News for hackers. Stuff that matters.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by sverige on Monday September 25, 2017 @07:35AM (#15329560)
I'm glad AMD is competitive again. Yes, Intel just surpassed them, but at twice the price. Plus, I suspect that competition pushes Intel into releasing better chips quicker.

I'm not really part of the "prosumer" market (what a word!), since I don't have a burning need for that much power, but it helps move prices lower in the middle and bottom of the performance range when the top end improves.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by kpil on Monday September 25, 2017 @08:37AM (#15329878)
The last time AMD was competitive, they delivered really good value for money. Yet they were only available in the "enthusiast" market segment as Intel were able to give all OEM strong incentives to not buy AMD.

Is there any chance that they are not having all OEMs by the balls this time too?

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by jhasse on Monday September 25, 2017 @11:23AM (#15331174)
> Intel were able to give all OEM strong incentives to not buy AMD.

They were bribing and blackmailing OEMs.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by subwayclub on Monday September 25, 2017 @02:20PM (#15332717)
If you look around, you can find AM4 platform in prebuilts from some of the biggest PC OEMs. Intel is still the majority of the lineup, of course, but APU systems have given AMD leverage here that they didn't have the last time they had competitive performance. It makes the OEMs offer the platform for an energy efficient/SFF build option, while also giving leeway to do an upgrade down the road.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by xchaotic on Monday September 25, 2017 @08:39AM (#15329891)
it's not even that, but in the OEM and server market, there's more than delivering 90% of perforamnce for 50% of the price - there's reliability, driver support and all other costs which means that a higher Intel CPU price might only translate to <5% higher TCO or something like that, in which case I'd have gone with Intel myself (no one got fired for buying IBM/Intel)
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by agumonkey on Monday September 25, 2017 @08:49AM (#15329960)
The consumer market was also forever growing at the time. Now companies are shipping less and less. Different situation I suppose.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by coredog64 on Monday September 25, 2017 @12:41PM (#15331900)
I beg to differ. The last time AMD was competitive, my employer was buying AMD server hardware from HPaq for their VMware environment. Granted, all our desktops/laptops were c2d or early core i-whatever.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by mtgx on Monday September 25, 2017 @09:29AM (#15330260)
> Yes, Intel just surpassed them, but at twice the price.

Which to me says that Intel is not competitive. If you can only release a slightly better product at twice the price, then you failed. Of course Intel's products have some branding inertia behind them, too, but that will be short-lived if the products don't become more competitive in the near future.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by smitherfield on Monday September 25, 2017 @11:44AM (#15331347)
On the other hand, you could also say that the i7-7740X[1], at a third TR's price, will (significantly) outperform TR in most real-world usage, and even for video-editing/compiling-Chromium type tasks, the $700 difference would probably be better spent on a better graphics card, more RAM or, since we're getting into overkill territory, a nicer monitor. And, in theory, I suspect that a dual-7740X build might match or beat TR in multithreaded, too.

[1] Kaby Lake-X, 4/8 cores/threads, 4.3/4.5 freq/turbo, $329

https://www.anandtech.com/show/11549/the-intel-kaby-lake-x-i...

https://www.anandtech.com/show/11697/the-amd-ryzen-threadrip...

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by Dylan16807 on Monday September 25, 2017 @01:06PM (#15332128)
That's a different category, though. The competition for low core count is Ryzen. Perhaps a 1600X. 6/12 cores/threads, 3.6 boosts to 4.0/4.1, $249.

> And, in theory, I suspect that a dual-7740X build might match or beat TR in multithreaded, too.

Is that possible? And I really doubt you'll get 8 cores to beat 16.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by smitherfield on Monday September 25, 2017 @01:29PM (#15332292)
>>>That's a different category, though.

My point is it's the category most enthusiasts would be happiest with, even if they think otherwise.

>>>Is that possible?

Looks like I was mistaken, I thought the Sky/Kaby Lake-X chips used the same socket as the Xeons. So no.

>>>And I really doubt you'll get 8 cores to beat 16.

If it were possible, it would be 8 cores operating at a 50% higher frequency (with substantially more room for overclocking, too) and that support AVX-512 instructions. And you get quickly-diminishing returns from throwing more threads at a program (just mathematically, even if it's embarrassingly parallel and CPU-bound, each time you double the threadcount you get half the improvement of the previous doubling).

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by Dylan16807 on Monday September 25, 2017 @02:22PM (#15332734)
> My point is it's the category most enthusiasts would be happiest with, even if they think otherwise.

That's fine, but use that category for both manufacturers.

> 8 cores operating at a 50% higher frequency

26% higher base, 10% higher boost.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by reitzensteinm on Monday September 25, 2017 @03:53PM (#15333526)
Kaby Lake-X does not support AVX-512...

With 3 glaring factual errors across two posts, I'm going to go out on a limb and suggest to you that the average enthusiast purchasing Threadripper is in fact more aware of the trade offs between the products available on the market than you are.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by kbart on Monday September 25, 2017 @08:32AM (#15329845)
Same here. I haven't upgraded my home PC for almost 5 years now, even though I do some digging from time to time to see if there's something worth buying in a middle tier. So far, it was simply not worth upgrading, I hope things will change soon. Heck, even GPU bought back in 2013 is still doing well (I remember times when 1 year old GPU was considered obsolete, even in a middle tier).
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by chiph on Monday September 25, 2017 @01:54PM (#15332501)
I just upgraded the gaming PC from an i7 2600 (ancient) to a Ryzen 7 1700. So far, video encoding is significantly faster with all 16 logical CPUs busy (but a GPU based program would be stupid fast). I'm having an issue where I get occasional lockups when gaming - updating the BIOS hasn't helped. I expect the game makers will need to ship updated code. One thing I found - the Ryzen is very sensitive to memory speed. Buy 2666 and don't overclock it much - if at all.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dingo_bat on Monday September 25, 2017 @08:54AM (#15329983)
I think you'd see a significant improvement now with Ryzen 7 or threadripper. Unless you spent >$3k on your rig ;)
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dagw on Monday September 25, 2017 @10:52AM (#15330924)
That depends very much on what you use your machine for.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by geezerjay on Tuesday September 26, 2017 @03:48AM (#15336916)
> That depends very much on what you use your machine for.

In generally it actually doesn't. The AMD Ryzen 7 1800x is selling for less than half the price of an Intel i7-6900k ($420 Vs $1010), and in benchmarks the Ryzen system beats the i7 or practically matches the performance.

Getting the same performance for 40% of the cost is something that does not depend on your use case.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dagw on Tuesday September 26, 2017 @07:14AM (#15337663)
Getting the same performance for 40% of the cost is something that does not depend on your use case.

Sure, but in many cases the practical difference between an Intel i7-6900k and for example an Intel i3-7XXX (or a 4 year old i5/7) is basically negligible, and the i3 is less than half the price of the Ryzen

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by jokoon on Monday September 25, 2017 @08:48AM (#15329946)
I wonder, what makes intel chips more expensive? Is it a matter of money sunk into research? Because it seems that in terms of FLOPS per $, AMD always wins, and I have a hard time understanding that.

What makes AMD more interesting?

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dogma1138 on Monday September 25, 2017 @12:06PM (#15331545)
Intel operates at 60% gross profit margin, AMD operates primarily in the red. In the past 15 quarters AMD had a single quarter in 2014 where it didn't suffered an operational loss (when the bulk of this generation of console royalties were paid out most likely)
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dingo_bat on Monday September 25, 2017 @08:53AM (#15329978)
> I wonder, what makes intel chips more expensive?

The fact that if you want a chip that powerful, there is only Intel. An example in GPUs are the NVIDIA Quaddro cards. If your frame needs more than 16GB memory to render, there is no other card available. So they sell the same chips packaged as a Quaddro at 5x the price of a Titan.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by smitherfield on Monday September 25, 2017 @09:19AM (#15330159)
I believe the biggest reason the workstation/enterprise GPU lines (AMD’s too) are priced so much higher than the gaming/consumer lines is because the “certifications” for CAD[1] and 3D graphics[2] software cost a king’s ransom plus require expensive testing and validation of every individual card before it’s sold.

[1] http://www.nvidia.com/object/quadro-design-and-manufacturing...

[2] http://www.nvidia.com/object/media-and-entertainment.html

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by gsnedders on Monday September 25, 2017 @09:42AM (#15330374)
> The fact that if you want a chip that powerful, there is only Intel.

How does, e.g., POWER8 compare? (And POWER9, soon?)

That said, POWER tends to be even more expensive than this.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by walki on Monday September 25, 2017 @10:09AM (#15330595)
> How does, e.g., POWER8 compare? (And POWER9, soon?)

POWER8 is not well suited for HPC workloads as their vector instructions (VMX/AltiVec) are only 128-bit wide vs Intel's latest Skylake Xeon CPUs have vector instructions (AVX512) that are 512-bit wide.

For non HPC workloads (e.g. integer arithmetic) the POWER8 CPUs were somehow competitive with Intel's CPUs when they were first released in 2015 but today AMD and Intel's CPUs are clearly faster.

From what I can tell CPU enthusiasts were not impressed by the POWER8 CPU architecture.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by Dylan16807 on Monday September 25, 2017 @12:54PM (#15332019)
But for any particular version of "that powerful", the exclusivity doesn't last long. The burning need for hardware that didn't exist a couple years ago and will be mainstream in a couple more years isn't all that strong.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by bsenftner on Monday September 25, 2017 @10:00AM (#15330514)
It is not so much a "chip that powerful" but a "chip that correct". Gaming GPUs are allowed errors because the rendered images are known to be visual output only, whereas an engineering GPU may be used for hard analysis, which cannot afford any rounding or other classes of the acceptable errors gaming GPUs are allowed.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by tomsmeding on Monday September 25, 2017 @10:31AM (#15330784)
Do you have a source for those claims? It seems highly unlikely to me that certain types of cpu's or gpu's are allowed errors to cut costs. Rounding mechanics are complicated, but I'd say a bug is a bug. As mentioned in a comment by jackmott in this thread, "engineering purposes" also often actively reduce precision for increased performance.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dijit on Monday September 25, 2017 @12:49PM (#15331966)
Double precision floating point and the addition of ECC memory.

In the case of nVidia the quadro cards are the only ones sold as manufactured by the company and are incredibly high binned.

Lots of people on this thread are conflating a few things such as ML, but I work in an industry where we deal a lot with GPUs and its certainly a fact that flipped bits are significantly more common than many think. If you do any work that requires the output to be nonvolatile then you can run into issues.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by NoPiece on Monday September 25, 2017 @12:51PM (#15331994)
Perhaps he is referring to ECC memory - high end pro model NVIDIA cards have it, and consumer cards don’t. Here is a paper showing that there are memory errors on the consumer non-ecc cards.

http://ieeexplore.ieee.org/document/5493404/?arnumber=549340...

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by eloff on Monday September 25, 2017 @10:17AM (#15330673)
Are you talking about double-precision floating point math? Or are you saying the gaming chips actually have issues?
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by jackmott on Monday September 25, 2017 @10:24AM (#15330731)
It is just complete nonsense. In fact deep learning/AI chips used for neural networks usually have reduced floating point precision because they don't need it.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by freeone3000 on Monday September 25, 2017 @05:24PM (#15334305)
We don't need it because errors in any particular value aren't important - the calculations assume an amount of inherent error greater than that produced by the hardware.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by smitherfield on Monday September 25, 2017 @10:57AM (#15330953)
Deep learning is still a fairly new and small field, scientific computing workloads are usually mostly double-precision.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by jackmott on Monday September 25, 2017 @10:18AM (#15330683)
nonsense
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by detaro on Monday September 25, 2017 @08:51AM (#15329965)
Other way around: AMD has to be cheaper to compete with Intel, which until now basically could charge what they wanted.

And this specific example here is clearl in the high-end enthusiast space, where whoever has the best can charge the highest price and the target market will pay it.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dmix on Monday September 25, 2017 @09:04AM (#15330056)
Costs of production rarely determine prices directly for any product - beyond setting the baseline from which the margin measures on. Market dynamics tend to do the rest (competition, market position, etc). Intel plays a role in it but not always.

There may be some that are down to the wire per unit cost (typically the cheaper ones) but I have a feeling Intel operates with plenty of margin on most of their higher end products. And plenty of them are the same chip repackaged.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by arca_vorago on Monday September 25, 2017 @12:04PM (#15331533)
For me, AMD tends to do better with multithreaded/parallel applications, but that tradeoff is at the expense of single core speeds. So mostly it depends on what you are using it for. I built a 64 core opteron server for doing physics calculations and it was probably my favorite build ever, so I can't wait to try the new AMD server lineup, this time I'll only need two CPUs to get 64 cores!
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by vbezhenar on Tuesday September 26, 2017 @06:36AM (#15337522)
For price of 7980XE you can buy Epic and have even more performance, if you care about multithreading.

The only thing that Intel surpassed them is single-thread performance. It's important even on workstation, IMO, that's the main reason I'm thinking to stick with Intel for now, everything else AMD made better.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by indescions_2017 on Monday September 25, 2017 @09:19AM (#15330166)
Me too ;) And with ROCm support for deep learning frameworks such as Tensorflow, GPU price competition aids in "democratizing" AI.
Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dogma1138 on Monday September 25, 2017 @09:34AM (#15330302)
Tensorflow isn’t supported yet. The ROCm libraries are optimized for AMD hardware explicitly this isn’t democratizing anything it just locks you into a different vendor other than NVIDIA.

If anything AMD should follow NVIDIA in supporting OpenACC which is the way to go as far as true probability goes.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by AlphaSite on Monday September 25, 2017 @12:02PM (#15331501)
Doesn’t ROCm compile to amd’s libs for AMD GPUs and cuda lins for Nvidia gpus?

It doesn’t matter that the rocm libs are optimised for AMD.

Re:Intel Core i9-7980XE and Core i9-7960X CPU Review Part 1:... by dogma1138 on Monday September 25, 2017 @12:24PM (#15331721)
No, ROCm is an amalgamation of a lot of things and it's been very inconsistently represented, you are thinking of HIP which in theory should that but in practice it's a tool to more easily convert CUDA applications to ROCm, since while you can in theory use NVCC as a backend for HIP the design directive for HIP make it nonviable.

In all effectiveness ROCm is AMD's version of CUDA it includes it's own run time and driver stack which effectively replaced the OpenCL frontend for AMD GPUs, basically it gives AMD the ability to do with their GPUs what CUDA allowed NVIDIA to do and it's not to be dependent on a camel (OpenCL).

This is what ROCm is: https://rocm.github.io/images/ROCm_Stack.png or at least this is what AMD is pushing it to be, currently a lot of things are still unfinished or non-existent.

The representation of it being open is misleading, while more of the source code is available than for CUDA, ROCm isn't vendor agnostic on any tangible level. In 2-3 years once it's somewhat in a production ready state it will lock you into a single vendor just like CUDA does.