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


To: smooth2o who wrote (191931)4/4/2006 1:37:39 PM
From: combjellyRead Replies (1) | Respond to of 275872
 
"From all I read, there's no reason to believe that K8L will have any more FP performance than Conroe."

Nor any reason to believe it will have less. So, for floating point, it will come down to clock rate for stuff running out of cache and for random access, latency to memory. Since it looks as if K8L will be better on both...



To: smooth2o who wrote (191931)4/4/2006 1:42:13 PM
From: j3pflynnRead Replies (1) | Respond to of 275872
 
smooth - That's just silly. Charlie has been very open about Conroe and Woodcrest being solid CPUs, and about the fact that AMD has to execute to keep up. On the other hand, in the past week or so, he seems to have gone very sour on Intel's future, perhaps he's seen something that isn't public knowledge yet? I don't get any sense at all of Charlie resenting "Conroe stepping on AMD's toes", as you put it.



To: smooth2o who wrote (191931)4/4/2006 1:46:37 PM
From: mas_Respond to of 275872
 
If you connect the K8L dots it looks like it will have 4 DP Flops/cycle in both Scalar and SIMD whereas Conroe will be 2 and 4 in these areas. It will be very hard on IPF's FP niche if true.