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 -- Ignore unavailable to you. Want to Upgrade?


To: porn_start878 who wrote (114024)6/3/2000 12:55:00 PM
From: kash johal  Read Replies (2) | Respond to of 1572918
 
Max,

Re: Athlon/Tbird performance.

Yup so far the performance is less than compelling although these 700's may have been crippled somewhat.

However the Duron's performance seemed faster than Athlon classic.

I suspect the Duron will be a much better value than the tbird, but the same can be said for celeron and cumine.

However Intel cripples the memory bus on celery for differentiation - which seems pretty smart.

I see duron/tbird being very similar performance on a clock 2 clock basis at least until the 760 and DDR in Q3.

In the meantime he key for tbird/duron is DECREASED cost, INCREASED MARGINS for AMD as opposed to killer performance.

regards,

Kash



To: porn_start878 who wrote (114024)6/3/2000 12:58:00 PM
From: dougSF30  Read Replies (1) | Respond to of 1572918
 
(1) M__a__x makes a good point about cache / 700MHz

The 1GHz tbird should womp all other the 1GHz athlon, since the latter runs with 1/3-speed L2.

(2) c't says they couldn't get a processor to test from AMD, and procured this 700 MHz CPU through "other channels".
Might this be an early engineering sample? Might improvements have been made in the production silicon?

I expect we'll know in... 36 hours or so, but it's fun to speculate. Comments?

Doug



To: porn_start878 who wrote (114024)6/3/2000 3:12:00 PM
From: Scumbria  Read Replies (3) | Respond to of 1572918
 
Max,

T-Bird is not going to show a huge performance improvement over Athlon on most benchmarks.

The reason is very simple. Athlon has a huge (128K) L1 cache, which gets a high hit rate. Speeding up the L2 for the infrequent L1 misses will produce only incremental performance improvement.

This is a different situation from the PIII->Coppermine transition, because PIII has a small (32K) L1 cache.

If there is a big performance bonus from T-Bird, it may be in clock speed from Dresden. Don't count on big benchmark numbers from T-Bird, because you will be disappointed.

Scumbria