Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Scumbria who wrote (114058)	6/4/2000 1:26:00 AM
From: Joe NYC	Read Replies (1) \| Respond to of 1573430

Scumbria, The video refresh bandwidth is a small portion of the required bandwidth for the graphics subsystem. Yes, but we are talking about Timna. I don't know what kind of bandwidth today's graphics cards have. I know it is a lot higher than the main PC memory. Did I make a mistake in my calculation? 1024 x 768 x 4 bytes per pixel x 85 times per second. I get 267 MB per second. I don't know what the latest memory technologies are in use now, but I know sometimes in the past, they used to have multiport memory, so that the memory buffer could be continuously read, without interupting writing new information to video memory. Anyway, my 267 MB per second includes only reading the buffer. Writing stuff to video memory requires additional bandwidth. And again, I am assuming that Timna will have only 1 memory interface, which will be shared between CPU and Graphics. Texture memory and framebuffer accesses suck up large amounts of bandwidth, and these too will have to be shared with the CPU. Oops, I should have read the second sentence before replying to the first. We may be in an agreement, except maybe I don't know the correct terminology. What do you call "video refresh" and what do you call "framebuffer access". I was talking mainly about framebuffer access. Joe