[AArch64][SelectionDAG] fix infinite loop caused by legalizing & combining CONCAT_VECTORS

Legalizing in `AArch64TargetLowering::LowerCONCAT_VECTORS()` and combining in `DAGCombiner::visitCONCAT_VECTORS()` could cause an infinite loop.
This commit fixes that issue by conditionally skipping the combining.

Fix https://github.com/llvm/llvm-project/issues/63322

Reviewed By: RKSimon, MaskRay

Differential Revision: https://reviews.llvm.org/D153316

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index ab36d22..b2853b9 100644 (file)
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -23159,7 +23159,13 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
 
     // If the input is a concat_vectors, just make a larger concat by padding
     // with smaller undefs.
-    if (In.getOpcode() == ISD::CONCAT_VECTORS && In.hasOneUse()) {
+    //
+    // Legalizing in AArch64TargetLowering::LowerCONCAT_VECTORS() and combining
+    // here could cause an infinite loop. That legalizing happens when LegalDAG
+    // is true and input of AArch64TargetLowering::LowerCONCAT_VECTORS() is
+    // scalable.
+    if (In.getOpcode() == ISD::CONCAT_VECTORS && In.hasOneUse() &&
+        !(LegalDAG && In.getValueType().isScalableVector())) {
       unsigned NumOps = N->getNumOperands() * In.getNumOperands();
       SmallVector<SDValue, 4> Ops(In->op_begin(), In->op_end());
       Ops.resize(NumOps, DAG.getUNDEF(Ops[0].getValueType()));

diff --git a/llvm/test/CodeGen/AArch64/dag-combine-concat-vectors.ll b/llvm/test/CodeGen/AArch64/dag-combine-concat-vectors.ll
new file mode 100644 (file)
index 0000000..64e6372
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/dag-combine-concat-vectors.ll
@@ -0,0 +1,70 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -mtriple=aarch64 -mattr=+sve < %s | FileCheck %s
+
+; Test that we do not end in an infinite loop (https://github.com/llvm/llvm-project/issues/63322)
+
+declare void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8>, <vscale x 16 x ptr>, i32 immarg, <vscale x 16 x i1>)
+
+define fastcc i8 @allocno_reload_assign() {
+; CHECK-LABEL: allocno_reload_assign:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov z3.b, #0 // =0x0
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    uunpklo z4.h, z3.b
+; CHECK-NEXT:    uunpkhi z7.h, z3.b
+; CHECK-NEXT:    uunpklo z2.s, z4.h
+; CHECK-NEXT:    uunpkhi z4.s, z4.h
+; CHECK-NEXT:    uunpklo z6.s, z7.h
+; CHECK-NEXT:    uunpkhi z16.s, z7.h
+; CHECK-NEXT:    ptrue p1.b
+; CHECK-NEXT:    mov z0.d, #0 // =0x0
+; CHECK-NEXT:    uunpklo z1.d, z2.s
+; CHECK-NEXT:    uunpkhi z2.d, z2.s
+; CHECK-NEXT:    uunpklo z3.d, z4.s
+; CHECK-NEXT:    uunpkhi z4.d, z4.s
+; CHECK-NEXT:    uunpklo z5.d, z6.s
+; CHECK-NEXT:    uunpkhi z6.d, z6.s
+; CHECK-NEXT:    uunpklo z7.d, z16.s
+; CHECK-NEXT:    uunpkhi z16.d, z16.s
+; CHECK-NEXT:  .LBB0_1: // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    fmov d17, xzr
+; CHECK-NEXT:    cmpeq p2.d, p0/z, z17.d, #0
+; CHECK-NEXT:    uzp1 p2.s, p2.s, p0.s
+; CHECK-NEXT:    uzp1 p2.h, p2.h, p0.h
+; CHECK-NEXT:    uzp1 p2.b, p2.b, p0.b
+; CHECK-NEXT:    mov z17.b, p2/z, #1 // =0x1
+; CHECK-NEXT:    fmov w8, s17
+; CHECK-NEXT:    sbfx x8, x8, #0, #1
+; CHECK-NEXT:    whilelo p2.b, xzr, x8
+; CHECK-NEXT:    not p2.b, p1/z, p2.b
+; CHECK-NEXT:    punpklo p3.h, p2.b
+; CHECK-NEXT:    punpkhi p2.h, p2.b
+; CHECK-NEXT:    punpklo p4.h, p3.b
+; CHECK-NEXT:    punpkhi p3.h, p3.b
+; CHECK-NEXT:    punpklo p5.h, p4.b
+; CHECK-NEXT:    punpkhi p4.h, p4.b
+; CHECK-NEXT:    st1b { z1.d }, p5, [z0.d]
+; CHECK-NEXT:    punpklo p5.h, p2.b
+; CHECK-NEXT:    st1b { z2.d }, p4, [z0.d]
+; CHECK-NEXT:    punpklo p4.h, p3.b
+; CHECK-NEXT:    punpkhi p2.h, p2.b
+; CHECK-NEXT:    punpkhi p3.h, p3.b
+; CHECK-NEXT:    st1b { z3.d }, p4, [z0.d]
+; CHECK-NEXT:    punpklo p4.h, p5.b
+; CHECK-NEXT:    st1b { z4.d }, p3, [z0.d]
+; CHECK-NEXT:    punpkhi p3.h, p5.b
+; CHECK-NEXT:    st1b { z5.d }, p4, [z0.d]
+; CHECK-NEXT:    punpklo p4.h, p2.b
+; CHECK-NEXT:    punpkhi p2.h, p2.b
+; CHECK-NEXT:    st1b { z6.d }, p3, [z0.d]
+; CHECK-NEXT:    st1b { z7.d }, p4, [z0.d]
+; CHECK-NEXT:    st1b { z16.d }, p2, [z0.d]
+; CHECK-NEXT:    b .LBB0_1
+  br label %1
+
+1:                                                ; preds = %1, %0
+  call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x ptr> zeroinitializer, i32 0, <vscale x 16 x i1> xor (<vscale x 16 x i1> shufflevector (<vscale x 16 x i1> icmp eq (<vscale x 16 x ptr> insertelement (<vscale x 16 x ptr> poison, ptr null, i64 0), <vscale x 16 x ptr> zeroinitializer), <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer), <vscale x 16 x i1> shufflevector (<vscale x 16 x i1> insertelement (<vscale x 16 x i1> poison, i1 true, i32 0), <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer)))
+  br label %1
+}
+
+uselistorder <vscale x 16 x i1> poison, { 1, 2, 0 }