Jan Beulich 9ea811973d perf bench: Make "default" memcpy() selection actually use glibc's implementation ... Since arch/x86/lib/memcpy_64.S implements not only __memcpy, but also memcpy, without further precautions this function will get chose by the static linker for resolving all references, and hence the "default" measurement didn't really measure anything else than the "x86-64-unrolled" one. Fix this by renaming (through the pre-processor) the conflicting symbol. On my Westmere system, the glibc variant turns out to require about 4% less instructions, but 15% more cycles for the default 1Mb block size measured. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4F16D6FD020000780006D72F@nat28.tlf.novell.com Signed-off-by: Jan Beulich <jbeulich@suse.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>		2012-01-24 19:50:19 -02:00
..
firewire	tools/firewire: nosy-dump: increment program version	2010-07-27 11:04:12 +02:00
hv	Staging: hv: move hyperv code out of staging directory	2011-10-10 22:52:55 -06:00
perf	perf bench: Make "default" memcpy() selection actually use glibc's implementation	2012-01-24 19:50:19 -02:00
power	Merge branches 'acpi', 'idle', 'mrst-pmu' and 'pm-tools' into next	2011-11-06 22:14:50 -05:00
slub	Merge branches 'slab/next' and 'slub/partial' into slab/for-linus	2011-10-26 18:09:12 +03:00
testing/ktest	ktest: Check parent options for iterated tests	2011-11-18 11:07:24 -05:00
usb	USB: ffs-test: fix header path	2011-02-28 19:27:12 -08:00
virtio	virtio_test: support event index	2011-05-30 11:14:15 +09:30