On Tue, 10 Jul 2018 20:38:24 +0200 "Jason A. Donenfeld" <ja...@zx2c4.com> wrote:
> I might not be understanding you correctly. Do you mean to suggest > that removing simd_relax() actually harms performance now? That having > it in there helps performance? Actually no, after your message I swapped kernels again to recheck, and nope, now the one with simd_relax removed appears faster a bit as it should be (by about 5%). Perhaps it was something else, maybe my test bench is not ideal: both "dual-core" VMs run on the same 8-core FX-8350, which has some of its cores coupled to share resources, so at the scheduler's whim VMs can probably affect each other. (Will try further tests with affinity pinning). -- With respect, Roman _______________________________________________ WireGuard mailing list WireGuard@lists.zx2c4.com https://lists.zx2c4.com/mailman/listinfo/wireguard