maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

X86: Don't fold spills into SSE operations if the stack is unaligned. 

Regalloc can emit unaligned spills nowadays, but we can't fold the
spills into SSE ops if we can't guarantee alignment. PR12250.

llvm-svn: 192064
This commit is contained in:
Benjamin Kramer 2013-10-06 13:48:22 +00:00
parent 2e408aefe0
commit 858a3880d6
2 changed files with 53 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -4166,6 +4166,10 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
const MachineFrameInfo *MFI = MF.getFrameInfo();
unsigned Size = MFI->getObjectSize(FrameIndex);
unsigned Alignment = MFI->getObjectAlignment(FrameIndex);
// If the function stack isn't realigned we don't want to fold instructions
// that need increased alignment.
if (!RI.needsStackRealignment(MF))
Alignment = std::min(Alignment, TM.getFrameLowering()->getStackAlignment());
if (Ops.size() == 2 && Ops[0] == 0 && Ops[1] == 1) {
unsigned NewOpc = 0;
unsigned RCSize = 0;

49
llvm/test/CodeGen/X86/unaligned-spill-folding.ll Normal file
View File

@ -0,0 +1,49 @@
; RUN: llc -mtriple=i386-unknown-freebsd -mattr=sse2 -stack-alignment=4 -relocation-model=pic < %s | FileCheck %s -check-prefix=UNALIGNED
; RUN: llc -mtriple=i386-unknown-freebsd -mattr=sse2 -stack-alignment=16 -relocation-model=pic < %s | FileCheck %s -check-prefix=ALIGNED
; RUN: llc -mtriple=i386-unknown-freebsd -mattr=sse2 -stack-alignment=4 -force-align-stack -relocation-model=pic < %s | FileCheck %s -check-prefix=FORCEALIGNED
@arr = internal unnamed_addr global [32 x i32] zeroinitializer, align 16
; PR12250
define i32 @test1() {
vector.ph:
br label %vector.body
vector.body:
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%0 = getelementptr inbounds [32 x i32]* @arr, i32 0, i32 %index
%1 = bitcast i32* %0 to <4 x i32>*
%wide.load = load <4 x i32>* %1, align 16
%2 = add nsw <4 x i32> %wide.load, <i32 10, i32 10, i32 10, i32 10>
%3 = xor <4 x i32> %2, <i32 123345, i32 123345, i32 123345, i32 123345>
%4 = add nsw <4 x i32> %3, <i32 112, i32 112, i32 112, i32 112>
%5 = xor <4 x i32> %4, <i32 543345, i32 543345, i32 543345, i32 543345>
%6 = add nsw <4 x i32> %5, <i32 73, i32 73, i32 73, i32 73>
%7 = xor <4 x i32> %6, <i32 345987, i32 345987, i32 345987, i32 345987>
%8 = add nsw <4 x i32> %7, <i32 48, i32 48, i32 48, i32 48>
%9 = xor <4 x i32> %8, <i32 123987, i32 123987, i32 123987, i32 123987>
store <4 x i32> %9, <4 x i32>* %1, align 16
%index.next = add i32 %index, 4
%10 = icmp eq i32 %index.next, 32
br i1 %10, label %middle.block, label %vector.body
middle.block:
ret i32 0
; We can't fold the spill into a padd unless the stack is aligned. Just spilling
; doesn't force stack realignment though
; UNALIGNED-LABEL: @test1
; UNALIGNED-NOT: andl $-{{..}}, %esp
; UNALIGNED: movdqu {{.*}} # 16-byte Folded Spill
; UNALIGNED-NOT: paddd {{.*}} # 16-byte Folded Reload
; ALIGNED-LABEL: @test1
; ALIGNED-NOT: andl $-{{..}}, %esp
; ALIGNED: movdqa {{.*}} # 16-byte Spill
; ALIGNED: paddd {{.*}} # 16-byte Folded Reload
; FORCEALIGNED-LABEL: @test1
; FORCEALIGNED: andl $-{{..}}, %esp
; FORCEALIGNED: movdqa {{.*}} # 16-byte Spill
; FORCEALIGNED: paddd {{.*}} # 16-byte Folded Reload
}