diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2013-03-27 00:02:20 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2013-03-27 00:02:20 +0000 |
| commit | b7e11e400dabced046e7ec53a66926716563bb36 (patch) | |
| tree | ac0269c393018ee12ba343e3e1f3fa47d8368cb3 /lib/Target/PowerPC/PPCCallingConv.td | |
| parent | ca442a4a1aabf6199e5aee09ec604e79916d9b92 (diff) | |
| download | llvm-b7e11e400dabced046e7ec53a66926716563bb36.tar.gz llvm-b7e11e400dabced046e7ec53a66926716563bb36.tar.bz2 llvm-b7e11e400dabced046e7ec53a66926716563bb36.tar.xz | |
Don't spill PPC VRSAVE on non-Darwin (even in SjLj)
As Bill Schmidt pointed out to me, only on Darwin do we need to spill/restore
VRSAVE in the SjLj code. For non-Darwin, don't spill/restore VRSAVE (and I've
added some asserts to make sure that we're not).
As it turns out, we're not currently handling the Darwin case correctly (I've
added a FIXME in the test case). I've tried adding various implied register
definitions/uses to force the spill without success, so I'll need to address
this later.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178096 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/PowerPC/PPCCallingConv.td')
| -rw-r--r-- | lib/Target/PowerPC/PPCCallingConv.td | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/lib/Target/PowerPC/PPCCallingConv.td b/lib/Target/PowerPC/PPCCallingConv.td index 2a680661d3..c8a29a3d2c 100644 --- a/lib/Target/PowerPC/PPCCallingConv.td +++ b/lib/Target/PowerPC/PPCCallingConv.td @@ -137,7 +137,8 @@ def CSR_SVR464 : CalleeSavedRegs<(add X14, X15, X16, X17, X18, X19, X20, VRSAV V20, V21, V22, V23, V24, V25, V26, V27, V28, V29, V30, V31)>; -def CSR_NoRegs : CalleeSavedRegs<(add)>; +def CSR_NoRegs : CalleeSavedRegs<(add VRSAVE)>; +def CSR_NoRegs_Darwin : CalleeSavedRegs<(add)>; def CSR_NoRegs_Altivec : CalleeSavedRegs<(add (sequence "V%u", 0, 31), VRSAVE)>; |