ARMEB: Fix trunc store for vector types

Reviewed at http://reviews.llvm.org/D4135

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211010 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index 47a48f18a3dff0911af79dbb6352e89ca77f2e46..3350601aadccd153a009237ba30a68a35bcffb6d 100644 (file)
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -8464,7 +8464,8 @@ static SDValue PerformSTORECombine(SDNode *N,
     SDLoc DL(St);
     SDValue WideVec = DAG.getNode(ISD::BITCAST, DL, WideVecVT, StVal);
     SmallVector<int, 8> ShuffleVec(NumElems * SizeRatio, -1);
-    for (unsigned i = 0; i < NumElems; ++i) ShuffleVec[i] = i * SizeRatio;
+    for (unsigned i = 0; i < NumElems; ++i)
+      ShuffleVec[i] = TLI.isBigEndian() ? (i+1) * SizeRatio - 1 : i * SizeRatio;
 
     // Can't shuffle using an illegal type.
     if (!TLI.isTypeLegal(WideVecVT)) return SDValue();

diff --git a/test/CodeGen/ARM/big-endian-neon-trunc-store.ll b/test/CodeGen/ARM/big-endian-neon-trunc-store.ll
new file mode 100644 (file)
index 0000000..65147ad
--- /dev/null
+++ b/test/CodeGen/ARM/big-endian-neon-trunc-store.ll
@@ -0,0 +1,26 @@
+; RUN: llc < %s -mtriple armeb-eabi -mattr v7,neon -o - | FileCheck %s
+
+define void @vector_trunc_store_2i64_to_2i16( <2 x i64>* %loadaddr, <2 x i16>* %storeaddr ) {
+; CHECK-LABEL: vector_trunc_store_2i64_to_2i16:
+; CHECK:       vmovn.i64  [[REG:d[0-9]+]]
+; CHECK:       vrev32.16  [[REG]], [[REG]]
+; CHECK:       vuzp.16    [[REG]], [[REG2:d[0-9]+]]
+; CHECK:       vrev32.16  [[REG]], [[REG2]]
+  %1 = load <2 x i64>* %loadaddr
+  %2 = trunc <2 x i64> %1 to <2 x i16>
+  store <2 x i16> %2, <2 x i16>* %storeaddr
+  ret void
+}
+
+define void @vector_trunc_store_4i32_to_4i8( <4 x i32>* %loadaddr, <4 x i8>* %storeaddr ) {
+; CHECK-LABEL: vector_trunc_store_4i32_to_4i8:
+; CHECK:       vmovn.i32 [[REG:d[0-9]+]]
+; CHECK:       vrev16.8  [[REG]], [[REG]]
+; CHECK:       vuzp.8    [[REG]], [[REG2:d[0-9]+]]
+; CHECK:       vrev32.8  [[REG]], [[REG2]]
+  %1 = load <4 x i32>* %loadaddr
+  %2 = trunc <4 x i32> %1 to <4 x i8>
+  store <4 x i8> %2, <4 x i8>* %storeaddr
+  ret void
+}
+