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: Tenchusatsu who wrote (104505)	6/17/2000 3:18:00 AM
From: pgerassi	Respond to of 186894

Dear Tench: The only fp benchmarks that Cmine is quicker is the dirty SPEC. When compiled by standard compilers, and Intel is not a standard compiler, Cmine loses 1568MHz (2 x 784MHz) to a single 700MHz Athlon (See QMC benchmarks). VFC 4.5 (Intel) failed to compile QMC benchmark (see Tim Willkin's scientific benchmark page). Unless I see Willie benchs by third parties using current standard compilers beating Athlons, all you have is rumors. I still think that the only publically verifiable benchmarks are those whose code, compiler, and OS are public domain. Given this, the type of benchmark shenanigans that go on (on all sides) will go up in smoke. Scientific (and public) review will separate the good from the hype. If some hardware vendor wants to prove that theirs is better, they must submit, publically available source code for the benchmark program, compiler, and OS. They could simply say use an already written benchmark, say QMC, on a compiler, say gcc, on an OS, say Red Hat Linux, using the following makefile. If they want a different code generator in the compiler, they submit the public source code required to change it. Any special fix in the compiler is available to all the competitors as well. For CPU manufacturers, the validity of this method will allow the playing field to be level and the scores to be much more forceful and useful. Their will be no rocks to hide with or under, the customers can rely on time tested benchmarks, the Manu. of CPUs, Memory, Chipsets, and other hardware can have a PR bonanza, and the competition will advance knowledge for everyone. By the way, the resulting code could build diagnostic sets for determining and fixing system performance problems for the casual user. Pete

To: Tenchusatsu who wrote (104505)	6/17/2000 9:24:00 AM
From: Scumbria	Respond to of 186894

Ten, I'll tell you what I told the PowerPC advocates seven years ago ... "I'll believe it when I see it." In case you haven't noticed, PowerPC is here and blowing the socks off everyone at 300MHz. In fact, they are slated to hit 1GHz before the end of the next millenium! Scumbria

To: Tenchusatsu who wrote (104505)	6/17/2000 11:09:00 AM
From: Elmer	Read Replies (2) \| Respond to of 186894

Re: "I've yet to see that oh-so-great FPU power. Certainly Athlon has the potential, given its strong FPU" I've seen some Athlon SPECfp scores from a compaq version of an optimized compiler (not yet public) and Athlon finally pulls even with CuMine. The scores did not include TBird. EP

To: Tenchusatsu who wrote (104505)	6/17/2000 3:34:00 PM
From: EricRR	Read Replies (1) \| Respond to of 186894

And fourth, HP is planning on moving its entire server line to IA-64, starting with Itanium, and continuing with McKinley Do you have a link for this? It is my understanding that HP continues to develop there next generation RISC chips, and IBM will FAB it for them (on SOI). Doesn't this show that HP has worries about EPIC? And will Mckinley really be about to beat an Alpha? If not, what's the business model? (given the effective backward incompatibility) Merced reminds me of that giant chip project that Intel abandoned just before they threw together the first X86 chip. The saga just drags on too long...