B), XLenVT, B, Mask);
+    if (DAG.computeKnownBits(A).countMinLeadingZeros() < ZeroPrefix)
+      A = DAG.getNode(ISD::AND, SDLoc(A), XLenVT, A, Mask);
+    if (DAG.computeKnownBits(B).countMinLeadingZeros() < ZeroPrefix)
+      B = DAG.getNode(ISD::AND, SDLoc(B), XLenVT, B, Mask);
     SDValue ShtAmt = DAG.getConstant(ElemSizeInBits, ElemDL, XLenVT);
     return DAG.getNode(ISD::OR, ElemDL, XLenVT, A,
                        DAG.getNode(ISD::SHL, ElemDL, XLenVT, B, ShtAmt),
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
index d9bb007a10f71..8aaffd41cbd16 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
@@ -2629,7 +2629,7 @@ define <16 x i8> @buildvec_v16i8_undef_edges(ptr %p) {
 ; RVA22U64-NEXT:    or a0, a0, a4
 ; RVA22U64-NEXT:    slli a6, a6, 24
 ; RVA22U64-NEXT:    or a1, a1, a2
-; RVA22U64-NEXT:    add.uw a1, a6, a1
+; RVA22U64-NEXT:    or a1, a6, a1
 ; RVA22U64-NEXT:    or a0, a0, a3
 ; RVA22U64-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
 ; RVA22U64-NEXT:    vmv.v.x v8, a1