SI
SI
discoversearch

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
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Duncan Baird who wrote ()2/22/2000 11:52:00 AM
From: Epinephrine  Read Replies (1) of 1571597
 
Thread,

Please read this!! Am I hallucinating????? (Especially the PPS at the end)

I haven't seen this posted yet. According to JC, Johan at Ace's has revised his Willamette article. He says that he was under the mistaken impression that Willamette had two ISSE2 units but it really only has one. The following text used to say 11.2 billion floating point operations instead of the 5.6 that it now claims.

"Intel is concentrating on ISSE2: No less than 144 new instructions. If Intel can rally enough support behind ISSE2, the Willamette FPU performance will blow everybody else out of the water, as the ISSE2 FPU performance is vastly superior to the x87 in single precision. A ISSE2 unit at 1.4 GHz, the clockspeed at which the fastest Willamette will ship (Q4 2000), would boast a peak of no less than 4 (SIMD) x 1.4 GHz = 5.6 billion floating-point operations per second (or FLOPS)! The x87 FPU would deliver a 'measly' 1.4 GFLOPS peak.
For comparison, if AMD manages to introduce a 1.2 GHz Athlon by the time the Willamette ships, the x87 FPU will peak at 2.4 GFLOPS, while the 3DNow! units will peak at 4.8 GLOPS."

Did you see what I do. The Athlon will do 2.4 GFlops on regular X87 floating point code and the Willamette will only be capable of 1.4GFlops!!!! If I am doing my math right that means that the Athlon is theoretically 42% faster (2.4GFlops as opposed to 1.4GFlops) than the Willamette at unoptimized code but the Willamette is only theoretically 15% faster than the Athlon (5.6GFlops as opposed to 4.8GFlops) on code optimized for each respective processor. Am I missing something here?

Thanks,

Epinephrine

PS: How do you do bolds and italics?

PPS: I just re-read that clip from Aces again and realized that their theoretical calculations were comparing a 1.4GHz Willamette to a 1.2GHz Athlon!!!!!! What am I missing here, blow holes in this please because I think I am dreaming!!
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News