[AArch64][SVE] Bail out of performPostLD1Combine for scalable types

[kmclaughlin]

Summary

performPostLD1Combine will introduce either a LD1LANEpost
or LD1DUPpost node, which will cause selection failure if the
return type is a scalable vector.

[efriedma]

I was looking into this too; looks like you beat me to it. :)

LGTM with a minor comment on the test.

llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll

9

Please add CHECK lines for the actual load/arithmetic you expect to be generated, even if they aren't really "important" to the crash.

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

static SDValue performPostLD1Combine(SDNode *N,
                                      TargetLowering::DAGCombinerInfo &DCI,
                                      bool IsLaneOp) {
   if (DCI.isBeforeLegalizeOps())
     return SDValue();
 
   SelectionDAG &DAG = DCI.DAG;
   EVT VT = N->getValueType(0);
 
+  if (VT.isScalableVector())
+    return SDValue();
+
   unsigned LoadIdx = IsLaneOp ? 1 : 0;
   SDNode *LD = N->getOperand(LoadIdx).getNode();
   // If it is not LOAD, can not do such combine.
   if (LD->getOpcode() != ISD::LOAD)
     return SDValue();
 
   // The vector lane must be a constant in the LD1LANE opcode.
   SDValue Lane;

llvm/test/CodeGen/AArch64/sve-ld-post-inc.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+; These tests are here to ensure we don't get a selection error caused
+; by performPostLD1Combine, which should bail out if the return
+; type is a scalable vector
+
+define <vscale x 4 x i32> @test_post_ld1_insert(i32* %a, i32** %ptr, i64 %inc) {
+; CHECK-LABEL: test_post_ld1_insert:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr w8, [x0]
+; CHECK-NEXT:    add x9, x0, x2, lsl #2
+; CHECK-NEXT:    str x9, [x1]
+; CHECK-NEXT:    fmov s0, w8
+; CHECK-NEXT:    ret
+  %load = load i32, i32* %a
+  %ins = insertelement <vscale x 4 x i32> undef, i32 %load, i32 0
+  %gep = getelementptr i32, i32* %a, i64 %inc
+  store i32* %gep, i32** %ptr
+  ret <vscale x 4 x i32> %ins
+}
+
+define <vscale x 2 x double> @test_post_ld1_dup(double* %a, double** %ptr, i64 %inc) {
+; CHECK-LABEL: test_post_ld1_dup:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ldr d0, [x0]
+; CHECK-NEXT:    add x8, x0, x2, lsl #3
+; CHECK-NEXT:    mov z0.d, d0
+; CHECK-NEXT:    str x8, [x1]
+; CHECK-NEXT:    ret
+  %load = load double, double* %a
+  %dup = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double %load)
+  %gep = getelementptr double, double* %a, i64 %inc
+  store double* %gep, double** %ptr
+  ret <vscale x 2 x double> %dup
+}
+
+declare <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double)