[PATCH] aarch64: Optimized memcmp for medium to large sizes

[Szabolcs Nagy]

On 06/03/18 13:54, Siddhesh Poyarekar wrote:
> On Tuesday 06 March 2018 06:45 PM, Adhemerval Zanella wrote:
>> On 02/02/2018 02:50, Siddhesh Poyarekar wrote:
>>> This improved memcmp provides a fast path for compares up to 16 bytes
>>> and then compares 16 bytes at a time, thus optimizing loads from both
>>> sources.  The glibc memcmp microbenchmark retains performance (with an
>>> error of ~1ns) for smaller compare sizes and reduces up to 31% of
>>> execution time for compares up to 4K on the APM Mustang.  On Qualcomm
>>> Falkor this improves to almost 48%, i.e. it is almost 2x improvement
>>> for sizes of 2K and above.
>>>
>>> 	* sysdeps/aarch64/memcmp.S: Widen comparison to 16 bytes at a
>>> 	time.
>>
>> LGTM with some comments clarifications below.
> 
> Thanks, fixed up and pushed.
> 

this broke the build for me:

/B/elf/librtld.os: In function `memcmp':
/S/string/../sysdeps/aarch64/memcmp.S:78: undefined reference to `.Lloop8'
collect2: error: ld returned 1 exit status
make[2]: *** [/B/elf/ld.so] Error 1
make[2]: Leaving directory `/S/elf'