[PATCH] Correct type used for VADD_SPLAT optimization on PowerPC

In PPCISelLowering.cpp: PPCTargetLowering::LowerBUILD_VECTOR(), there
is an optimization for certain patterns to generate one or two vector
splats followed by a vector add or subtract.  This operation is
represented by a VADD_SPLAT in the selection DAG.  Prior to this
patch, it was possible for the VADD_SPLAT to be assigned the wrong
data type, causing incorrect code generation.  This patch corrects the
problem.

Specifically, the code previously assigned the value type of the
BUILD_VECTOR node to the newly generated VADD_SPLAT node.  This is
correct much of the time, but not always.  The problem is that the
call to isConstantSplat() may return a SplatBitSize that is not the
same as the number of bits in the original element vector type.  The
correct type to assign is a vector type with the same element bit size
as SplatBitSize.

The included test case shows an example of this, where the
BUILD_VECTOR node has a type of v16i8.  The vector to be built is {0,
16, 0, 16, 0, 16, 0, 16, 0, 16, 0, 16, 0, 16, 0, 16}.  isConstantSplat
detects that we can generate a splat of 16 for type v8i16, which is
the type we must assign to the VADD_SPLAT node.  If we do not, we
generate a vspltisb of 8 and a vaddubm, which generates the incorrect
result {16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
16}.  The correct code generation is a vspltish of 8 and a vadduhm.

This patch also corrected code generation for
CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll, which had been marked
as an XFAIL, so we can remove the XFAIL from the test case.

llvm-svn: 209662

3 files changed, 26 insertions, 5 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 214c8692060..cf4c9e61a58 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -5531,10 +5531,14 @@ SDValue PPCTargetLowering::LowerBUILD_VECTOR(SDValue Op,
     // we convert to a pseudo that will be expanded later into one of
     // the above forms.
     SDValue Elt = DAG.getConstant(SextVal, MVT::i32);
-    EVT VT = Op.getValueType();
-    int Size = VT == MVT::v16i8 ? 1 : (VT == MVT::v8i16 ? 2 : 4);
-    SDValue EltSize = DAG.getConstant(Size, MVT::i32);
-    return DAG.getNode(PPCISD::VADD_SPLAT, dl, VT, Elt, EltSize);
+    EVT VT = (SplatSize == 1 ? MVT::v16i8 :
+              (SplatSize == 2 ? MVT::v8i16 : MVT::v4i32));
+    SDValue EltSize = DAG.getConstant(SplatSize, MVT::i32);
+    SDValue RetVal = DAG.getNode(PPCISD::VADD_SPLAT, dl, VT, Elt, EltSize);
+    if (VT == Op.getValueType())
+      return RetVal;
+    else
+      return DAG.getNode(ISD::BITCAST, dl, Op.getValueType(), RetVal);
   }
 
   // If this is 0x8000_0000 x 4, turn into vspltisw + vslw.  If it is
diff --git a/llvm/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll b/llvm/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll
index 00a402e0e48..8802b97d2a6 100644
--- a/llvm/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll
+++ b/llvm/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll
@@ -1,6 +1,5 @@
 ; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep vadduhm
 ; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep vsubuhm
-; XFAIL: *
 
 define <4 x i32> @test() nounwind {
 	ret <4 x i32> < i32 4293066722, i32 4293066722, i32 4293066722, i32 4293066722>
diff --git a/llvm/test/CodeGen/PowerPC/splat-bug.ll b/llvm/test/CodeGen/PowerPC/splat-bug.ll
new file mode 100644
index 00000000000..4b5250b259f
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/splat-bug.ll
@@ -0,0 +1,18 @@
+; RUN: llc -mcpu=ppc64 -O0 -fast-isel=false < %s | FileCheck %s
+
+; Checks for a previous bug where vspltisb/vaddubm were issued in place
+; of vsplitsh/vadduhm.
+
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+@a = external global <16 x i8>
+
+define void @foo() nounwind ssp {
+; CHECK: foo:
+  store <16 x i8> <i8 0, i8 16, i8 0, i8 16, i8 0, i8 16, i8 0, i8 16, i8 0, i8 16, i8 0, i8 16, i8 0, i8 16, i8 0, i8 16>, <16 x i8>* @a
+; CHECK: vspltish [[REG:[0-9]+]], 8
+; CHECK: vadduhm {{[0-9]+}}, [[REG]], [[REG]]
+  ret void
+}
+