For graphics, it’s performance if we start requiring SSE2. Lately, canvasmark benchmark, and increasingly more trouble when updating Skia library. — - Milan
> On May 6, 2016, at 14:39 , Henri Sivonen <hsivo...@hsivonen.fi> wrote: > > On Fri, May 6, 2016 at 8:17 PM, Gregory Szorc <g...@mozilla.com> wrote: >> On Fri, May 6, 2016 at 9:39 AM, Benjamin Smedberg <benja...@smedbergs.us> >> wrote: >> >>> I agree that we should drop support for non-SSE2. It mattered 7 years ago >>> (see https://bugzilla.mozilla.org/show_bug.cgi?id=500277) but it really >>> doesn't matter now. >>> >> >> Wait - are we talking about requiring SSE or SSE2? The thread up to this >> point was talking about requiring just SSE, not SSE2. I just want to make >> sure we're on the same page since according to mhoye's post the non-SSE2 >> population is ~25x larger than the non-SSE population... > > What does requiring SSE without requiring SSE2 buy us apart from > VS2015 compat? Is it enough to fully avoid x87-style non-IEEE floating > point math? (SSE2 is usually cited when talking about migrating from > x87 to IEEE.) > > It seems that requiring SSE2 is the typical discontinuity point as > seen in Windows itself, Chromium, Rust, various codec optimizations, > C++ compiler defaults (MSVC and, I believe, clang), etc. > > That is to say, I hope the outcome here is that we start requiring SSE2. > > On Fri, May 6, 2016 at 9:11 PM, Milan Sreckovic <msrecko...@mozilla.com> > wrote: >> While I agree we should drop non-SSE (and have started a conversation to >> drop non-SSE2 as well :), the comparison to dropping 10.6-10.8 users is >> somewhat unfair. Those users can upgrade 10.9 easier than the non-SSE users >> can buy a new computer. > > Upgrading from Mac OS X 10.6 can be more expensive than buying a new > entry-level Windows PC if what kept you on 10.6 was expensive PPC-era > proprietary software (e.g. PPC-era Creative Suite for casual enough > use that you don't need the latest for the features). Also, some Macs > can't upgrade beyond 10.7. So the comparison is fairer than it first > may seem. > > -- > Henri Sivonen > hsivo...@hsivonen.fi > https://hsivonen.fi/ > _______________________________________________ > dev-platform mailing list > dev-platform@lists.mozilla.org > https://lists.mozilla.org/listinfo/dev-platform _______________________________________________ dev-platform mailing list dev-platform@lists.mozilla.org https://lists.mozilla.org/listinfo/dev-platform
