Help me here: were was ever staded max 95W TDP for Zen? Because everyone says that but I can't find the original source, it almost seems like a fixation...
Google AMD zen 95W ??.
Help me here: were was ever staded max 95W TDP for Zen? Because everyone says that but I can't find the original source, it almost seems like a fixation...
Help me here: were was ever staded max 95W TDP for Zen? Because everyone says that but I can't find the original source, it almost seems like a fixation...
95W sounds about right for 6-cores at high IPC and frequency but it's quite limited if you have 8-cores. Unless the turbo speeds are much higher than stock, then it could work but it would need decent cooling.
In regard to that... if wraith cooler is any indication 125W TDP is a more plausible estimation for the top Zen. Why design a new cooler and don't make it compatible with an incoming product?
One can say that if overclocking brings 8c zen from 3.3 single core to all cores 3.8 at hsw ipc level at say 400 usd on a cheap mb most desktop users wouldnt care if tdp got to 160w. It would be a slam dunk imo.
Well they can run it 95w tdp then. Something no 8c intel cpu can do but that doesnt mean all change to zen
Naw, people are all over lower power. You see it in the AMD threads; the 390x is faster but uses more juice so get a gimped 970. The 380x is faster but uses more juice so get a 960.
'Course, that's GPUs, but the same applies to CPUs. AMD has to have good performance AND lower power, if they're gonna sway the enterprise buyers.
That's not IDS values there or TEV detailsAll is in the second slide of Aten Ra s post, FTR dynamic power was measured at 0.880V, wich tell us that at this voltage everything is perfect, they wouldnt use value that would crush the metrics, wouldnt they..?..
Beside if it cant do 1V it would be a first in the industry, dont count on such irrationnal theories..
Not a quotable person, at all.It seems pretty clear what the Red Team+ member is saying. It seems to me that you are just attacking juanrga because you don't like him.
See above. That's also not how semiconductor physics works. You can see it explained thoroughly in the IBM paper.The limitation is in the transistor power dissipation, if shrinked 1.4x they will have 2x less area, so their perf/watt should be increased by 2x if you want to operate them at same frequency.
Intel s 14nm didnt improve much their perf/Watt compared to their 22nm, i once stated it ad nauseam but seems people are keeping using them as if they were the end of all, 14nm LPP work at lower voltage for the same frequency, so the individual transistors dissipation will be less in a square proportion of the voltage, that s physics laws and is not much subject to any debate set apart correcting absolute values of various parameters.
Powerpoint process metrics does not equal actual complex logic implementations. Nor are those graph readings as simplistic as some AnandTech bar chart.
I've seen 3.33 GHz predicted as the base clock for 8c/16t 95w TDP Summit Ridge with 4.0 GHz being the top turbo bin. So I'm going with that for now, seem plausible?
Sorry to repeat myself, but I agree 100% with AtenRa that Summit Ridge needs to beat XV in MT workloads on a core-per-core vs. module-per-module basis, or otherwise it'll be a disappointment. We could have had 4-8m XV last year if AMD had really wanted it. I would love to have gotten a chip like that in 2015.
Sorry to repeat myself, but I agree 100% with AtenRa that Summit Ridge needs to beat XV in MT workloads on a core-per-core vs. module-per-module basis, or otherwise it'll be a disappointment. We could have had 4-8m XV last year if AMD had really wanted it. I would love to have gotten a chip like that in 2015.
I'm sad that you set your expectations to unreasonably high levels AMD promised 40% IPC improvement over Excavator and you say that you will be disappointed if it doesn't provide > 84% (e.g in Cinebench R15)? What 84%? That is what the second core in a CU is worth, in Cinebench R15 (CMT yield). Even if the SMT yield (>= 25%) is for some reason included to the core to core comparison, it still wouldn't be enought to make up the required difference.
Zen is also the most unhyped processor in a while. Were you also around when some were convinced Zen was only a low power, low performance design? :sneaky:Zen is probably the most hyped up processor in the history of X86 processors. I was around for the hype around Barcelona and Bulldozer, and it did not compare to this.
Zen is also the most unhyped processor in a while. Were you also around when some were convinced Zen was only a low power, low performance design? :sneaky:
Yeaa. Just shows there is a huge low freq but high efficiency/density market here.Yeah, there is this one too, so Intel can certainly do it, which probably means AMD can do it, or get close to it.
http://ark.intel.com/products/93806/Intel-Xeon-Processor-E7-4850-v4-40M-Cache-2_10-GHz
16 cores, 40M cache, 2.1/2.8ghz, 115W tdp.
I made no insinuation towards you.I was around and if you check my post history you will see that I was against this, given that AMD itself was saying that Zen was a high performance design.
That's why I mentioned the low power scenario, there will always be people choosing unlikely scenarios. Doesn't mean most people following this thread believe Zen is a Skylake-X killer.Anyway, Zen has gone from, "oh hey, hope we can get SNB-levels of IPC" to "it's going to be faster than 5960X with 2/3rd the TDP."
I was around and if you check my post history you will see that I was against this, given that AMD itself was saying that Zen was a high performance design.
Anyway, Zen has gone from, "oh hey, hope we can get SNB-levels of IPC" to "it's going to be faster than 5960X with 2/3rd the TDP."
By the eve of the launch, I wouldn't be surprised if people will be predicting that 8C/16T Summit Ridge will be a 10C/20T Skylake-X killer. For $299, of course.
1 or 2 people with super high expectations is no where near what bulldozer had.
it doesn't matter how many times you repeat it, zen just doesn't have the hype bulldozer did. large swathes of the forum were expecting intel to get conroed. this time around? most people are just hoping amd gets back into the big leagues.