Message304870
> AFAIK gcc does not enable SSE3 and SSE4 on X86_64 by default.
Linux now supports multiple variants of the same function, one variant per CPU type, the binding is done when a library is loaded. But I don't know how to implement that :-(
There is target_clones("sse4.1,avx") the function attribute in GCC for example. It compiles a function twice, once for generic CPU, once for SSE4.1.
See also ifunc: "indirect function", "CPU dispatch" or "function resolver". |
|
Date |
User |
Action |
Args |
2017-10-24 08:04:06 | vstinner | set | recipients:
+ vstinner, christian.heimes, benjamin.peterson, mgorny |
2017-10-24 08:04:06 | vstinner | set | messageid: <1508832246.41.0.213398074469.issue31834@psf.upfronthosting.co.za> |
2017-10-24 08:04:06 | vstinner | link | issue31834 messages |
2017-10-24 08:04:06 | vstinner | create | |
|