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.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: combjelly who wrote (43394)	6/8/2001 12:18:55 PM
From: Jim McMannis	Respond to of 275872

RE:"Oh yeah, a representative of 3DPower was there and said the company will have an announcement about 3Dfx sometime today. Wish I knew what THAT was about. Anyway, we are supposed to check their website at 3dpower.com for the details. I checked earlier and there was nothing, but hope springs eternal..." Supposedly 3DPower is going to resurrect 3DFX. It's been floating around on the net for at least 6 months. Supposedly a bunch of ex 3DFX engineers have joined in. I'm not sure what Nvidia got when the bought 3DFX but it wasn't all. Jim

To: combjelly who wrote (43394)	6/8/2001 12:22:21 PM
From: peter_luc	Respond to of 275872

Thanks for the interesting report! <eom>

To: combjelly who wrote (43394)	6/8/2001 12:52:58 PM
From: andreas_wonisch	Read Replies (3) \| Respond to of 275872

Combjelly, Re: Let see, the 4.2GBytes per second is split evenly between the video and the CPU/everything else. What happens if you use an external video card? Does the CPU get all the bandwidth then? Andreas PS: Thanks for the interesting reports. Sounds promising to me.

To: combjelly who wrote (43394)	6/10/2001 11:48:49 AM
From: dale_laroy	Read Replies (1) \| Respond to of 275872

>Let see, the 4.2GBytes per second is split evenly between the video and the CPU/everything else.< This is what Ace's Hardware was claiming all along. Curiously, when the actual announcement was made on June 4th, Ace's claimed they were previously wrong, and the bandwidth is shared as two 64-bit channels to both GPU and CPU rather than being two separate 64-bit channels. They even had a description of the crossbar switch in their article. >the greater IPC is surprising since the Hammers are also supposed to have a deeper pipe.< What I am wondering about is if Hammer has some type of multithreading. Even with Coarse Grained Multithreading Clawhammer could easily exceed the IPC of Barton in multithreaded situations, yet this would not translate to higher, or even equal, IPC in single threaded situations.