From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <49397F3E.9070801@telus.net> Date: Fri, 5 Dec 2008 11:21:34 -0800 From: Paul Lalonde User-Agent: Thunderbird 2.0.0.17 (Windows/20080914) MIME-Version: 1.0 To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net> References: <13426df10812042239pde2100dw696049def0160c4a@mail.gmail.com> <39cb2be32e592403f7336c6200cf56a3@quanstro.net> <13426df10812051049j40b40b78u4ae74a3fc7df07a3@mail.gmail.com> In-Reply-To: <13426df10812051049j40b40b78u4ae74a3fc7df07a3@mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [9fans] image/memimage speed Topicbox-Message-UUID: 5b2c9902-ead4-11e9-9d60-3106f5b1d025 Again, you can stream a whole frame buffer reasonably fast - that should be nearly full-rate; it should be full rate if you pre-fetch with sufficient advance notice (500-1000 clocks), or DMA. But random access reads *have* to be slow: you get a stall while the system goes to PCIe for each cache line you attempt to read from. Paul ron minnich wrote: > On Fri, Dec 5, 2008 at 10:32 AM, Russ Cox wrote: > > >> To a first approximation, no one reads directly from video memory. >> > > That is certainly true, but it's been a concern for some time for GPU > computing, and the chipset folks are paying attention. > > ron > >