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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Paul Engel who wrote (119204)	11/25/2000 5:52:55 PM
From: Sam P.	Read Replies (1) \| Respond to of 186894

Paul, I suggest that you are one of my preferred liars if you insist I make a choice.

To: Paul Engel who wrote (119204)	11/25/2000 5:57:52 PM
From: Tenchusatsu	Read Replies (5) \| Respond to of 186894

*Tom's third* article on Pentium 4: tomshardware.com Seems Tom's tone is changing once again, and this time, it's due to the efforts of a few Intel employees in Munich. These employees basically took the source code of the MPEG4 encoding software and recompiled it using Intel's Compiler 5.1 on various settings. Here are some interesting tidbits that I gleaned off of the article: 1) Pentium 4 performance increased by a factor of 3.6** on the High Quality iDCT settings. This is a straight recompile without SSE or SSE2 instructions. 2) Pentium 4 performance increased by another 35% using SSE2 (beyond #1 above). 3) The performance of Pentium III increased by 83% with a straight recompile (no SSE or SSE2). 4) Interestingly enough, the performance of AMD Athlon increased by 73% with a straight recompile. This just goes to show that even AMD's Athlon benefits from Intel's compiler. (I suppose this version didn't use 3DNow. It's unknown to anyone what kinds of improvements we'll see from compilers which optimize specifically for Athlon.) 5) All these results were obtained by doing quick-n-dirty recompiles with Intel's compiler. No additional effort was made to improve performance in other ways, like profiling, hand-crafted assembly code, alternative encoding algorithms, etc. I encourage everyone to read the article for themselves. It makes for some very, very interesting reading. Hopefully it also sheds some light on the performance situation with Pentium 4, both legacy and future. Tenchusatsu