RE: Improve CRC32C performance on SSE4.2
От | Devulapalli, Raghuveer |
---|---|
Тема | RE: Improve CRC32C performance on SSE4.2 |
Дата | |
Msg-id | PH8PR11MB828602D3AE9A19531E42A2DBFBC02@PH8PR11MB8286.namprd11.prod.outlook.com обсуждение исходный текст |
Ответ на | Re: Improve CRC32C performance on SSE4.2 (John Naylor <johncnaylorls@gmail.com>) |
Ответы |
Re: Improve CRC32C performance on SSE4.2
|
Список | pgsql-hackers |
> Here's another idea to make it more automatic: Give up on initializing every > capability at once. I'm not sure I like giving up this. Initializing and running CPUID check with the attribute constructor is very valuablefor two reasons: (1) you get everything done at load time before main and (2) you don’t have to run cpuid check forevery feature (popcount, crc32c, or anything else you add in the future) multiple times. It keep the cpuid functionalityin a central place that makes it a modular design. On MSVC, we could have the first SIMD feature call pg_cpucap_initialize() which runs CPUID stores the cpu features. Any subsequentcall can skip (because it has already been initialized) by using a static variable or some other approach. Doesthis make sense? Raghuveer
В списке pgsql-hackers по дате отправления: