David Sehr 6c4265a541 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. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176464 91177308-0d34-0410-b5e6-96231b3b80d8		2013-03-05 00:02:23 +00:00
..
align-mode-argument-error.s
asm-printing-bundle-directives.s
autogen-inst-offset-align-to-end.s	[MC] bundle alignment: prevent padding instructions from crossing bundle boundaries	2013-01-31 17:00:03 +00:00
autogen-inst-offset-padding.s
bundle-group-too-large-error.s
bundle-lock-option-error.s
different-sections.s
lit.local.cfg
lock-without-bundle-mode-error.s
long-nop-pad.s	The current X86 NOP padding uses one long NOP followed by the remainder in	2013-03-05 00:02:23 +00:00
pad-align-to-bundle-end.s	[MC] bundle alignment: prevent padding instructions from crossing bundle boundaries	2013-01-31 17:00:03 +00:00
pad-bundle-groups.s
relax-at-bundle-end.s	[MC] Bundle alignment: Invalidate relaxed fragments	2013-02-05 17:55:27 +00:00
relax-in-bundle-group.s
single-inst-bundling.s
switch-section-locked-error.s
unlock-without-lock-error.s