CHADBOGA
Platinum Member
Not only that, but the little cores don't have SMT, so it will be 24 threads vs 32 threads.I don't see how 8 big cores and 8 little cores beats 16 big cores. Could happen, I guess. I wouldn't count on it.
Not only that, but the little cores don't have SMT, so it will be 24 threads vs 32 threads.I don't see how 8 big cores and 8 little cores beats 16 big cores. Could happen, I guess. I wouldn't count on it.
Pros: Something tells me Intel will take the performance crown away from AMD, not just today, but will best what AMD has next
It's an unannounced goal for the lowest power chips to get nearly identical performance in single thread.
I don't see how 8 big cores and 8 little cores beats 16 big cores. Could happen, I guess. I wouldn't count on it.
the new intel launch is a little strange. big (Golden Cove) and little (Gracemont) cores in the design. Other features such as PCIe 5.0 and DDR5 should be present as well.
IF so they say it comes out in March and motherboards come out second half?????
We might see AMD waiting tooooo long for zen 4
AMD also said Zen 3 was in design phase at the end of last year. Either way, I wouldn't worry too much about it.AMD needs Zen 4 sooner than later, they will definitely lose the ST crown against Golden Cove since Zen 3 seems to have only a slightly better IPC than Sunny Cove which is a 2017 design. Next year Warhol is next which still uses Zen 3 cores. AMD said a few days ago that Zen 4 is in design phase currently, this is in big contrast to ADL-S which is up and running fully enabled with all cores.
AMD also said Zen 3 was in design phase at the end of last year. Either way, I wouldn't worry too much about it.
It has been 9 days. Will you please now tell us exactly what you wanted to say?We can continue this discussion in a week or so.
I stand corrected, you're absolutely rightThis is not true, AMD revealed it in August: https://www.techradar.com/news/amd-zen-3-has-finished-its-design-phase-rumored-to-launch-in-2020
Zen 4 is still in design phase in October which makes sense because they are bringing a refresh release next year.
No can do, still waiting for something else to happen.It has been 9 days. Will you please now tell us exactly what you wanted to say?
paired with 8 Atom cores that are utterly useless in the desktop power envelope.
Golden Cove will certainly take the ST crown. It'll be interesting to see how big an upgrade it will be (hopefully big).AMD needs Zen 4 sooner than later, they will definitely lose the ST crown against Golden Cove since Zen 3 seems to have only a slightly better IPC than Sunny Cove which is a 2017 design.
Nevertheless it's a bit unfair to compare Zen 3 to Sunny Cove, as it's a higher frequency design (reaching 4.9 on TSMC 7nm) while Sunny Cove couldn't really clock past 4.0. WIllow cove is essentially Sunny Cove that clocks well and has minor improvements. It's a better comparison to Zen 3.
So this means that intel did nothing with Willow Cove arch? Despite them flat out mentioning they decided not to chase IPC to get the clocks up.IPC has nothing to do with how high a core can clock, hence IPC. Also, it was the process node (10nm) that limited Sunny Cove clocks, not the uArch.
Nevertheless it's a bit unfair to compare Zen 3 to Sunny Cove, as it's a higher frequency design (reaching 4.9 on TSMC 7nm) while Sunny Cove couldn't really clock past 4.0. WIllow cove is essentially Sunny Cove that clocks well and has minor improvements. It's a better comparison to Zen 3.
It should be useful in mobile.
And I would not expect the Sapphire Rapids Golden Cove Core to be much different than that of Alder Lake's Big Core. Other than the mesh and more big cores.
Haven't been paying enough attention, obviously, but that is a *****g sad regression.When I was still at Intel, Sapphire Rapids was supposed to be a from-scratch design. The fact that it has become a small evolution is quite telling of Intel's design woes.
Sure, it would be useful in mobile, if the Intel big core becomes so inadequate that an undervolted/underclocked big core actually gets beaten by an overcharged Atom.
When I was still at Intel, Sapphire Rapids was supposed to be a from-scratch design. The fact that it has become a small evolution is quite telling of Intel's design woes.
Lol, where on earth did you hear that? I thought you were just obviously trolling before, but since some people are taking you seriously, might as well point out that this, as well as your previous comments, are all 100% BS.
You also have to factor in per mm2. There's some amount of workloads that 4 Atom cores would beat an big core.
You heard wrong then. Simple as.Heard it inside an Intel office building while I was still working there as a CPU design engineer, from people on that very project before it got canned and most of the good people involved left Intel.
Heard it inside an Intel office building while I was still working there as a CPU design engineer, from people on that very project before it got canned and most of the good people involved left Intel.
You heard wrong then. Simple as.
Lol, sure you did. As evidenced by your hysteria about literally every project they have in the pipeline. We know it has, at minimum, a new core, new PCIe, and new DDR. And there's more than that. In what world is that incremental?