[llvm] 5cf9f2c - [RISCV] Fix M1 shuffle on wrong SrcVec in lowerShuffleViaVRegSplitting

[Luke Lau via llvm-commits]

Author: Luke Lau
Date: 2024-01-26T20:25:05+07:00
New Revision: 5cf9f2cd9888feea23a624c1de3cc37ce8ce8112

URL: https://github.com/llvm/llvm-project/commit/5cf9f2cd9888feea23a624c1de3cc37ce8ce8112
DIFF: https://github.com/llvm/llvm-project/commit/5cf9f2cd9888feea23a624c1de3cc37ce8ce8112.diff

LOG: [RISCV] Fix M1 shuffle on wrong SrcVec in lowerShuffleViaVRegSplitting

This fixes a miscompile from #79072 where we were taking the wrong SrcVec to do
the M1 shuffle. E.g. if the SrcVecIdx was 2 and we had 2 VRegsPerSrc, we ended
up taking it from V1 instead of V2.

Added: 
    

Modified: 
    llvm/lib/Target/RISCV/RISCVISelLowering.cpp
    llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 0cfadfbdb89b4e..5b1a246a19c8e8 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -4745,7 +4745,7 @@ static SDValue lowerShuffleViaVRegSplitting(ShuffleVectorSDNode *SVN,
     if (SrcVecIdx == -1)
       continue;
     unsigned ExtractIdx = (SrcVecIdx % VRegsPerSrc) * NumOpElts;
-    SDValue SrcVec = (unsigned)SrcVecIdx > VRegsPerSrc ? V2 : V1;
+    SDValue SrcVec = (unsigned)SrcVecIdx >= VRegsPerSrc ? V2 : V1;
     SDValue SubVec = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, M1VT, SrcVec,
                                  DAG.getVectorIdxConstant(ExtractIdx, DL));
     SubVec = convertFromScalableVector(OneRegVT, SubVec, DAG, Subtarget);

diff  --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
index b2b6e3b4414b1f..8499086994bc01 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
@@ -149,15 +149,13 @@ define <4 x i64> @m2_splat_into_identity_two_source_v2_hi(<4 x i64> %v1, <4 x i6
   ret <4 x i64> %res
 }
 
-; FIXME: This is a miscompile, we're clobbering the lower reg group of %v2
-; (v10), and the vmv1r.v is moving from the wrong reg group (should be v10)
 define <4 x i64> @m2_splat_into_slide_two_source_v2_lo(<4 x i64> %v1, <4 x i64> %v2) vscale_range(2,2) {
 ; CHECK-LABEL: m2_splat_into_slide_two_source_v2_lo:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
-; CHECK-NEXT:    vrgather.vi v10, v8, 0
-; CHECK-NEXT:    vmv1r.v v11, v8
-; CHECK-NEXT:    vmv2r.v v8, v10
+; CHECK-NEXT:    vrgather.vi v12, v8, 0
+; CHECK-NEXT:    vmv1r.v v13, v10
+; CHECK-NEXT:    vmv2r.v v8, v12
 ; CHECK-NEXT:    ret
   %res = shufflevector <4 x i64> %v1, <4 x i64> %v2, <4 x i32> <i32 0, i32 0, i32 4, i32 5>
   ret <4 x i64> %res