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: Tenchusatsu who wrote (67273)8/2/1999 12:29:00 AM
From: Charles R  Read Replies (2) of 1573967
 
Tenchusatsu,

<<Timna doesn't have SSE.>
It doesn't? How do you know?>

I could be misinformed but I thought Timna had the PII core but I don't know about Timna-refresh. May be you can correct me.

Also, check out this from Aces - the new 3Dnow instructions (not used in the original benchmarks used by Dirk Meyer, if my memory serves me right) are starting to do some magic.

*************Begin Clip**************

Now thanks to WaterCooler again for some of his wonderful posts on C't's K7/Athlon review.
First we have the SPEC95 scores using P6 optimized binary here which are done by C't.
SPECfp95(base)/SPECint95(base):

K7600 21.5 / 27.1
PIII600 14.8 / 24.8
PIIIXeon550 14.8 / 24.2

Now for some 3Dmarks99 from this post. :)

CPU regular X87 Regular 3DNOW/SSE K7 special 3DNOW
K7 600 6225 10434 12168
PIII 600 5504 9112
K6-3 450 2639 6857 crash

So one can see that with regular 3Dnow K7/Athlon gains about 68% over its X87 speed, while PIII 600 gains 66% with SSE. On the other end K6-3 does gain 160% with 3dNOW and with the new 3Dnow instructions K7 gains about 96% which shows the potential of the new instructions (a congrat to the AMD engineer who wrote the special codes for 3dmark99) .

*******************End clip*****

Chuck
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext