[PowerPC] Don't crash on larger splats achieved through 1-byte splats

We've implemented a 1-byte splat using XXSPLTISB on P9. However, LLVM will
produce a 1-byte splat even for wider element BUILD_VECTOR nodes. This patch
prevents crashing in that situation.

Differential Revision: https://reviews.llvm.org/D35650

llvm-svn: 310358

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 2c0936b..204bdcc 100644 (file)
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -7650,6 +7650,15 @@ SDValue PPCTargetLowering::LowerBUILD_VECTOR(SDValue Op,
         return DAG.getBitcast(Op.getValueType(), NewBV);
       return NewBV;
     }
+
+    // BuildVectorSDNode::isConstantSplat() is actually pretty smart. It'll
+    // detect that constant splats like v8i16: 0xABAB are really just splats
+    // of a 1-byte constant. In this case, we need to convert the node to a
+    // splat of v16i8 and a bitcast.
+    if (Op.getValueType() != MVT::v16i8)
+      return DAG.getBitcast(Op.getValueType(),
+                            DAG.getConstant(SplatBits, dl, MVT::v16i8));
+
     return Op;
   }
 

diff --git a/llvm/test/CodeGen/PowerPC/splat-larger-types-as-v16i8.ll b/llvm/test/CodeGen/PowerPC/splat-larger-types-as-v16i8.ll
new file mode 100644 (file)
index 0000000..2ae61f1
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/splat-larger-types-as-v16i8.ll
@@ -0,0 +1,20 @@
+; RUN: llc -mcpu=pwr9 -mtriple=powerpc64-unknown-unknown < %s | FileCheck %s
+; RUN: llc -mcpu=pwr9 -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s
+define <8 x i16> @test1() {
+entry:
+  ret <8 x i16> <i16 257, i16 257, i16 257, i16 257, i16 257, i16 257, i16 257, i16 257>
+; CHECK-LABEL: test1
+; CHECK: xxspltib 34, 1
+}
+define <8 x i16> @testAB() {
+entry:
+; CHECK-LABEL: testAB
+; CHECK: xxspltib 34, 171
+  ret <8 x i16> <i16 43947, i16 43947, i16 43947, i16 43947, i16 43947, i16 43947, i16 43947, i16 43947>
+}
+define <4 x i32> @testAB32() {
+entry:
+; CHECK-LABEL: testAB32
+; CHECK: xxspltib 34, 171
+  ret <4 x i32> <i32 2880154539, i32 2880154539, i32 2880154539, i32 2880154539>
+}