This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH x86_64] Update memcpy, mempcpy and memmove selection order for Excavator CPU BZ #19583


On Thu, Mar 17, 2016 at 7:16 AM, Pawar, Amit <Amit.Pawar@amd.com> wrote:
>>A few comments:
>>
>>1. Since there is bit_arch_Fast_Copy_Backward already, please add bit_arch_Avoid_AVX_Fast_Unaligned_Load instead.
> Thought to ask for one more suggestion, bit_arch_Avoid_AVX_Fast_Unaligned_Load is more readable but what to select by avoiding it? Can it be used to set any feature bit and not only Fast_Copy_Backward right?

If bit_arch_Avoid_AVX_Fast_Unaligned_Load is set, the next best
one will be selected.   See bit_arch_Slow_SSE4_2 for example.

>>2. Please verify that index_arch_XXX are the same and use one index_arch_XXX to set all bits.  There are examples in sysdeps/x86/cpu-features.c.
> My fault, didnât notice that.
>
>>3. Please use proper ChangeLog format:
>>
>>        * file (name of function, macro, ...): What changed.
>>
>
> Thanks,
> Amit Pawar



-- 
H.J.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]