[SystemZ] Don't create PERMUTE nodes with an undef operand.

It's better to reuse the first source value than to use an undef second operand, because that will make more resulting VPERMs have identical operands and therefore MachineCSE more successful. Review: Ulrich Weigand
jaebaek · May 18, 2020 · 31ecef7 · 31ecef7
1 parent 691980e
commit 31ecef7
Show file tree

Hide file tree

Showing 3 changed files with 32 additions and 4 deletions.
diff --git a/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp b/llvm/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -4474,7 +4474,8 @@ static SDValue getGeneralPermuteNode(SelectionDAG &DAG, const SDLoc &DL,
     else
       IndexNodes[I] = DAG.getUNDEF(MVT::i32);
   SDValue Op2 = DAG.getBuildVector(MVT::v16i8, DL, IndexNodes);
-  return DAG.getNode(SystemZISD::PERMUTE, DL, MVT::v16i8, Ops[0], Ops[1], Op2);
+  return DAG.getNode(SystemZISD::PERMUTE, DL, MVT::v16i8, Ops[0],
+                     (!Ops[1].isUndef() ? Ops[1] : Ops[0]), Op2);
 }
 
 namespace {

diff --git a/llvm/test/CodeGen/SystemZ/vec-perm-14.ll b/llvm/test/CodeGen/SystemZ/vec-perm-14.ll
@@ -0,0 +1,27 @@
+; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 | FileCheck %s
+;
+; Test that only one vperm of the vector compare is needed for both extracts.
+
+define void @fun() {
+; CHECK-LABEL: fun
+; CHECK: vperm
+; CHECK-NOT: vperm
+bb:
+  %tmp = load <4 x i8>, <4 x i8>* undef
+  %tmp1 = icmp eq <4 x i8> zeroinitializer, %tmp
+  %tmp2 = extractelement <4 x i1> %tmp1, i32 0
+  br i1 %tmp2, label %bb1, label %bb2
+
+bb1:
+  unreachable
+
+bb2:
+  %tmp3 = extractelement <4 x i1> %tmp1, i32 1
+  br i1 %tmp3, label %bb3, label %bb4
+
+bb3:
+  unreachable
+
+bb4:
+  unreachable
+}
diff --git a/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll b/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intrinsics.ll
@@ -5377,12 +5377,12 @@ define void @constrained_vector_fptrunc_v3f64(<3 x double>* %src, <3 x float>* %
 ; SZ13-LABEL: constrained_vector_fptrunc_v3f64:
 ; SZ13:       # %bb.0: # %entry
 ; SZ13-NEXT:    vl %v1, 0(%r2), 4
+; SZ13-NEXT:    ld %f0, 16(%r2)
 ; SZ13-NEXT:    vledb %v1, %v1, 0, 0
 ; SZ13-NEXT:    larl %r1, .LCPI97_0
-; SZ13-NEXT:    ld %f0, 16(%r2)
-; SZ13-NEXT:    vl %v2, 0(%r1), 3
-; SZ13-NEXT:    vperm %v1, %v1, %v0, %v2
 ; SZ13-NEXT:    ledbra %f0, 0, %f0, 0
+; SZ13-NEXT:    vl %v2, 0(%r1), 3
+; SZ13-NEXT:    vperm %v1, %v1, %v1, %v2
 ; SZ13-NEXT:    ste %f0, 8(%r3)
 ; SZ13-NEXT:    vsteg %v1, 0(%r3), 0
 ; SZ13-NEXT:    br %r14