[PATCH] aarch64: optimized memcpy implementation for thunderx2

[Anton Youdkevitch]

Optimized memcpy implementation using "ext" instruction. The
speedup is up to 30% on larger lengths comparing to the existing
thunderx2 implementation. Performance comparison is done using
the standard lib's benchmarks.

STREAM benchmark improved ~3% comparing to it being compiled
with '-fno-builtin' flag.


OK?
-------------- next part --------------
A non-text attachment was scrubbed...
Name: memcpy-ext.patch
Type: text/x-patch
Size: 28539 bytes
Desc: not available
URL: <http://sourceware.org/pipermail/libc-alpha/attachments/20180928/0c19f045/attachment.bin>