[DAGCombiner] Account for getVectorIdxTy() when narrowing vector load

This patch makes ReplaceExtractVectorEltOfLoadWithNarrowedLoad convert
the element number from getVectorIdxTy() to PtrTy before doing pointer
arithmetic on it.  This is needed on z, where element numbers are i32
but pointers are i64.

Original patch by Richard Sandiford.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236530 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 4669d6c2f18dd5e77d93ff04a805508d963795d3..bf42aabeab2933d5db65f7eceffd8f1468e047b5 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -11416,9 +11416,10 @@ SDValue DAGCombiner::ReplaceExtractVectorEltOfLoadWithNarrowedLoad(
     Offset = DAG.getConstant(PtrOff, DL, PtrType);
     MPI = OriginalLoad->getPointerInfo().getWithOffset(PtrOff);
   } else {
+    Offset = DAG.getZExtOrTrunc(EltNo, DL, PtrType);
     Offset = DAG.getNode(
-        ISD::MUL, DL, EltNo.getValueType(), EltNo,
-        DAG.getConstant(VecEltVT.getStoreSize(), DL, EltNo.getValueType()));
+        ISD::MUL, DL, PtrType, Offset,
+        DAG.getConstant(VecEltVT.getStoreSize(), DL, PtrType));
     MPI = OriginalLoad->getPointerInfo();
   }
   NewPtr = DAG.getNode(ISD::ADD, DL, PtrType, NewPtr, Offset);

diff --git a/test/CodeGen/SystemZ/vec-extract-02.ll b/test/CodeGen/SystemZ/vec-extract-02.ll
new file mode 100644 (file)
index 0000000..c91e852
--- /dev/null
+++ b/test/CodeGen/SystemZ/vec-extract-02.ll
@@ -0,0 +1,15 @@
+; Verify ReplaceExtractVectorEltOfLoadWithNarrowedLoad fixes
+;
+; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
+
+; Test a case where a vector extraction can be simplified to a scalar load.
+; The index must be extended from i32 to i64.
+define i32 @f1(<4 x i32> *%ptr, i32 %index) {
+; CHECK-LABEL: f1:
+; CHECK: risbg {{%r[0-5]}}, %r3, 30, 189, 2
+; CHECK: l %r2,
+; CHECK: br %r14
+  %vec = load <4 x i32>, <4 x i32> *%ptr
+  %res = extractelement <4 x i32> %vec, i32 %index
+  ret i32 %res
+}