[llvm] 1b15397 - [PowerPC] Do not RAUW combined nodes in VECTOR_SHUFFLE legalization

[Nemanja Ivanovic via llvm-commits]

Author: Nemanja Ivanovic
Date: 2020-07-06T22:09:28-05:00
New Revision: 1b1539712e1ee30c02ed20493682fc05d52391c0

URL: https://github.com/llvm/llvm-project/commit/1b1539712e1ee30c02ed20493682fc05d52391c0
DIFF: https://github.com/llvm/llvm-project/commit/1b1539712e1ee30c02ed20493682fc05d52391c0.diff

LOG: [PowerPC] Do not RAUW combined nodes in VECTOR_SHUFFLE legalization

When legalizing shuffles, we make an attempt to combine it into
a PPC specific canonical form that avoids a need for a swap. If the
combine is successful, we RAUW the node and the custom legalization
replaces the now dead node instead of the one it should replace.
Remove that erroneous call to RAUW.

Added: 
    

Modified: 
    llvm/lib/Target/PowerPC/PPCISelLowering.cpp
    llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 815a84e8c320..ff8e2382ec65 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -9896,9 +9896,10 @@ SDValue PPCTargetLowering::LowerVECTOR_SHUFFLE(SDValue Op,
   // to vector legalization will not be sent to the target combine. Try to
   // combine it here.
   if (SDValue NewShuffle = combineVectorShuffle(SVOp, DAG)) {
-    DAG.ReplaceAllUsesOfValueWith(Op, NewShuffle);
     Op = NewShuffle;
     SVOp = cast<ShuffleVectorSDNode>(Op);
+    V1 = Op.getOperand(0);
+    V2 = Op.getOperand(1);
   }
   EVT VT = Op.getValueType();
   bool isLittleEndian = Subtarget.isLittleEndian();

diff  --git a/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll b/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll
index 53e48b185714..ada7c73cd9ed 100644
--- a/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll
+++ b/llvm/test/CodeGen/PowerPC/canonical-merge-shuffles.ll
@@ -375,5 +375,49 @@ entry:
   ret <4 x i32> %vecins1
 }
 
+define dso_local <16 x i8> @no_RAUW_in_combine_during_legalize(i32* nocapture readonly %ptr, i32 signext %offset) local_unnamed_addr #0 {
+; CHECK-P8-LABEL: no_RAUW_in_combine_during_legalize:
+; CHECK-P8:       # %bb.0: # %entry
+; CHECK-P8-NEXT:    addis r5, r2, .LCPI15_0 at toc@ha
+; CHECK-P8-NEXT:    sldi r4, r4, 2
+; CHECK-P8-NEXT:    xxlxor v4, v4, v4
+; CHECK-P8-NEXT:    addi r5, r5, .LCPI15_0 at toc@l
+; CHECK-P8-NEXT:    lxsiwzx v2, r3, r4
+; CHECK-P8-NEXT:    lvx v3, 0, r5
+; CHECK-P8-NEXT:    vperm v2, v4, v2, v3
+; CHECK-P8-NEXT:    blr
+;
+; CHECK-P9-LABEL: no_RAUW_in_combine_during_legalize:
+; CHECK-P9:       # %bb.0: # %entry
+; CHECK-P9-NEXT:    sldi r4, r4, 2
+; CHECK-P9-NEXT:    lxsiwzx v2, r3, r4
+; CHECK-P9-NEXT:    addis r3, r2, .LCPI15_0 at toc@ha
+; CHECK-P9-NEXT:    addi r3, r3, .LCPI15_0 at toc@l
+; CHECK-P9-NEXT:    lxvx v3, 0, r3
+; CHECK-P9-NEXT:    xxlxor v4, v4, v4
+; CHECK-P9-NEXT:    vperm v2, v4, v2, v3
+; CHECK-P9-NEXT:    blr
+;
+; CHECK-NOVSX-LABEL: no_RAUW_in_combine_during_legalize:
+; CHECK-NOVSX:       # %bb.0: # %entry
+; CHECK-NOVSX-NEXT:    sldi r4, r4, 2
+; CHECK-NOVSX-NEXT:    vxor v2, v2, v2
+; CHECK-NOVSX-NEXT:    lwzx r3, r3, r4
+; CHECK-NOVSX-NEXT:    std r3, -16(r1)
+; CHECK-NOVSX-NEXT:    addi r3, r1, -16
+; CHECK-NOVSX-NEXT:    lvx v3, 0, r3
+; CHECK-NOVSX-NEXT:    vmrglb v2, v2, v3
+; CHECK-NOVSX-NEXT:    blr
+entry:
+  %idx.ext = sext i32 %offset to i64
+  %add.ptr = getelementptr inbounds i32, i32* %ptr, i64 %idx.ext
+  %0 = load i32, i32* %add.ptr, align 4
+  %conv = zext i32 %0 to i64
+  %splat.splatinsert = insertelement <2 x i64> undef, i64 %conv, i32 0
+  %1 = bitcast <2 x i64> %splat.splatinsert to <16 x i8>
+  %shuffle = shufflevector <16 x i8> %1, <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+  ret <16 x i8> %shuffle
+}
+
 declare double @dummy() local_unnamed_addr
 attributes #0 = { nounwind }