mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
[SystemZ] Use preferred 16-byte function alignment
While not necessary for correctness, it is preferable for performance reasons on all architectures we currently support to align functions to 16-byte boundaries by default. llvm-svn: 330718
This commit is contained in:
parent
cf35a2cfd3
commit
7b39b149d1
@ -122,6 +122,8 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM,
|
||||
|
||||
// Instructions are strings of 2-byte aligned 2-byte values.
|
||||
setMinFunctionAlignment(2);
|
||||
// For performance reasons we prefer 16-byte alignment.
|
||||
setPrefFunctionAlignment(4);
|
||||
|
||||
// Handle operations that are handled in a similar way for all types.
|
||||
for (unsigned I = MVT::FIRST_INTEGER_VALUETYPE;
|
||||
|
Loading…
Reference in New Issue
Block a user