Enable shrink wrapping for PPC64

Re-enable shrink wrapping for PPC64 Little Endian.

One minor modification to PPCFrameLowering::findScratchRegister was necessary to handle fall-thru blocks (blocks with no terminator) correctly.

Tested with all LLVM test, clang tests, and the self-hosting build, with no problems found.

PHabricator: http://reviews.llvm.org/D14778

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@254314 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCFrameLowering.cpp b/lib/Target/PowerPC/PPCFrameLowering.cpp
index c7a3bbd3762a360152b8c44398f075c5cb16873f..5a151eb6ab25f21a01e7d479d2804a6913892147 100644 (file)
--- a/lib/Target/PowerPC/PPCFrameLowering.cpp
+++ b/lib/Target/PowerPC/PPCFrameLowering.cpp
@@ -573,10 +573,18 @@ bool PPCFrameLowering::findScratchRegister(MachineBasicBlock *MBB,
   RS.initRegState();
   RS.enterBasicBlock(MBB);
 
-  // The scratch register will be used at the end of the block, so must consider
-  // all registers used within the block
-  if (UseAtEnd && MBB->begin() != MBB->getFirstTerminator())
-    RS.forward(MBB->getFirstTerminator());
+  if (UseAtEnd && !MBB->empty()) {
+    // The scratch register will be used at the end of the block, so must consider
+    // all registers used within the block
+
+    MachineBasicBlock::iterator MBBI = MBB->getFirstTerminator();
+    // If no terminator, back iterator up to previous instruction.
+    if (MBBI == MBB->end())
+      MBBI = std::prev(MBBI);
+
+    if (MBBI != MBB->begin())
+      RS.forward(MBBI);
+  }
   
   if (!RS.isRegUsed(R0)) 
     return true;
@@ -1768,6 +1776,6 @@ PPCFrameLowering::restoreCalleeSavedRegisters(MachineBasicBlock &MBB,
 }
 
 bool PPCFrameLowering::enableShrinkWrapping(const MachineFunction &MF) const {
-  // FIXME: Enable this for non-Darwin PPC64 once it is confirmed working.
-  return false;
+  return (MF.getSubtarget<PPCSubtarget>().isSVR4ABI() &&
+          MF.getSubtarget<PPCSubtarget>().isPPC64());
 }

diff --git a/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll b/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll
index a23888425bf5492e3a38051bc76b5098d031fb5d..2da8e8d0984c9a809a4ecc048f5b404214f2c9bb 100644 (file)
--- a/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll
+++ b/test/CodeGen/PowerPC/ppc-shrink-wrapping.ll
@@ -1,6 +1,5 @@
 ; RUN: llc -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=ENABLE
 ; RUN: llc -mtriple=powerpc64le-unknown-linux-gnu %s -o - -enable-shrink-wrap=false |  FileCheck %s --check-prefix=CHECK --check-prefix=DISABLE
-; XFAIL: *
 ;
 ; Note: Lots of tests use inline asm instead of regular calls.
 ; This allows to have a better control on what the allocation will do.