Path: csiph.com!v102.xanadu-bbs.net!xanadu-bbs.net!news.glorb.com!border3.nntp.dca.giganews.com!border1.nntp.dca.giganews.com!nntp.giganews.com!news.iecc.com!.POSTED!nerds-end From: "Dmitry A. Kazakov" Newsgroups: comp.compilers Subject: Re: Green Compiler ? Date: Sun, 30 Dec 2012 09:22:46 +0100 Organization: cbb software GmbH Lines: 35 Sender: johnl@iecc.com Approved: comp.compilers@iecc.com Message-ID: <12-12-039@comp.compilers> References: <12-12-010@comp.compilers> <12-12-013@comp.compilers> <12-12-023@comp.compilers> <12-12-027@comp.compilers> <12-12-033@comp.compilers> Reply-To: mailbox@dmitry-kazakov.de NNTP-Posting-Host: news.iecc.com Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Trace: leila.iecc.com 1356903563 42891 64.57.183.58 (30 Dec 2012 21:39:23 GMT) X-Complaints-To: abuse@iecc.com NNTP-Posting-Date: Sun, 30 Dec 2012 21:39:23 +0000 (UTC) Keywords: code, performance Posted-Date: 30 Dec 2012 16:39:23 EST X-submission-address: compilers@iecc.com X-moderator-address: compilers-request@iecc.com X-FAQ-and-archives: http://compilers.iecc.com Xref: csiph.com comp.compilers:823 On Fri, 28 Dec 2012 12:57:52 -0500, George Neuner wrote: > On Fri, 28 Dec 2012 09:11:23 +0100, "Nils M Holm" wrote: > >>Why does a game *have to* use the maximum number of frames per >>second? When a given number of frames per second is sufficient, >>in the sense that additional frames will not make the video output >>any smoother, why increase the frame rate further? > > Unfortunately, games are hardly the only offenders. When I worked in > medical imaging (circa mid 90's), there was a requirement to render > cineloops at 66fps regardless of image size, pixel depth or 2D vs 3D > processing. There were no 3-D GPUs and SIMD CPUs of the day > (UltraSparc, Pentium MMX, etc.) were not equal to many of the imaging > tasks. We had to use custom FPGA based hardware to achieve the > required frame rates at a (halfway) reasonable (to the user) cost. > > AFAIA, medical cineloops still are required to be rendered at 66fps. > Doesn't matter that 40fps is faster than almost any human can see. I thought it so, but it seems urban legend. In late 90's I worked in a project that in particular rendered waveforms (electrocardiogram). It was a huge problem then as it required to run on a conventional PC. There was no specific fps specification, but requirement that curves scrolled smoothly to human eye. Experiments shown that only at 10ms refresh rate you stop noticing curve's jitter. Maybe there is some relation to aliasing issues. Certainly the brain needs much more time for 3D scenes than for simple geometric shapes. And it is probably way different for LED displays now than for tubes then. -- Regards, Dmitry A. Kazakov http://www.dmitry-kazakov.de