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)
AMD 259.65+2.3%3:59 PM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: combjelly who wrote (257456)12/19/2008 8:14:05 PM
From: wbmwRead Replies (1) of 275872
 
Re: At first glance, Atom has a significant advantage, 1.8GHz vs. 1GHz as top clocks. But, ARM can get more work done per instruction.

Yes, and you give several examples, but also note that Atom comes with many performance oriented features not found in other in-order architectures, such as micro-ops fusion and Hyperthreading. As a net product, I'm not sure who can claim victory in performance per clock, but you'll have a hard time convincing me that ARM can overcome a 40% clock disadvantage (assuming the 1.6GHz Netbook Atom sku).

You also mention code size, but even if we recognize that ARM can produce smaller code, it says nothing about the size of the execution path through the code, which is what actually affects performance.

You also mention new ISA instructions, but has there been a comparison between Thumb2 and SSE2 and 3? Atom includes SSE instructions, which might also benefit Intel in apps that use them. Speaking of which, what kind of Netbook applications do you expect developers to port over to Thumb2? Seems like the ecosystem advantage that Intel has will give more of a pull towards Windows based devices.

Re: Under most conditions, Atom likely does not have an IPC advantage, and the A8 likely has an advantage in work per instruction. Once the A8 makes it to 45nm, the clock rate advantage of the Atom will likely be smaller.

You've made a rather bold leap of faith to presume that given your explanation, one could conclude that Cortex has better IPC. I would at least call it ambiguous, and admit that ARM *could* have an advantage, but I'd like to see it tested. As for 45nm process enhancements, maybe you are optimistic enough to believe that a new process node without High-K and Metal Gates can get a 60% generational performance leap these days, but I remain skeptical. I see Atom continuing to lead ARM in clock speed in the high power domain of Netbooks, but things might get closer when the battle moves to MIDs.

Either way, I think I've made a point here relative to your previous claim that ARM will "mop the floor" with Atom in terms of performance.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext