diff options
| author | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2021-06-04 19:32:03 -0500 |
|---|---|---|
| committer | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2021-07-06 18:07:31 +0200 |
| commit | 37a92f3b03bf165245a9d0dc4830dcc6fed7c253 (patch) | |
| tree | b2229dac725387c47daccb2320e16b1928b9bbd1 /llvm/lib/Transforms/Utils/LoopVersioning.cpp | |
| parent | ddfb074a80a24f94290d895b74d2c80626d953ba (diff) | |
| download | llvm-37a92f3b03bf165245a9d0dc4830dcc6fed7c253.zip llvm-37a92f3b03bf165245a9d0dc4830dcc6fed7c253.tar.gz llvm-37a92f3b03bf165245a9d0dc4830dcc6fed7c253.tar.bz2 | |
[SystemZ] Generate XC loop for memset 0 of variable length.
Benchmarking has shown that it is worthwhile to implement a variable length
memset of 0 with XC (exclusive or) like gcc does, instead of using a libcall.
This requires the use of the EXecute Relative Long (EXRL) instruction which
can now be done in a framework that can also be used with other target
instructions (not just XC).
Review: Ulrich Weigand
Differential Revision: https://reviews.llvm.org/D103865
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopVersioning.cpp')
0 files changed, 0 insertions, 0 deletions