From e2b375192478d8f6b20678bf79c27763a8e861b3 Mon Sep 17 00:00:00 2001
From: Hal Finkel <hfinkel@anl.gov>
Date: Mon, 31 Mar 2014 17:48:16 +0000
Subject: [PATCH] [PowerPC] Don't ever expand BUILD_VECTOR of v2i64 with
 shuffles

If we have two unique values for a v2i64 build vector, this will always result
in two vector loads if we expand using shuffles. Only one is necessary.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205231 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/PowerPC/PPCISelLowering.cpp |  9 +++++++++
 lib/Target/PowerPC/PPCISelLowering.h   |  5 +++++
 test/CodeGen/PowerPC/vsx.ll            | 11 ++++++-----
 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/lib/Target/PowerPC/PPCISelLowering.cpp b/lib/Target/PowerPC/PPCISelLowering.cpp
index 9015a3c5216..32ac1dce906 100644
--- a/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -8845,6 +8845,15 @@ bool PPCTargetLowering::isFMAFasterThanFMulAndFAdd(EVT VT) const {
   return false;
 }
 
+bool
+PPCTargetLowering::shouldExpandBuildVectorWithShuffles(
+                     EVT VT , unsigned DefinedValues) const {
+  if (VT == MVT::v2i64)
+    return false;
+
+  return TargetLowering::shouldExpandBuildVectorWithShuffles(VT, DefinedValues);
+}
+
 Sched::Preference PPCTargetLowering::getSchedulingPreference(SDNode *N) const {
   if (DisableILPPref || PPCSubTarget.enableMachineScheduler())
     return TargetLowering::getSchedulingPreference(N);
diff --git a/lib/Target/PowerPC/PPCISelLowering.h b/lib/Target/PowerPC/PPCISelLowering.h
index 9461e46198c..da6d4dcc3a3 100644
--- a/lib/Target/PowerPC/PPCISelLowering.h
+++ b/lib/Target/PowerPC/PPCISelLowering.h
@@ -477,6 +477,11 @@ namespace llvm {
     /// expanded to fmul + fadd.
     virtual bool isFMAFasterThanFMulAndFAdd(EVT VT) const;
 
+    // Should we expand the build vector with shuffles?
+    virtual bool
+    shouldExpandBuildVectorWithShuffles(EVT VT,
+                                        unsigned DefinedValues) const;
+
     /// createFastISel - This method returns a target-specific FastISel object,
     /// or null if the target does not support "fast" instruction selection.
     virtual FastISel *createFastISel(FunctionLoweringInfo &FuncInfo,
diff --git a/test/CodeGen/PowerPC/vsx.ll b/test/CodeGen/PowerPC/vsx.ll
index a1710938ab5..9c37fe6d40d 100644
--- a/test/CodeGen/PowerPC/vsx.ll
+++ b/test/CodeGen/PowerPC/vsx.ll
@@ -631,12 +631,13 @@ define <2 x i32> @test80(i32 %v) {
   ret <2 x i32> %i
 
 ; CHECK-LABEL: @test80
-; CHECK: addi
-; CHECK: addi
-; CHECK: lxvd2x
+; CHECK-DAG: addi [[R1:[0-9]+]], 3, 3
+; CHECK-DAG: addi [[R2:[0-9]+]], 1, -16
+; CHECK-DAG: addi [[R3:[0-9]+]], 3, 2
+; CHECK: std [[R1]], 8([[R2]])
+; CHECK: std [[R3]], -16(1)
+; CHECK: lxvd2x 34, 0, [[R2]]
 ; CHECK-NOT: stxvd2x
-; FIXME: We still make one vector for each vector element and this shuffle them
-; together instead of just composing one vector on the stack.
 ; CHECK: blr
 }
 
-- 
2.34.1