[llvm] 0073582 - [DAGCombiner] Use getVectorElementCount inside visitINSERT_SUBVECTOR

[Joe Ellis via llvm-commits]

Author: Joe Ellis
Date: 2021-01-11T14:15:11Z
New Revision: 007358239decd45819a6fa44eb2a2e07fd85e796

URL: https://github.com/llvm/llvm-project/commit/007358239decd45819a6fa44eb2a2e07fd85e796
DIFF: https://github.com/llvm/llvm-project/commit/007358239decd45819a6fa44eb2a2e07fd85e796.diff

LOG: [DAGCombiner] Use getVectorElementCount inside visitINSERT_SUBVECTOR

This avoids TypeSize-/ElementCount-related warnings.

Differential Revision: https://reviews.llvm.org/D92747

Added: 
    llvm/test/CodeGen/AArch64/dag-combine-insert-subvector.ll

Modified: 
    llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index be57d9250db7..75dbc2227f6a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -21008,8 +21008,8 @@ SDValue DAGCombiner::visitINSERT_SUBVECTOR(SDNode *N) {
   if (N0.isUndef() && N1.getOpcode() == ISD::BITCAST &&
       N1.getOperand(0).getOpcode() == ISD::EXTRACT_SUBVECTOR &&
       N1.getOperand(0).getOperand(1) == N2 &&
-      N1.getOperand(0).getOperand(0).getValueType().getVectorNumElements() ==
-          VT.getVectorNumElements() &&
+      N1.getOperand(0).getOperand(0).getValueType().getVectorElementCount() ==
+          VT.getVectorElementCount() &&
       N1.getOperand(0).getOperand(0).getValueType().getSizeInBits() ==
           VT.getSizeInBits()) {
     return DAG.getBitcast(VT, N1.getOperand(0).getOperand(0));
@@ -21026,7 +21026,7 @@ SDValue DAGCombiner::visitINSERT_SUBVECTOR(SDNode *N) {
     EVT CN1VT = CN1.getValueType();
     if (CN0VT.isVector() && CN1VT.isVector() &&
         CN0VT.getVectorElementType() == CN1VT.getVectorElementType() &&
-        CN0VT.getVectorNumElements() == VT.getVectorNumElements()) {
+        CN0VT.getVectorElementCount() == VT.getVectorElementCount()) {
       SDValue NewINSERT = DAG.getNode(ISD::INSERT_SUBVECTOR, SDLoc(N),
                                       CN0.getValueType(), CN0, CN1, N2);
       return DAG.getBitcast(VT, NewINSERT);
@@ -21107,8 +21107,10 @@ SDValue DAGCombiner::visitINSERT_SUBVECTOR(SDNode *N) {
   // If the input vector is a concatenation, and the insert replaces
   // one of the pieces, we can optimize into a single concat_vectors.
   if (N0.getOpcode() == ISD::CONCAT_VECTORS && N0.hasOneUse() &&
-      N0.getOperand(0).getValueType() == N1.getValueType()) {
-    unsigned Factor = N1.getValueType().getVectorNumElements();
+      N0.getOperand(0).getValueType() == N1.getValueType() &&
+      N0.getOperand(0).getValueType().isScalableVector() ==
+          N1.getValueType().isScalableVector()) {
+    unsigned Factor = N1.getValueType().getVectorMinNumElements();
     SmallVector<SDValue, 8> Ops(N0->op_begin(), N0->op_end());
     Ops[InsIdx / Factor] = N1;
     return DAG.getNode(ISD::CONCAT_VECTORS, SDLoc(N), VT, Ops);

diff  --git a/llvm/test/CodeGen/AArch64/dag-combine-insert-subvector.ll b/llvm/test/CodeGen/AArch64/dag-combine-insert-subvector.ll
new file mode 100644
index 000000000000..a89e3a09c1f1
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/dag-combine-insert-subvector.ll
@@ -0,0 +1,28 @@
+; RUN: llc < %s -o /dev/null 2>&1 | FileCheck --allow-empty %s
+
+; This regression test is defending against a ElementCount warning 'Possible incorrect use of
+; EVT::getVectorNumElements() for scalable vector'. This warning appeared in
+; DAGCombiner::visitINSERT_SUBVECTOR because of the use of getVectorNumElements() on scalable
+; types.
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; CHECK-NOT: warning:
+
+target triple = "aarch64-unknown-linux-gnu"
+attributes #0 = {"target-features"="+sve"}
+
+declare <16 x float> @llvm.experimental.vector.extract.v16f32.nxv4f32(<vscale x 4 x float>, i64)
+declare <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double>, <8 x double>, i64)
+
+define <vscale x 2 x double> @reproducer_one(<vscale x 4 x float> %vec_a) #0 {
+  %a = call <16 x float> @llvm.experimental.vector.extract.v16f32.nxv4f32(<vscale x 4 x float> %vec_a, i64 0)
+  %b = bitcast <16 x float> %a to <8 x double>
+  %retval = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> %b, i64 0)
+  ret <vscale x 2 x double> %retval
+}
+
+define <vscale x 2 x double> @reproducer_two(<4 x double> %a, <4 x double> %b) #0 {
+  %concat = shufflevector <4 x double> %a, <4 x double> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3>
+  %retval = call <vscale x 2 x double> @llvm.experimental.vector.insert.nxv2f64.v8f64(<vscale x 2 x double> undef, <8 x double> %concat, i64 0)
+  ret <vscale x 2 x double> %retval
+}