fix memcpy/memset/memmove lowering when optimizing for size

Fixing MinSize attribute handling was discussed in D11363. 
This is a prerequisite patch to doing that.

The handling of OptSize when lowering mem* functions was broken
on Darwin because it wants to ignore -Os for these cases, but the
existing logic also made it ignore -Oz (MinSize).

The Linux change demonstrates a widespread problem. The backend
doesn't usually recognize the MinSize attribute by itself; it
assumes that if the MinSize attribute exists, then the OptSize 
attribute must also exist. 

Fixing this more generally will be a follow-on patch or two.

Differential Revision: http://reviews.llvm.org/D11568



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243693 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel 2015-07-30 21:41:50 +00:00
parent dd6dcb6cee
commit 8a6197a968
4 changed files with 24 additions and 61 deletions

View File

@ -4151,6 +4151,18 @@ static bool FindOptimalMemOpLowering(std::vector<EVT> &MemOps,
return true;
}
static bool shouldLowerMemFuncForSize(const MachineFunction &MF) {
const Function *F = MF.getFunction();
bool HasMinSize = F->hasFnAttribute(Attribute::MinSize);
bool HasOptSize = F->hasFnAttribute(Attribute::OptimizeForSize);
// On Darwin, -Os means optimize for size without hurting performance, so
// only really optimize for size when -Oz (MinSize) is used.
if (MF.getTarget().getTargetTriple().isOSDarwin())
return HasMinSize;
return HasOptSize || HasMinSize;
}
static SDValue getMemcpyLoadsAndStores(SelectionDAG &DAG, SDLoc dl,
SDValue Chain, SDValue Dst,
SDValue Src, uint64_t Size,
@ -4171,7 +4183,7 @@ static SDValue getMemcpyLoadsAndStores(SelectionDAG &DAG, SDLoc dl,
bool DstAlignCanChange = false;
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo *MFI = MF.getFrameInfo();
bool OptSize = MF.getFunction()->hasFnAttribute(Attribute::OptimizeForSize);
bool OptSize = shouldLowerMemFuncForSize(MF);
FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Dst);
if (FI && !MFI->isFixedObjectIndex(FI->getIndex()))
DstAlignCanChange = true;
@ -4284,7 +4296,7 @@ static SDValue getMemmoveLoadsAndStores(SelectionDAG &DAG, SDLoc dl,
bool DstAlignCanChange = false;
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo *MFI = MF.getFrameInfo();
bool OptSize = MF.getFunction()->hasFnAttribute(Attribute::OptimizeForSize);
bool OptSize = shouldLowerMemFuncForSize(MF);
FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Dst);
if (FI && !MFI->isFixedObjectIndex(FI->getIndex()))
DstAlignCanChange = true;
@ -4378,7 +4390,7 @@ static SDValue getMemsetStores(SelectionDAG &DAG, SDLoc dl,
bool DstAlignCanChange = false;
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo *MFI = MF.getFrameInfo();
bool OptSize = MF.getFunction()->hasFnAttribute(Attribute::OptimizeForSize);
bool OptSize = shouldLowerMemFuncForSize(MF);
FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Dst);
if (FI && !MFI->isFixedObjectIndex(FI->getIndex()))
DstAlignCanChange = true;

View File

@ -964,11 +964,11 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
//// temporary - rewrite interface to use type
MaxStoresPerMemset = 8;
MaxStoresPerMemsetOptSize = Subtarget->isTargetDarwin() ? 8 : 4;
MaxStoresPerMemsetOptSize = 4;
MaxStoresPerMemcpy = 4; // For @llvm.memcpy -> sequence of stores
MaxStoresPerMemcpyOptSize = Subtarget->isTargetDarwin() ? 4 : 2;
MaxStoresPerMemcpyOptSize = 2;
MaxStoresPerMemmove = 4; // For @llvm.memmove -> sequence of stores
MaxStoresPerMemmoveOptSize = Subtarget->isTargetDarwin() ? 4 : 2;
MaxStoresPerMemmoveOptSize = 2;
// On ARM arguments smaller than 4 bytes are extended, so all arguments
// are at least 4 bytes aligned.

View File

@ -1723,14 +1723,12 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
computeRegisterProperties(Subtarget->getRegisterInfo());
// On Darwin, -Os means optimize for size without hurting performance,
// do not reduce the limit.
MaxStoresPerMemset = 16; // For @llvm.memset -> sequence of stores
MaxStoresPerMemsetOptSize = Subtarget->isTargetDarwin() ? 16 : 8;
MaxStoresPerMemsetOptSize = 8;
MaxStoresPerMemcpy = 8; // For @llvm.memcpy -> sequence of stores
MaxStoresPerMemcpyOptSize = Subtarget->isTargetDarwin() ? 8 : 4;
MaxStoresPerMemcpyOptSize = 4;
MaxStoresPerMemmove = 8; // For @llvm.memmove -> sequence of stores
MaxStoresPerMemmoveOptSize = Subtarget->isTargetDarwin() ? 8 : 4;
MaxStoresPerMemmoveOptSize = 4;
setPrefLoopAlignment(4); // 2^4 bytes.
// Predictable cmov don't hurt on atom because it's in-order.

View File

@ -59,48 +59,16 @@ entry:
; DARWIN: movq
}
; FIXME: Both Linux and Darwin should lower to a memcpy call; minsize is on.
define void @test3_minsize(i8* nocapture %A, i8* nocapture %B) nounwind minsize noredzone {
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
; LINUX-LABEL: test3_minsize:
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: movq
; LINUX: memcpy
; DARWIN-LABEL: test3_minsize:
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: memcpy
}
; FIXME: Darwin should lower to a memcpy call; minsize is on.
define void @test3_minsize_optsize(i8* nocapture %A, i8* nocapture %B) nounwind optsize minsize noredzone {
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %A, i8* %B, i64 64, i32 1, i1 false)
ret void
@ -108,22 +76,7 @@ define void @test3_minsize_optsize(i8* nocapture %A, i8* nocapture %B) nounwind
; LINUX: memcpy
; DARWIN-LABEL: test3_minsize_optsize:
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: movq
; DARWIN: memcpy
}
; Large constant memcpy's should be inlined when not optimizing for size.