diff options
| author | David Sehr <sehr@google.com> | 2013-03-05 00:02:23 +0000 |
|---|---|---|
| committer | David Sehr <sehr@google.com> | 2013-03-05 00:02:23 +0000 |
| commit | 4c8979cd4d19814b8de2e45bd4cc42a5d99ebe19 (patch) | |
| tree | 0c1a536f13bd7189f92e7d89cd00ddd75b63bbb9 /llvm/lib/CodeGen/StackProtector.cpp | |
| parent | 85707b28e865b7b5baef750418f587956035ffe5 (diff) | |
| download | llvm-4c8979cd4d19814b8de2e45bd4cc42a5d99ebe19.zip llvm-4c8979cd4d19814b8de2e45bd4cc42a5d99ebe19.tar.gz llvm-4c8979cd4d19814b8de2e45bd4cc42a5d99ebe19.tar.bz2 | |
The current X86 NOP padding uses one long NOP followed by the remainder in
one-byte NOPs. If the processor actually executes those NOPs, as it sometimes
does with aligned bundling, this can have a performance impact. From my
micro-benchmarks run on my one machine, a 15-byte NOP followed by twelve
one-byte NOPs is about 20% worse than a 15 followed by a 12. This patch
changes NOP emission to emit as many 15-byte (the maximum) as possible followed
by at most one shorter NOP.
llvm-svn: 176464
Diffstat (limited to 'llvm/lib/CodeGen/StackProtector.cpp')
0 files changed, 0 insertions, 0 deletions