diff options
author | Evan Cheng <evan.cheng@apple.com> | 2014-02-11 23:49:31 +0000 |
---|---|---|
committer | Evan Cheng <evan.cheng@apple.com> | 2014-02-11 23:49:31 +0000 |
commit | 9f5baa3c7e01e632722a0d7c37b3aa82591bc8a8 (patch) | |
tree | e99668f1d962ebed1f93617d766e50b8a49440f1 /lib | |
parent | e48e9419eaa7f3cf18924ecf99da9fd84f7b94d8 (diff) | |
download | llvm-9f5baa3c7e01e632722a0d7c37b3aa82591bc8a8.tar.gz llvm-9f5baa3c7e01e632722a0d7c37b3aa82591bc8a8.tar.bz2 llvm-9f5baa3c7e01e632722a0d7c37b3aa82591bc8a8.tar.xz |
Tweak ARM fastcc by adopting these two AAPCS rules:
* CPRCs may be allocated to co-processor registers or the stack – they may never be allocated to core registers
* When a CPRC is allocated to the stack, all other VFP registers should be marked as unavailable
The difference is only noticeable in rare cases where there are a large number of floating point arguments (e.g.
7 doubles + additional float, double arguments). Although it's probably still better to avoid vmov as it can cause
stalls in some older ARM cores. The other, more subtle benefit, is to minimize difference between the various
calling conventions.
rdar://16039676
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@201193 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Target/ARM/ARMCallingConv.td | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/lib/Target/ARM/ARMCallingConv.td b/lib/Target/ARM/ARMCallingConv.td index 9ca2e465d8..b1c1f3eab1 100644 --- a/lib/Target/ARM/ARMCallingConv.td +++ b/lib/Target/ARM/ARMCallingConv.td @@ -64,6 +64,13 @@ def FastCC_ARM_APCS : CallingConv<[ CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>, CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8, S9, S10, S11, S12, S13, S14, S15]>>, + + // CPRCs may be allocated to co-processor registers or the stack – they + // may never be allocated to core registers. + CCIfType<[f32], CCAssignToStackWithShadow<4, 4, [Q0, Q1, Q2, Q3]>>, + CCIfType<[f64], CCAssignToStackWithShadow<8, 4, [Q0, Q1, Q2, Q3]>>, + CCIfType<[v2f64], CCAssignToStackWithShadow<16, 4, [Q0, Q1, Q2, Q3]>>, + CCDelegateTo<CC_ARM_APCS> ]>; |