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

copy mmx values from/to memory with GPRs on x86-32 

instead of with mmx registers.  This horribleness is apparently
done by gcc to avoid having to insert emms in places that really 
should have it.  This is the second half of rdar://5741668.

llvm-svn: 47474
This commit is contained in:
Chris Lattner 2008-02-22 05:18:04 +00:00
parent e665095da1
commit ab8bfc28c8
2 changed files with 28 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -5897,7 +5897,31 @@ static SDOperand PerformSTORECombine(StoreSDNode *St, SelectionDAG &DAG,
St->isVolatile(), St->getAlignment());
}
// TODO: 2 32-bit copies.
// Otherwise, lower to two 32-bit copies.
SDOperand LoAddr = Ld->getBasePtr();
SDOperand HiAddr = DAG.getNode(ISD::ADD, MVT::i32, LoAddr,
DAG.getConstant(MVT::i32, 4));
SDOperand LoLd = DAG.getLoad(MVT::i32, Ld->getChain(), LoAddr,
Ld->getSrcValue(), Ld->getSrcValueOffset(),
Ld->isVolatile(), Ld->getAlignment());
SDOperand HiLd = DAG.getLoad(MVT::i32, Ld->getChain(), HiAddr,
Ld->getSrcValue(), Ld->getSrcValueOffset()+4,
Ld->isVolatile(),
MinAlign(Ld->getAlignment(), 4));
LoAddr = St->getBasePtr();
HiAddr = DAG.getNode(ISD::ADD, MVT::i32, LoAddr,
DAG.getConstant(MVT::i32, 4));
SDOperand LoSt = DAG.getStore(LoLd.getValue(1), LoLd, LoAddr,
St->getSrcValue(), St->getSrcValueOffset(),
St->isVolatile(), St->getAlignment());
SDOperand HiSt = DAG.getStore(HiLd.getValue(1), HiLd, HiAddr,
St->getSrcValue(), St->getSrcValueOffset()+4,
St->isVolatile(),
MinAlign(St->getAlignment(), 4));
return DAG.getNode(ISD::TokenFactor, MVT::Other, LoSt, HiSt);
}
return SDOperand();
}

5
llvm/test/CodeGen/X86/mmx-copy-gprs.ll
View File

@ -1,4 +1,5 @@
; RUN: llvm-as < %s | llc -march=x86-64 | grep {movq.*(%rsi), %rax}
; RUN: llvm-as < %s | llc -march=x86 | grep {movl.*4(%eax),}
; This test should use GPRs to copy the mmx value, not MMX regs. Using mmx regs,
; increases the places that need to use emms.
@ -6,9 +7,9 @@
; rdar://5741668
target triple = "x86_64-apple-darwin8"
define i32 @foo(<1 x i64>* %x, <1 x i64>* %y) nounwind {
define void @foo(<1 x i64>* %x, <1 x i64>* %y) nounwind {
entry:
%tmp1 = load <1 x i64>* %y, align 8 ; <<1 x i64>> [#uses=1]
store <1 x i64> %tmp1, <1 x i64>* %x, align 8
ret i32 undef
ret void
}