diff options
| author | Preston Gurd <preston.gurd@intel.com> | 2013-03-04 18:13:57 +0000 |
|---|---|---|
| committer | Preston Gurd <preston.gurd@intel.com> | 2013-03-04 18:13:57 +0000 |
| commit | 9a2cfffdb6340c54ff553c1b81364d0f17fa8f45 (patch) | |
| tree | 999ad911d34f3f83d1140500e731228c5f07df84 /lib/Target | |
| parent | ff4faabd2d98776372f45f7592482c9239cc40f2 (diff) | |
Bypass Slow Divides
* Only apply divide bypass optimization when not optimizing for size.
* Fixed bug caused by constant for 0 value of type Int32,
used dividend type to generate the constant instead.
* For atom x86-64 apply the divide bypass to use 16-bit divides instead of
64-bit divides when operand values are small enough.
* Added lit tests for 64-bit divide bypass.
Patch by Tyler Nowicki!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176442 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target')
| -rw-r--r-- | lib/Target/X86/X86ISelLowering.cpp | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index 451acca5f3..5d12b0a392 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -181,9 +181,12 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM) setSchedulingPreference(Sched::RegPressure); setStackPointerRegisterToSaveRestore(RegInfo->getStackRegister()); - // Bypass i32 with i8 on Atom when compiling with O2 - if (Subtarget->hasSlowDivide() && TM.getOptLevel() >= CodeGenOpt::Default) + // Bypass expensive divides on Atom when compiling with O2 + if (Subtarget->hasSlowDivide() && TM.getOptLevel() >= CodeGenOpt::Default) { addBypassSlowDiv(32, 8); + if (Subtarget->is64Bit()) + addBypassSlowDiv(64, 16); + } if (Subtarget->isTargetWindows() && !Subtarget->isTargetCygMing()) { // Setup Windows compiler runtime calls. |