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: Elmer who wrote (120377)7/16/2000 10:02:05 PM
From: Epinephrine  Read Replies (1) of 1571423
 
RE:<My point is simply this. Athlon and CuMine are so close that neither is entitled to claim superiority much less claim to be a generation ahead.>

Elmer,

You seem to be claiming two things, let's take them one at a time. To me they are:

1) The Coppermine platform as it currently stands, taken as a whole, is competitive with the Athlon platform in it's current state.

2) That somehow the fact that Coppermine is competitive with the current manifestation of Athlon debases the K7 core's claim to architectural superiority.

Ok, on #1 we agree. It's #2 that is my point of contention. I could list for you all the ways that K7 core is undebatably a superior architecture but I will let you do your own research and will only list one example... The triple issue FPU.

As we both know the K7 core has a triple issue FPU whereas the P6 core has a double issue FPU. I am not a CPU architect so verify this for yourself but as I understand it the word "issue" refers to an instruction pipeline. Both the K7 core and the P6 core have one of those instruction pipelines allocated to decoding instructions. The second pipeline on the P6 core performs addition and multiplication whereas on the K7 core addition and multiplication both have their own respective pipelines. This means that the K7 core can perform an addition operation and a multiplication operation at the same time whereas the P6 core must perform the operations sequentially. I believe that the multiplication pipeline on the K7 core can also do addition if there is no multiplication needed. In essence all this means that the K7 core can inherently process more instructions per clock than the P6 core. This is fundamental superiority by design

This is just one of the architectural points that makes the K7 core undebateably faster and more efficient by design (read superior) than the P6 core.

If it makes you feel better to think that the fact that AMD is not utilizing it's core to it's fullest potential yet proves that the K7 core is not an inherently superior design to the P6 core then be my guest.

But that does not change the fact that the K7 core IS superior. Whether or not AMD can capitalize on that superiority and extract better performance is something that is subject to debate but whether or not the K7 core is fundamentally superior to the P6 core is not. The fact that you would debate that tells me one of three things:

1) you do not understand the architectural details of the respective cores well enough to realize the truth

2) you do understand but your bias is making you turn a blind eye

3) you do understand and you know the truth but you are just goading us (me).

I don't know whether to hope that it's #2 or #3, I don't want you to be turning a blind eye buy I'd like to think that you wouldn't be wasting all our time just to stir up sh|+

Regards,

Epinephrine
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