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: Tenchusatsu who wrote (40129)	10/26/1998 2:57:00 PM
From: Ali Chen	Read Replies (2) \| Respond to of 1573829

Ten, <AGP is far from useless, my friend.> Really? If you are not familiar with motivations for your own products, read on: ftp://download.intel.com/pc-supp/platform/agp20.pdf This is a 3MB .pdf file, so I made an excerpt for easy readings: page1: "1.1 Motivation In general, 3D rendering has a voracious appetite for memory bandwidth ... requiring high speed access to ever larger amounts of memory, thus raising the bill of material costs for 3D enabled platforms. Containing these costs while enabling performance improvements is the primary motivation for the A.G.P. By providing up to an order of magnitude bandwidth improvement between the graphics accelerator and system memory, some of the 3D rendering data structures may be effectively shifted into main memory, relieving the pressure to increase the cost of the local graphics memory. Texture data are the first structures targeted for shifting to system memory for four reasons: 1. Textures are generally read only ...blah-blah, 2. Shifting textures balances the bandwidth ... blah-blah; 3. Texture size is ... blah-blah; 4. Texture data is not persistent.. blah-blah; ... Reducing costs by moving graphics data to main memory is the primary motivation for the A.G.P., which is designed to provide a smooth, incremental transition for today's PCI based graphics vendors as they develop higher performance components in the future." ----------------------------------<end of AGP quote> So, as you see, the whole motivation behind the AGP were textures, textures, and more textures. What was miscalculated here are FOUR (!) things. First, the AGP is not for free for system performance - continuous pumping of textures does interfere with system eating up the precious system performance. Second, the AGP is good only on streaming data, but for other plain 2-D tasks they had to keep a back door, in a form of supplementary PCI-like channel, but with lower performance than regular PCI! Third, the whole idea assumes that Intel' CPU will be capable to provide the whole rendering while they can't keep the pace with specialized 3D rendering hardware for obvious reasons. Forth, manufacturers of video DRAMs did not sleep on laurels and come up with affordable products. If you check out, say, BestBuy, you may find out a bunch of 3-D video cards with 16MB of memory, for just $129! This is the market answer to Intel's AGP "innovation" - 16MB Voodoo-accelerated card for $129. Any more questions, my dear Intelfriend?