[Bug libc/17801] New: memcpy is slower on amd64 than on i686 with a Sandy Bridge CPU

["bugs at linkmauve dot fr" <sourceware-bugzilla at sourceware dot org>]

https://sourceware.org/bugzilla/show_bug.cgi?id=17801

            Bug ID: 17801
           Summary: memcpy is slower on amd64 than on i686 with a Sandy
                    Bridge CPU
           Product: glibc
           Version: 2.20
            Status: NEW
          Severity: minor
          Priority: P2
         Component: libc
          Assignee: unassigned at sourceware dot org
          Reporter: bugs at linkmauve dot fr
                CC: drepper.fsp at gmail dot com

On amd64 memcpy is actually calling __memcpy_avx_unaligned, and on i686 itâs
calling __memcpy_ssse3_rep, and with a Sandy Bridge CPU, AVX is slower than
SSSE3, despite being newer.

I tested by disabling the AVX implementation and got nearly the same speed on
amd64 than with the i686 version of the same program.

Other functions (like memmove or strncmp) may also be affected, but I havenât
checked them.

Other CPUs as well, Iâve heard that Ivy Bridge also has a slower AVX
implementation, maybe some AMD ones too.

-- 
You are receiving this mail because:
You are on the CC list for the bug.