[fpc-devel] State of SSE/AVX intrinsics
J. Gareth Moreton
gareth at moreton-family.com
Wed Apr 22 15:05:59 CEST 2020
Whether they be new functions or just an optional parameter, I do agree
that they should be compatible with FreeMem rather than requiring their
own function - Microsoft's non-portable _aligned_malloc requires calling
a specialised 'free' function, but the C11 and C++17 standards, despite
having new functions, can use 'free' without any problems.
My impression is that the alignment of GetMem is implementation-specific
and is fine for most applications. On x86_64 at least, it seems to be
at least 16 bytes, but there are some cases where you want 32 bytes
(256-bit AVX), 64 bytes (AVX512) or 4,096 bytes (memory paging).
Gareth aka. Kit
On 22/04/2020 11:07, Michael Van Canneyt wrote:
> On Wed, 22 Apr 2020, Tomas Hajny wrote:
>> On 2020-04-21 20:47, J. Gareth Moreton wrote:
>>> As I mentioned in my future development post,
>>> do you think FPC could benefit from
>>> GetMemAligned and ReallocMemAligned routines?
>>> The internal functions could be used to help
>>> control such custom alignment in dynamic
>> Wouldn't it be better to use either some kind of global property or
>> an optional additional argument than completely new routines
>> requiring explicit handling not only from the end-user programs, but
>> also from all units which may in turn be involved in memory
>> allocation (including various containers etc.)?
> I think so too.
> What's more, I thought the memory allocation routines already
> guarantee some
> form of alignment, simply because of the internal structures used by
> the memory
> manager ?
This email has been checked for viruses by Avast antivirus software.
More information about the fpc-devel