Date: Mon, 06 Apr 2015 15:56:35 -0400 From: John Baldwin <jhb@freebsd.org> To: freebsd-current@freebsd.org Cc: Adrian Chadd <adrian@freebsd.org>, David Chisnall <theraven@freebsd.org> Subject: Re: SSE in libthr Message-ID: <2321449.loLalmYxzs@ralph.baldwin.cx> In-Reply-To: <CAJ-VmoniprFmBxXwQpxf5uGD%2BCrbE4D1e149qe1FFZOzFgHLAg@mail.gmail.com> References: <5515AED9.8040408@FreeBSD.org> <FDC008DE-6B3A-4D02-A250-67DEFB1E0B1D@FreeBSD.org> <CAJ-VmoniprFmBxXwQpxf5uGD%2BCrbE4D1e149qe1FFZOzFgHLAg@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Saturday, March 28, 2015 10:41:48 AM Adrian Chadd wrote: > Ok, so how do we reduce the amount of FPU save and restores, or make > them cheaper? Or make them more useful. If you are using SSE/AVX more often between context switches in ways that are beneficial then that might offset the cost of the save and restore and result in a net win. I have variants of strlen, memcpy, and memset that use SSE. However, microbenchmarks aren't super useful as you have noted. If you would like to try these out in some real workloads I can provide a patch to libc. -- John Baldwin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?2321449.loLalmYxzs>