[llvm] [TargetLowering] Handle vector types in expandFixedPointMul (PR #102635)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-selectiondag

@llvm/pr-subscribers-backend-aarch64

Author: Björn Pettersson (bjope)

<details>
<summary>Changes</summary>

In TargetLowering::expandFixedPointMul when expanding fixed point multiplication, and when using a widened MUL as strategy for the lowering, there was a bug resulting in assertion failures like this:
   Assertion `VT.isVector() == N1.getValueType().isVector() &&
   "SIGN_EXTEND result type type should be vector iff the operand "
   "type is vector!"' failed.

Problem was that we did not consider that VT could be a vector type when setting up the WideVT. This patch should fix that bug.

---
Full diff: https://github.com/llvm/llvm-project/pull/102635.diff


2 Files Affected:

- (modified) llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp (+3) 
- (modified) llvm/test/CodeGen/AArch64/smul_fix.ll (+14) 


``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index bef70dcb71f567..8f189729356497 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -10782,6 +10782,9 @@ TargetLowering::expandFixedPointMul(SDNode *Node, SelectionDAG &DAG) const {
   unsigned LoHiOp = Signed ? ISD::SMUL_LOHI : ISD::UMUL_LOHI;
   unsigned HiOp = Signed ? ISD::MULHS : ISD::MULHU;
   EVT WideVT = EVT::getIntegerVT(*DAG.getContext(), VTSize * 2);
+  if (VT.isVector())
+    WideVT =
+        EVT::getVectorVT(*DAG.getContext(), WideVT, VT.getVectorElementCount());
   if (isOperationLegalOrCustom(LoHiOp, VT)) {
     SDValue Result = DAG.getNode(LoHiOp, dl, DAG.getVTList(VT, VT), LHS, RHS);
     Lo = Result.getValue(0);
diff --git a/llvm/test/CodeGen/AArch64/smul_fix.ll b/llvm/test/CodeGen/AArch64/smul_fix.ll
index 7bd80a00ec81b2..50a189df2be53f 100644
--- a/llvm/test/CodeGen/AArch64/smul_fix.ll
+++ b/llvm/test/CodeGen/AArch64/smul_fix.ll
@@ -137,3 +137,17 @@ define <4 x i64> @vec3(<4 x i64> %x, <4 x i64> %y) nounwind {
   %tmp = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> %x, <4 x i64> %y, i32 32)
   ret <4 x i64> %tmp
 }
+
+define <4 x i16> @widemul(<4 x i16> %x, <4 x i16> %y) nounwind {
+; CHECK-LABEL: widemul:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    smull v0.4s, v0.4h, v1.4h
+; CHECK-NEXT:    shrn v1.4h, v0.4s, #16
+; CHECK-NEXT:    xtn v2.4h, v0.4s
+; CHECK-NEXT:    add v1.4h, v1.4h, v1.4h
+; CHECK-NEXT:    shl v0.4h, v1.4h, #13
+; CHECK-NEXT:    usra v0.4h, v2.4h, #2
+; CHECK-NEXT:    ret
+  %tmp = call <4 x i16> @llvm.smul.fix.v4i16(<4 x i16> %x, <4 x i16> %y, i32 2)
+  ret <4 x i16> %tmp
+}

``````````

</details>


https://github.com/llvm/llvm-project/pull/102635