Path: utzoo!attcan!uunet!tut.cis.ohio-state.edu!zaphod.mps.ohio-state.edu!samsung!munnari.oz.au!metro!ipso!fawlty!johnmac From: johnmac@fawlty.towers.oz (John MacLean) Newsgroups: comp.sys.apple2 Subject: Re: DMA SCSI card Message-ID: <207@fawlty.towers.oz> Date: 28 May 90 04:37:51 GMT Organization: Tower Technology, Lane Cove, NSW Lines: 40 >Believe me, it is. Matt Gulick put together a "Star Wars" demo on his hard >disk, which was 30 megabytes of frames stored consecutively at the block >level. The frame rate was approx 33 fps. Now we are getting even more than far-fetched. 33fps = 33*32K = 1056K per second. This is *MORE* than Apple quotes as the theoretical upper limit of the DMA SCSI card transfer rate! All I can say is, well done Matt, you have achieved the impossible. I like to prove people wrong about the GS myself, but keep the facts straight. From what you have described, I can only conclude that: - the demo was very fast. - the graphics were stored at the block level (ie: no GS/OS or other file system on the partition). - palettes or scan line control bytes were not updated. Even with all of this (which I must say is very impressive, and I would really like to see it) I do not believe your frame rates. I would easily believe 20 fps (if the code is written in this way). I could possibly believe 25 fps or so. Any higher, and Apple has misquoted the transfer rate of thier card. It is simply not possible for the card to be run at its maximum transfer rate over multiple calls to the driver. This is because of delays between head movements, latency waiting for start of track (or at least start of block with full track caching). Would someone like to quote the ACTUAL number of SHR screens displayed, and the ACTUAL time it took to display them all. Regards, John MacLean. -- This net: johnmac@fawlty.towers.oz.au Phone: +61 2 427 2999 That net: uunet!fawlty.towers.oz.au!johnmac Fax: +61 2 427 7072 Snail: Tower Technology, Unit D 31-33 Sirius Rd, Home: +61 2 960 1453 Lane Cove, NSW 2066, Australia.