Yup. And while correcting: > Against AMD counterparts, that 5.0 GHz frequency carves through anything like butter.
That is rather optimistic... the Intel is frequently bested by the 3700x and especially the 3900x - I would expect a 3950X might even win the majority of tests run here.
I went ahead and did a quick count: * 3900X has 13 wins (7 more than 10%) * 9990XE has 21 wins (10 more than 10%)
Now obviously the 9990XE is faster, but it better be with 2 more cores and 5 ghz and 400 watt power use and a price - well... ;-)
But it sure isn't the slam dunk it is described at - Ian writes like this monster wins in >90% of the tests, which it doesn't, not by a long shot. If it was readily available at $600 and had a TDP of 140W, I'd call it a winner, even if it doesn't *always* win. But if intel has to go THIS extreme and still loses in over 1/3rd of the graphs here at Anandtech, it is more a show of weakness if anything.
And all that while we await the 3950X and new gen Threadripper - it is good for Intel that they weren't out yet and part of the benchmark, otherwise the halo would be even harder to make out...
Agree; I expected to read a completely impartial review, like always, but I feel some sort of inclination to bold strengths in a way that a true discussion of 9990xe's weaknesses is out of favor!
I agree too. Ian was too excited when writing this review.
I'm more concerned that we'll have to stare at this processor in the lineup from now on as each AMD TR3 processor is covered. That's totally unfair because this CPU is for auction only and in limited supply permanently. Thus it'll look like Intel wins everything all the time. And then there are the people who will call this site a shill site because of that...
The whole article is another desperate move from Intel, just a few weeks before AMD releases Ryzen 3950X 16C/32T and new Threadripper 3rd gen. Unfortunately they found Anandtech and Dr. Ian Cutress again, to support their pathetic effort with some credibility. And suddenly after publishing this kind of article, the problem moves from Intel's side to Anandtech's side. My condolences.
"This ultra-rare thing isn’t sold to consumers – Intel only sells it to select partners, and even then it is only sold via an auction, once per quarter, with no warranty from Intel."
But the chip isn't selling for all that much at auction apparently... I was expecting much more than 2849 euros if this thing really is the golden ticket for HFT. From a financial perspective, this isn't worth Intel's time or effort relative to letting top-tier partners and resellers buy up the whole supply of 9990XE's to do the binning on their own. Regardless, it's less expensive than a Super Bowl ad I suppose and probably more effective considering their target audience.
It is a niche product for a niche market... one that the article talked about at length. "Bragging rights" doesn't come into play when it is a tool for making money.
It just doesn't make sense. If single threaded performance is king then why do you need 14 cores running at 5 GHz? If multithreaded performance is king then why not go wider? The low latency case doesn't make sense. You could assemble multiple systems focused on single threaded performance for less money than this 14 core auction-only chip costs. When people say it's only for bragging rights, they are not wrong.
you want as many cores as you can get, but those cores must respond as quickly as possible. You're effectively packet-watching: as soon as you see a packet you need to read it, determine if it is to be acted upon, determine how it is to be acted upon, and then respond, and you need to do it faster than everyone else. Everyone else has as close as is possible to the same network latency (e.g. stock exchanges employ huge fibre loops to ensure every endpoint has the same light-speed lag), so if you can run at 5GHz vs. 4GHz of your competitors you can respond to any given packet before they can. It's only a hair faster, but if you're jsut barely first you're still first so your transaction request is the one the stock exchange acts upon and not everyone else's.
You want more cores because each core can run its own worker with its own algorithm (or more workers on the same algorithm to offset by packet arrival). You never want to be operating at a lower frequency than everyone else because it means NOTHING that you have 64 cores if every one of your cores is consistently too slow to beat out everyone else.
You want all those cores on one die because you need to remain consistent in response (i.e. not have one worker working at cross-purposes against another) and inter-socket or worse inter-machine latency will kill you dead in the race to respond.
If high frequency is the ultimate goal and money is not an issue, why staying water.cooling.and not going straight to LN2. LN2 is cheap by wall street standards and it would allow to go higher than 6 GHz for sure. Btw in the great explanation you give regarding the need of high frequency CPU in HFT , I see nowhere optimization of the network card whatever it is and of its firmware.
>If high frequency is the ultimate goal and money is not an issue, why staying water.cooling.and not going straight to LN2. LN2 is cheap by wall street standards... These kinds of machines are used by automated systems doing stock trading thousands of times per second. (It's why being a day-trader is absolutely worthless because automated software can do your task thousands of times faster and more accurately given historical trends.) LN2 isn't "expensive" but this is a machine that needs to have the highest single-threaded performance possible, with as many cores as possible, yet still run 24/7 to keep up with the market. The system can never sleep, as we're talking potentially hundreds of thousands of dollars lost per few seconds of downtime. And that's why LN2 isn't used--It evaporates and while LN2 cooled systems can overclock higher than non-LN2 systems, it's at such a bleeding edge of instability that it in-and-of-itself will cost the stock-trader money whenever it inevitably gets a cold-bug and needs to reboot or if the thermal transfer between the pot and the IHS cracked at ultra-low temperatures and the temps are starting to rise, or if there's condensation around ICs, or if the power delivery system is starting to fail because it's been ran over-spec for the last 50 days, etc.
What are you talking about? MRI tools in every big hospital in the world is working 24/7 with LN2 . Every semiconductor fab in the world use LN2 in manufacturing environnement. LN2 is not an exotic material. So you tell me you can spend 10s millions of dollar to gain a few ns in HFT but you don't want to go beyond water cooling to gain a few GHz on your CPU Something is wrong here.
You clearly don't understand the difference between those machines and these. You just don't have a mind for it. Do not try to argue. Don't even try to think about it man. You are useless.
The difference is that those machines were designed with LN2 cooling in mind for sustained operation. Computers were not. Having a skilled overclocker precisely control a benchmark for a (relatively) short time is nothing like having a machine designed to automatically consistently do it over long periods. Developing a computer that could do his would not only be VERY expensive but there is also a risk of it simply not working consistently enough in the end anyway and you are back to square one.
You are the one clearly not understanding the situation. It seems financial companies involved in HFT can spend 10s millions us$ to gain a few ns . But they wouldn't want to spend those same dollars to get 1 or 2 more GHz with special custom LN2 or whatever other ultra low temp cooling system? Something doesn't add up here.
Because after a while, the system breaks down under LN2 cooling. There is such a thing as silicon being too cold, you know. Google intel cold bug, for example.
Have you seen LN2 cooling? It's not really practical for prolonged use -- you have to keep the LN2 flowing, you have to vent the gasses of the expended LN2, you have to resupply the LN2 somehow.
But you're missing the most important constraint of all for high-frequency trading, which is the reason they're building this processor into just 1 rack unit -- these machines aren't running on some remote data center, they're running in a network closet or very small data center probably just a floor or two away from a major stock exchange, in the same building. There is only so much space to be had. The space that's available is generally auctioned and can run well into 5-figures per month for a single rack unit. That's why they're building the exotic 1U liquid cooling in the first place, it'd be much easier to cool in even 2 units (there's even off-the-shelf radiators, then).
These machines are installed in exchange-owned and managed datacentres. "No LN2" as a rule would scupper that concept from the start, but even if it were allowed then you still have the problem of daily shipments of LN2 into a metropolitan centre, failover if a delivery is missed, dealing with large volumes of N2 gas generated in a city centre, etc. Just a logistical nightmare in general.
I think you probably could do something like that. You would want to run it on a beta system in parallel with your production system for a long time to make sure you had the 99.999999% uptime required. You would have to get pretty down and dirty to make it a 24/7 system. Probably a closed loop LN2 system, and I don't even know what kind of machine is required to condense from gas to liquid. You would also probably want heaters on the other components of the motherboard so that only the die was kept at the target low temp, and other components at the correct operating temp. And you would probably have to submerge the entire thing in some dielectric fluid like mineral oil to prevent condensation from building up. It would be expensive no doubt, but if (m/b)illions are on the line, then why not? Also, before embarking on something like this, you would want to make certain that you had tweaked every last bit of your software, both third party software settings and internally authored code, to minimize latency.
Judging from your description I would argue that a traditional PC is a horrible choice for such a problem, given the money at stake. They should be spinning custom ASICs that have the network stack and logic all put together. Even going through a NIC across a PCIe bus and into main memory and back out again is burning thousands of nanoseconds.
They do, not all HFT trading houses use software running on COTS hardware. Depending on where you go you can find FPGAs and even ASICs. However, not all of them have the expertise to move to hardware solutions; many are tied to their internal sofware and as such they will invest in the fastest COTS hardware money can buy.
An ASIC has a significant (many months to years) lead time between "we need X design" and functioning silicon. Trading algorithms are a constant arms race being updated to counter others' algorithm changes (who then counter your counters, etc) on the days to hours timescales.
It's not as simple as you need hundreds of threads or you need one. Compiling is an obvious example. You have a mixture of tasks - some take more threads (e.g. you have a large number of files in a makefile you can compile at once), some take less threads (you have a smaller makefile with only a few files), some take one thread (you need to link). A chip like this with 14 cores and very high single thread performance it turns out is ideal for this sort of task. Compiling is very much not a niche market.
Word (in the article) is that it helps with web browsing as well. So there is that. ;)
That being said, I don't look at this CPU as being competitive to AMD offerings simply because you can't buy the thing. However it is nice to see that Intel can do something if they put their mind to it.
You don't need all those cores running on a single platform to do HFT. In fact, that winds up being a negative because all the cores are competing for memory cycles. Instead what you want to do is mirror (not split, but do a full mirror) the packet stream to a whole bunch of platforms with fewer cores which can then maximally leverage their memory bandwidth and CPU caches. You also filter the packets inside the NIC itself, not with the CPU.
You also don't need to have a high-frequency CPU to minimize response time. The CPU is calculating outcomes from likely moves way ahead of time, long before actually receiving any packet telling it what movement actually happened. When the packet comes in, the CPU really only needs to look up the appropriate response from a table that has already been calculated. In fact, the NIC itself could do the table lookup for certain actions and bypass the CPU entirely.
So you want lots of cores, but they don't actually have to be ultra fast. Anyone using something like this processor to try to 'get ahead' in the HFT game is going to be in for a big surprise.
Thanks for the clarification. I thought that leaning on a single, many-core high-frequency CPU for this sort of task sounded a lot like optimising the wrong part of the whole process.
They likely auction the chips due to the aggressive binning required. I expect if they could roll out this kind of chip easily, they would have already. Think: 10 chips for every 100,000 can do 4-5 GHz @ 14 cores, 255 watt TDP.
Why such an angry statement? 14 is a very respectable number of cores. 14 at 5GHz is a world exclusive. I wouldn't even call this a product -- more of a hand-picked specialty part auction, which is perfectly reasonable (if uncommon) for any manufacturer to do. The fact that the parts sold indicates the demand is there. Why ignore the demand?
"Stories of companies spending 10s of millions to implement line-of-sight microwave transmitter towers to shave off 3 milliseconds from the latency time is a story I once heard. "
“It needed its burrow to be straight, maybe the most insistently straight path ever dug into the earth. It needed to connect a data centre on the South Side of Chicago to a stock exchange in northern New Jersey. Above all, apparently, it had to be secret," Mr Lewis said.
I call BS on that story. Why would you spend hundreds of millions (it must have cost at least that right?) to dig a straight 800+ mile tunnel between Chicago and NYC to get a 13 ms latency just so you could be destroyed by offices in NYC with 5 ms latency. Makes no sense. Your only choice is to move physically close to the source, if lowest latency is the winner then that's the only way to get it and be competitive.
Authors happily embellish existing stories, misrepresent details, and just plain old make sh** up to sell books. And then news outlets happily garbage-in, garbage-out these stories to get hits. I'm pretty sure that's what happened with that "story".
Companies have done it. Hell years ago I INTERVIEWED with a company that did it. It would blow your mind to find out what the financial folks will do to accelerate trading. A large portion of stock market trades are automated and driven by machine learning or predictive algorithms. How do I know, that position I interviewed for years ago (2003) was for a software developer for such an algorithm. I didn't get the job, because I didn't have the skills they were looking for at the time, but we did have a very interesting conversation about how their platform worked. It's fascinating how finance pushes everything forward.
Yes, I believe that those companies probably often spend lots of money to buy competitive advantages. I am simply stating that they'd not be buying a competitive advantage here (since the real competition is based in NYC had has an insurmountable advantage - the laws of physics not letting signals travel between Chicago and Wall St. faster than 13 ms) so they wouldn't spend the money. They would spend money buying an actual competitive advantage, i.e. offices in NYC.
> Why would you spend hundreds of millions (it must have cost at least that right?) to dig a straight 800+ mile tunnel between Chicago and NYC to get a 13 ms latency just so you could be destroyed by offices in NYC with 5 ms latency. Makes no sense. Your only choice is to move physically close to the source, if lowest latency is the winner then that's the only way to get it and be competitive.
When something doesn't seem to make sense, maybe the error is in your understanding of the situation. Did you ever consider that there are financial markets outside of NYC, and that some people might be trading between markets, or using signals from one market to inform trades in others?
This one is easy to answer, because there are two stock exchanges in play. NYSE in New York and CHX in Chicago. If you can send information from one exchange to the other quicker than others then you have an opportunity for arbitrage.
"Our analysis of the market data confirms that as of April 2010, the fastest communication route connecting the Chicago futures markets to the New Jersey equity markets was through fiber optic lines that allowed equity prices to respond within 7.25–7.95 ms of a price change in Chicago (Adler, 2012). In Au-gust of 2010, Spread Networks introduced a new fiber optic line that was shorter than the pre-existing routes and used lower latency equipment. This technology reduced Chicago–New Jersey latency to approximately 6.65 ms (Steiner, 2010; Adler,2012)."
I don't have the time to read the whole paper right now, I'll just trust my professor here. If there is actually something wrong with their methodology then I think the world would like to hear it.
<<“It needed its burrow to be straight, maybe the most insistently straight path ever dug into the earth. It needed to connect a data centre on the South Side of Chicago to a stock exchange in northern New Jersey. Above all, apparently, it had to be secret," Mr Lewis said>>
That's just a bunch of hogwash. You couldn't dig a straight line from Chicago to Jersey. It's just fancy sounding hogwash meant to convince those without the logic or background to see it for the hogwash it is. It's no more true than grimm's fairy tales.
“That's just a bunch of hogwash. You couldn't dig a straight line from Chicago to Jersey. It's just fancy sounding hogwash meant to convince those without the logic or background to see it for the hogwash it is. It's no more true than grimm's fairy tales.“
I love how the less a particular poster knows about this issue, the angrier they get and the more certain they sound about the nonsense they spout.
I dunno, it may be absolutely terrible value for money, and not even obtainable by pretty much the entire world's population, but I do like it when a tech company does something because they can, not because they should. It's this sort of attitude that keeps us all evolving.
Why would you love to have it? Just because it is an Intel CPU? The same company that has *hardware* security vulnerabilities? A much cheaper Ryzen system is shown to be just as fast as this product...
Exactly! It's just a bit of fun. As a product, it would be useless for my day job, but an absolute hoot in my gaming pc back at home. Who cares that it's pointless, and overpriced by a factor of five? I'm never going to buy it, and neither is anybody else here.
I love all the hate from AMD fanbois here who don't understand that for some things, single thread speed is king. And that apparently didn't read the article long enough to see the completely valid application for these yet felt justified in slamming Intel for selling it. Not surprisingly, those were the first comments, as they didn't have to read the article before commenting.
I love the Intel fanboys, who must post such a comment even before any AMD fan had said anything, just because they know that the value of money on that thing is atrocious and that it loses to a 12 core AMD consumer CPU is several tests.
IN a way - they absolutely do. You get 'invited' to by one of those limited production supercars, you don't just walk into a dealer and say here's my 2.5 million. You earn the invitation based on how many other cars by that manufacturer you already own. Want a 1 of 250 Ferrari supercar? If you don;t own any other Ferraris, good luck, even if you have plenty of money to pay for it.
No, speaking as someone that has walked into a Ferrari dealer with someone trying to buy a Ferrari, the other poster is absolutely right. You cannot walk into a Ferrari dealer and pick up a limited model no matter how many dollar bills you have. Even for something like a 488GTB, you will be waiting years unless you buy every option on the car and lease a crappy model like a California to move up in the queue. You can buy used ones in cash but with Ferrari, they rather protect their brand than cater to new money.
With *enough* money, you can buy Ferrari and make them sell it, too. It's tautological. Good thing, though: By they time someone controls that amount of money, they'd see the futility.
Sure it is, so go and buy an i3-9350K for (probably) 1% the price, and have the same single-threaded performance. If you want 14-cores, you're likely going to be doing multi-threaded work, you get my drift?
This product has a small niche where you work on both types, and somehow need the 5-10% more ST perf the 9990XE has, over, say the 3950X which will boost to 4.7 on a single core at vastly (and this is a huuuge under-statement) lower power draw and price.
Proponents of Intel claim that Single-threaded speed is so important (because, hey, that 5% is all they have these days) but don't seem to understand that Zen2 has absolutely fantastic single-threaded performance. Within 10% of Intel's best, thanks to slightly higher IPC, and the clock speeds on 1T boost get up there in the high 4 GHz area, too.
>(because, hey, that 5% is all they have these days)
And it's 5% on single threaded tasks that are instantaneous on our desktop PC. I don't have any desire to have 5% more performance there. What I want is the +30-50% performance on multithreaded tasks that have real, wall clock times that can be improved, which is what Ryzen delivers. Who cares if an Intel CPU has 5% better javascript when everything I do in my web browser is instantaneous? So instead of 15ms its 13ms? Ok? What blows my mind is when my kernel compiles or video encoding times are shaved off by MINUTES.
I love how people are turning this into Intel vs AMD, even when this is an extremely niche CPU for an extremely niche market.
>Who cares if an Intel CPU has 5% better JavaScript? Well apparently people who buy these care. You are irrelevant to the discussion because you were never part of the target market for this anyway
In scenarios where 'winner takes it all' those 5% are more than enough. Previously I worked on algorithmic trading and there it would be worth every cent.
> Against AMD counterparts, that 5.0 GHz frequency carves through anything like butter.
From the benchmarks, it lost to the 12 cores 3900X on more than one occasion. While it's true that for specific workloads the 9990XE would be much better, on average it seems to definitely not be worth the price. Also, comparisons to Zen 2 EPYC CPUs (or Threadrippers, which will soon be released) would be much more apt.
I was thinking the same. Even if I don’t take the power draw into account I am not impressed at all. And at 600W I would expect this to destroy the 3900X, so these results are actually quite embarrassing for Intel. I personally would rather wait for a 16 core Zen 3 AND pay for it than have this one for free.
An over 300W chip that loses in so many cases from chips that cost under $500, with less than half power consumption. And Intel is $auctioning$ it. That isn't even funny. It's tragic.
600W for performance that's not even going to be that much over a 3950X (if at all?) Intel is a laughing stock at this point. Can't wait to see the 9900KS, and have a good laugh at the last desperate, dying twitches of the Skylake architecture.
Why? And on which basis would you forbid it? I think the better way to deal with this is to attach a tiny tax to each transaction. So if it's really worth it, they may do it. But the government gets its share and can redistribute to something more useful.
It has no useful purpose for society, the fact it is difficult to identify the people being harmed does not mean that harm is not taking place.
I think making people have a 1 second relationship with a share is not unreasonable. Just because someone can do something doesn't mean we have to allow it. We have speed limits, laws against dishonesty and murder and we could just as easily have one against HFT.
The fact that exchanges sell expensive server space to these companies for lower pings, while purportedly being the arbiters of fair play and price transparency is, of course, another big issue.
So anything you in your all knowing capacity deem as not useful for society at large it should be illegal? Doesn't that mean gaming should be illegal?
I've yet to meet a single one of these people that complain about HFT that actually understand how the market works, how stock trading function and what HFT even is. Most of them simply heard some talking point they regurgitate without any understanding of how the stock market even works let alone how a stock transaction works or what HFT involves.
It's a mix of ignorance and jealousy, that they can't be the successful ones rolling in dough, and all investing is somehow evil and taking advantage of the common worker. There are some downsides to HFT, namely increased market volatility and cascading problems where a fall in prices can trigger millions of stop losses that compound the issue, but like you said, most have zero clue.
I am not jealous of an industry that has basically bought its way to success through lobbying and every time it explodes it expects the rest of us to reboot it, while mysteriously keeping the proceeds prior to the crash. An industry that gives away billions of our dollars of our money to avoid their own prosecution. Where almost no-one goes to jail after egregious lies, fraud, money laundering,....
All investing is not evil, however many of the practices of the industry are. Lobbying against fiduciary duty for the small investor, for example. If you actually look at the share classes available you will undoubtedly see some that no-one who understood what they were being sold would ever buy. Telling people 'they are responsible for their future' while not cleaning up the industry is like throwing sheep to wolves. And no, it is not everyone's responsibility to know every evil practice in every area of life in which they are forced to deal. It is unrealistic for the well educated, let alone the average citizen. It is why we have laws, which are generally reactive rather than proactive and thus mainly address known abuses rather prospective ones.
Nice article, except the final page. Why mention "highest ST for HEDT" and "carves through AMD like butter" etc., then you don't even make mention of any MT performance in summary. You could have said, in MT scenarios, it performs about the same as any Intel 18 or AMD 24 core server CPU or some such.
my meaning is the summary shouldn't just be for what is awesome, but should also summarize all the results... no mention of multi threading performance on the final page at all, because it isn't special?
Agreed. This product is a pathetic attempt to push their slight advantage in single-core, and justify the obscene pricing too. It's disgusting, really, tech press seem to lap up these things without understanding that this product is, well, pointless.
Intel made like 5 of them. So, AMD could bin a 3950X so damn effectively, you can have 4.7 on all 16-cores, because trust me with that level of binning; it's possible. But they won't, because they actually have people buying thier silicon for datacentres.
Anyway, the ST performance isn't even that much higher. Nothing worth the obscene price. I'll wait for the 3950X, and hope AT will sing its praises as it will likely demolish Intel's entire HEDT at a lower price and half the power use - it's only fair.
Guys, seriously... I'm an AMD person myself, but give Intel some credit - I doubt (sadly) that AMD could even release a Ryzen 5Ghz base clock part right now. Granted they might be able to bin out a 4.7 one but....
2nd, everyone going on and on about how expensive the 9990XE. Like it's under $3000? That's stupid cheap! Historically these HPC chips are like 1 or 2 cores enabled out of 12 and you pay over 5 or 10grand for them. Look up the old socket 1366 HPC chips like Xeon X5698 some time!
It is stupid cheap for a halo professional performance part from Intel. But even a cheap HPC - $3000 proc - it is more money than I could ever justify personally spending for what would essentially be a glorified gaming rig.
Which means, we're not the target market. Even in your world.
The whole point of this chip is that it throws price-to-perf out of the window for highest possible ST perf sustainable on all-cores. You know, like what the article describes?
But sure, AMD has better value or something, so everyone that buys Intel is stupid, despite the fact that different people have different usage scenarios and, gasp, Intel performs better under certain cases
Everytime there is a worthless product from Intel or Apple you always see fan boys and smart ass trying to defend it. Single threaded 9900K >= Multi threaded 2990WX, maybe even 3950X >
Hey Ian, please again thank ICC for letting you guys have a full run though with one of these systems.
While yes, this will never be a practical option for the vast majority of people, it IS one VERY AWESOME datapoint(s) for benchmark purposes. No more hypothetical "but what if 5Ghz Skylake" no - you have actual numbers, it shows the scaling for Intel's current'ish gen out to the extreme end.
I hope you are able to run more on this box to fill out the numbers in Bench - (which you may have already, I haven't actually looked yet).
I cant really tell how this is different from my 8700k from a performance perspective.
Looking at the article i think this is cheap marketing. Good move. But anyways it's crazy 14c cpu is now touted for their single thread performance. Seriously one have to wonder the meaning of all this. What am i doing here? Lol
Please test SLOWER/VERY SLOW not FAST/FASTER for encoding. I would not STORE anything ripped at FAST/FASTER...LOL. Who rips at this crap quality level? Besides, with 14c why wouldn't you want top quality (or fairly close)? It's not much more time and might yield completely different results. Never understood why people keep running tests that are NOT how we would USE the tested device/game etc. Test it like we USE it or quit wasting your (our?) time.
Raise your hand if you're ripping your blurays with fast/faster settings...Nobody. You can rip with SLOWER faster than you can create the content on these chips today, so why ruin your vid? L4.1 HIGH, VERY SLOW. Done (and I do 2pass, control other settings too, but you get the point). Nobody is archiving anything with your settings right? Emulate the pirates (seriously, one NFO file can tell you a LOT about these settings) :) They would NUKE your rip. Mediainfo can tell you all the settings also if you don't know where to get an nfo file from the people who've been ripping since the net started...LOL. Just saying...It's like claiming 1440p is the new enthusiast resolution (Ryan did this in his 660ti article...ROFL - see the comment section where I destroyed that crap), which isn't even true TODAY...LOL. YEARS later. Wake me when 1440p hits 10%. Right now it takes 1440p+4k to hit ~6.5% total...ROFL. 1440p is STILL not even 5% yet (4.98...ROFL). 1080p however 65%! Hmm, where should we spend MOST of our time testing then? Ah, UNDER 1440p with 4k being a complete joke still at 1.6%.
https://store.steampowered.com/hwsurvey/Steam-Hard... Wrong still for 7yrs Ryan Smith, AND counting. Is 10% even good enough to call it the new enthusiast resolution? Maybe Ryan will be right 2020. I digress...Don't even get me started on the complete BS that 4k testing is (1.6% of 130mil steam users say 4k is still dead). Apparently people don't like turning crap down (that devs meant for us to SEE) as much as Ryan etc think. :)
It's true that relatively few systems have a high-resolution screen. In fact I'd go further and say that for general usage of current systems, the combination of 4K+1440p is closer to 3% (with 1440p being ~2.5% of that). That's what I see on my media hosting website.
However, enthusiasts *are* the 3%. Or at least a lot of it. Most people use all-in-ones, work laptops, or school netbooks. They may install Steam on them and game on them, because they have to - they probably didn't buy new hardware specifically to do so. Reviews are all about new hardware.
If they *did* want to buy a new piece of video hardware, they may want to know how it'd perform if also buying a 1440p monitor and plug it in, perhaps once prices come down a bit. Or even 4K!
It's also a better way to measure GPU power than running them in a CPU-limited zone (after all, your GPU may end be paired with a future CPU by the time you buy it). The higher-end cards that tend to be reviewed are also intended to potentially last multiple CPU cycles - in reality I suspect most buy something further down the scale and just use it with one CPU, but it's an option.
Your point is fairer with IGP, but that's what IGP level is for. Most serious gamers are not using IGP. And this review doesn't *have* any GPU tests, though, so your comment may be better saved for one that does; it came off as ranting a little too hard about Ryan. :-)
Of course reviews are about new hardware...But the point is about HOW you test them. Are you acting like I'll MAYBE, if the wind blows right, stars align, etc, in 5yrs, or are you testing for what we will do with it for the next few years NOW? You know, like what I actually BOUGHT it for, NOW. I'm an enthusiast (know pretty much only them, since only deal with IT people pretty much), and have nothing like what they are pushing (no 4k desire for anyone I know, most not on 1440p). It isn't because I can't afford 4k, just don't care (for many reasons currently, lacking gpus for one, you need TWO still). I can afford those two titans every month too, but what for? They'd fry me in my PC room after 30mins of gaming due to heat in my state. So I'm stuck waiting for a 7nm NV card that takes AMD's 7nm a step further in watts heat (or I'll just downclock their no doubt better 7nm version since they waited) so I can play my next monitor (hopefully xmas this year or next) at max details, and of course my current 1920x1200 will be maxed finally by it until I finally see a monitor I want (c'mon dell 30+ with gsync). I'll pay $1200, just make it!
I see nothing wrong with "ranting" (not how I see it, but whatever) if you're still right and it is relevant to 95% of users who are STILL not using stuff like they seem to think we do (and you keep testing stuff WRONG over and over). The point is a pattern of reviewing products in ways we don't actually use them. If 95% of users were running 4k monitors, it would be just as stupid to test 720p all day in every review right? Unless you're trying to prove a specific point by doing said test, there is no reason to wash rinse and repeat this. Your review should cover your audience NOW, with a mention of the future maybe as an afterthought (like RTX on day one, hmm, hope they use it). RTX didn't fly off the shelves until more about the features came out. Most people don't care about the future of their tech, they are buying for today's perf or features they need.
No, The same people buy new titans yearly (Multiple Titans in many cases, 4 at a time, 2080ti's also) according to Jen Hsun himself. The bulk of top sales go to the same rich who can afford them yearly easily. Heck I can afford them too (easy with no Visa bills, no car (cash), no cell, no cabletv (just HSI), just don't care to act rich for not much more perf :)
More than 3% buy enthusiast cards. Heck 3% of sales is likely Titans alone, and that card alone is not what I call enthusiasts (Ryan thought it was 660ti back then, it was NOT the top card, probably correct too, but it wasn't built for 1440p he was pushing). Anything over $250, you're probably more than a casual gamer.
NO serious gamer is using igp...LOL. Do you know serious gamers who play 720p with details down? I don't say NEVER test 4k or 1440p, I say there is no need to spend 2/3 of each review of gpus on this crap (you can read many posts of mine in reviews like this). TEST more of what we PLAY at NOW, RIP at quality levels most would want to watch, etc. When the future comes, I'll be on other hardware (probably most enthusiasts huh?)...ROFL. Test a few games a year in a 4k review, no need to do it repeatedly as if it is used by more than a few %. People are FAR more interested in how it works NOW as I use it, than "futureproof" junk I may never use if nobody supports it ever. I'm not against testing a 4k game per review, but not a 4k test for every game in said review. Same for ripping, I humbly ask who watches this crap quality? Why are all the ripping tests in crap qual? They turn off stuff users specifically BUY NV cards for. You know, like acting CUDA wouldn't be used by a NV buyer if they had a choice. Nobody buys NV to do OpenCL...ROFLMAO. You buy for CUDA if you can for your app. I could go on, but you should get the point: TEST IT LIKE WE USE IT, no matter what you're testing today, tomorrow, etc.
My point is fair for ALL single gpu cards, as there isn't one yet that can do 4K on ALL games without turning tons of crap down on a per game basis. Pricing isn't bad, so this is clearly a big deal to people. No point in buying something new, only to degrade it's perf out of the box just to get enough fps to enjoy your game (not as the dev intended you to see it at this point either). But, then, I don't enjoy that game at this point. I need the details ON.
IF, if, but, maybe...blah...How about spending MOST of your time testing what we actually DO with whatever you are reviewing, instead of wasting time on what YOU WISH we used this stuff for. This is why Anandtech is my last resort these days and tomshardware even less used (same site really now).
Isn't the myth of high-frequency traders using tuned CPUs a bit overblown? I'm not saying it doesn't happen, but would they really even go so far as to forego ECC memory?
I guess you have to be fastest to earn serious money. And there's no "fast" ECC RAM in terms of desktop OC. If with ECC you can get a guaranteed answer too late, it's not going to matter. Better risk the seldom error without ECC - it's probably going to be fine...
So I'm a true blood capitalist but I just don't see the utility or reason for existence for "high speed trading". They are making money on the difference between prices at the millisecond level. It offers nothing back to society and seems to exist only due to how stock and commodity trading works.
Stocks should exist for public ownership of companies, to provide funding for those companies and hopefully for the stockholders to benefit from the growth and profit of said companies.
It shouldn't exsist as a glorified casino game, which is essentially what "high speed trading" is.
The older 3Dmark physics tests don't scale to all available processor cores, so those numbers are misleading. My observation has been that the newer/more demanding the base benchmark, the wider the physics. So e.g. I doubt that Ice Storm actually scores beyond 4 physical cores, while I have seen the physics benchmark correllating to the DX12 graphics (keep forgetting the name) actually pushed all 18 cores in my workstation. I run HWinfo on a secondary screen to monitor what's happening on the system and it cleary reflects that most cores aren't used on these CPU-only physics tests.
1.290V at 5 GHz all core may be "amazing" but it should really be "expected": Any chip that requires more voltage and thus power to push electrons through layer interconnects will fail the binning because of heat. And with every little part of 14 cores and their caches needing to qualify, it's easy to see how rare these are.
Agreeing to disagree with you, Ian, after seeing the benchmark results, I would hardly call this the slam dunk and beast it is made out to be. It is good in several benchmarks but it is highly specialized to the point I would argue the 9900KS would be the better choice of the two in nearly all cases for high frequency applications and the 3900X (and by extension 3950X) in multi-core applications. All in all, I am not really impressed and even less so with Threadripper 3000 and Cascade Lake on the verge of release.
Who cares about tests done on Windows? Who would bother with Chrome compilation on Windows?? Author(s) sees that increasingly more tests are being done with Open Source and clumsily tries to mimic that. But for those interested in real testing - go to phoronix.com and openbenchmarking.org Lots love, xxx.
This certainly will sound abrupt - it's for that tiny little world and tiny people in it - the office?? Step outside for a moment and look at big data, clusters, HPC, all sort of servers & services, also academia! Linux & open source everywhere. Why? Might think... some media streaming, transcoding, codecs, etc. you might need that i9-9990XE beast in the office and for windows - sure if you click once here once there to run something - heavy duty transcoding that's Linux all around the clock. But if one does only pure 'office' and thinks s/he must have this i9-9990XE - well these are the same sort of people who even today when it makes no financial sense whatsoever(do not mention this is not 'office' cpu), who have been happy to pay hefty taxes to Intel for years, those people will do it anyway, will waste money on it, as they do with anything else I'm sure. But anyway, 'the office' stuff also we do with Linux, easy.
Did you say 600W under full load? For a single CPU socket and only 14 cores? That isn't a wattage that will beget a limited market. That's a wattage that makes the chip D.O.A. No market. At all. Anywhere. Not for 'high frequency trading' or anything else.
Spelling error: "Blender can take advantage of more cores, and whule the frequency of the 9990XE helps compared to the 7940X, it isn't enough to overtake 18-core hardware." "while", not "whule": "Blender can take advantage of more cores, and while the frequency of the 9990XE helps compared to the 7940X, it isn't enough to overtake 18-core hardware."
What's interesting about this processors benchmarks is that even at 5.0GHz AMD's Zen2 processors are still fairly close. -- Not that I'm trying to attract fanboys, it's just interesting to compare the IPC, memory latency, etc.
IMHO, Linpack (Intel® Math Kernel Library (Intel® MKL) Benchmarks) with not-too-many cores gives good upper bound estimation of practically obtainable perfomance in engineering and science.
As I look at this and the struggle to make predictable quantum computing hardware, I see us reaching an inflection point where "traditional" methods will have to adapt a hybrid quantum piece because the features will have shrunk to the point where quantum effects become the norm, vice the exception.
"... These companies not only pay through the nose for the hardware, but also pay experts and specialists to tune those systems for low latency. That means tweaking the memory, overclocking the processor ...".
Financial trading is often done on the Network Card, see NextPlatform's article "Hypercalers Lead The Way To The Future With SmartNICs" or Wikipedia's "Reducing latency in the order chain".
When the network card has received a bit of the packet it's starts reviewing which decisions it is able to make based on a partial packet, further narrowing down it's options as more data is received. If it's lucky it can send an order before the packet is completely received - if it can't it calculates if it's worth bailing out or running late with the others.
The CPUs on HFT machines have fewer CPU cores that can be overclocked since they only need to convert orders to the FPGA. Trading is so fast they implemented 'speed bumps'.:
"The IEX speed bump—or trading slowdown—is 350 microseconds, which the SEC ruled was within the "immediately visible" parameter.".
I dunno, considering my 3900x is being cooled by a 240mm AIO and at boost barely goes over 105W and yet gets up to a toasty 78C I am pretty sure I don't want to even imagine that damn cooling rig it would take to keep Intel's 200W+ monster cool under boost. I don't have that much need or interest in such a thing, and if anyone else does I sure hope you live in a climate that lets you pull in -10C air into your case.
Be kind of fun to test this placeholder from Intel with air cooling pitted against air-cooled AMD competition. Yawn...poor Intel, it's going to be a lot of last gasping from them until they put Ryzens and TR's and EPYCs under X-ray to figure out some aspects of manufacturing a modern CPU...;) I'm sure it's all been very instructive for them.
Sim Thăng Long - Sim số đẹp, giá rẻ Email ĐK: [email protected] User name: simthanglong Giới thiệu: Sim Thăng Long là một trong những đơn vị cung cấp sim lớn nhất toàn quốc, luôn mang đến sự tin cậy cũng như hài lòng cho mọi khách hàng. Địa chỉ: 22 Ô Chợ Dừa, Đống Đa, Hà Nội SĐT: 024 6666 6666 Email: [email protected] Website: https://simthanglong.vn File LOGO: https://simthanglong.vn/images/sim-so-dep-simthang... Headline: Sim Thăng Long - Sim số đẹp chất lượng, giá rẻ nhất Việt Nam Description: Sim Thăng Long là một trong những thương hiệu luôn quan tâm đến những nhu cầu của khách hàng và cung cấp ra những sim số đẹp và giá rẻ nhất Hastag: #Simthanglong, #Simsodep, #simgiare
Bài giới thiệu: Sim Thăng Long được xem là hệ thống phân phối sim số đẹp lớn nhất – Uy tín nhất Việt Nam với hơn 12 triệu Sim Số Đẹp, Sim Phong Thủy, Sim Năm Sinh… của tất cả các nhà mạng lớn tại Việt Nam, đáp ứng mọi nhu cầu về sim số đẹp của Quý khách hàng và giao hàng trên toàn quốc. Tất cả những sản phẩm sim tại Sim Thăng Long đều sẽ được đăng ký miễn phí thông tin chính chủ và được cung cấp từ các nhà mạng lớn nhất Việt Nam như Viettel, Vinaphone, Mobifone hay nhà mạng Vietnamobile hoặc Gmobile, iTelecom. Để tìm được sim số đẹp ưng ý, quý khách hàng có thể truy cập website: Simthanglong.vn hoặc liên hệ hotline: 024.6666.6666 để được nhân viên tư vấn cụ thể khi có nhu cầu tìm sản phẩm sim phù hợp. Quý khách hàng cũng có thể tìm đến hệ thống cửa hàng của Sim Thăng Long trên nhiều tỉnh thành khác nhau trên cả nước để được nhân viên bán hàng tư vấn và giúp lựa chọn được số sim ưng ý.
sim phát 868686 với nhà mạng dạng số cùng đủ các khoảng giá tuyệt nhất sim đuôi 868686 với các đầu số Vietnamobile, Vina, Mobi, Viettel, Gmobile cùng đủ các khoảng giá, ưu đãi tuyệt nhất cho quý khách thỏa sức lựa chọn tại Sim Thăng Long. mua ngay sim phát 868686 các mạng Vina, Viettel, Vietnamobile, Mobi, Gmobile được để với giá tốt tại Sim Thăng Long ngay nào!!!
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
145 Comments
Back to Article
willis936 - Monday, October 28, 2019 - link
>but also pay experts and specialists to tune those systems for high latencyI believe this should read "low latency".
jospoortvliet - Tuesday, October 29, 2019 - link
Yup. And while correcting:> Against AMD counterparts, that 5.0 GHz frequency carves through anything like butter.
That is rather optimistic... the Intel is frequently bested by the 3700x and especially the 3900x - I would expect a 3950X might even win the majority of tests run here.
jospoortvliet - Tuesday, October 29, 2019 - link
I went ahead and did a quick count:* 3900X has 13 wins (7 more than 10%)
* 9990XE has 21 wins (10 more than 10%)
Now obviously the 9990XE is faster, but it better be with 2 more cores and 5 ghz and 400 watt power use and a price - well... ;-)
But it sure isn't the slam dunk it is described at - Ian writes like this monster wins in >90% of the tests, which it doesn't, not by a long shot. If it was readily available at $600 and had a TDP of 140W, I'd call it a winner, even if it doesn't *always* win. But if intel has to go THIS extreme and still loses in over 1/3rd of the graphs here at Anandtech, it is more a show of weakness if anything.
And all that while we await the 3950X and new gen Threadripper - it is good for Intel that they weren't out yet and part of the benchmark, otherwise the halo would be even harder to make out...
Netmsm - Tuesday, October 29, 2019 - link
Agree;I expected to read a completely impartial review, like always, but I feel some sort of inclination to bold strengths in a way that a true discussion of 9990xe's weaknesses is out of favor!
jgraham11 - Tuesday, October 29, 2019 - link
Agreed!Look at that amazing performance at 250W (which will probably run even hotter, just like the 9900k "stock (95W)" vs out of box settings(140W+)
Compared to the AMD 3900X at half the power(105W), that thing is a heater!
Same story as all the other recent articles about Intel chips:
Intel runs old games better, runs hotter, consumes more power, higher clock speed!
AMD runs new games better, runs cooler, consumes less power (in this case half at least), runs applications better
ballsystemlord - Wednesday, October 30, 2019 - link
I agree too. Ian was too excited when writing this review.I'm more concerned that we'll have to stare at this processor in the lineup from now on as each AMD TR3 processor is covered. That's totally unfair because this CPU is for auction only and in limited supply permanently.
Thus it'll look like Intel wins everything all the time. And then there are the people who will call this site a shill site because of that...
NikosD - Friday, November 1, 2019 - link
The whole article is another desperate move from Intel, just a few weeks before AMD releases Ryzen 3950X 16C/32T and new Threadripper 3rd gen.Unfortunately they found Anandtech and Dr. Ian Cutress again, to support their pathetic effort with some credibility.
And suddenly after publishing this kind of article, the problem moves from Intel's side to Anandtech's side.
My condolences.
peevee - Monday, October 28, 2019 - link
"This ultra-rare thing isn’t sold to consumers – Intel only sells it to select partners, and even then it is only sold via an auction, once per quarter, with no warranty from Intel."Pathetic strategy for bragging rights only...
fackamato - Monday, October 28, 2019 - link
I think you're in the wrong forums?Of course people will buy this if it brings value to them versus the price they have to pay.
bananaforscale - Thursday, October 31, 2019 - link
Sure, if value == bragging rights. Or if they have more money than sense.Batmeat - Monday, October 28, 2019 - link
Agreed.This chip is auction only. Expect to pay HUGE DOLLARS for this assuming you even have access to the auctions.
mrvco - Monday, October 28, 2019 - link
But the chip isn't selling for all that much at auction apparently... I was expecting much more than 2849 euros if this thing really is the golden ticket for HFT. From a financial perspective, this isn't worth Intel's time or effort relative to letting top-tier partners and resellers buy up the whole supply of 9990XE's to do the binning on their own. Regardless, it's less expensive than a Super Bowl ad I suppose and probably more effective considering their target audience.Cygni - Monday, October 28, 2019 - link
It is a niche product for a niche market... one that the article talked about at length. "Bragging rights" doesn't come into play when it is a tool for making money.willis936 - Monday, October 28, 2019 - link
It just doesn't make sense. If single threaded performance is king then why do you need 14 cores running at 5 GHz? If multithreaded performance is king then why not go wider? The low latency case doesn't make sense. You could assemble multiple systems focused on single threaded performance for less money than this 14 core auction-only chip costs. When people say it's only for bragging rights, they are not wrong.edzieba - Monday, October 28, 2019 - link
To GREATLY oversimplify HFT loads:you want as many cores as you can get, but those cores must respond as quickly as possible. You're effectively packet-watching: as soon as you see a packet you need to read it, determine if it is to be acted upon, determine how it is to be acted upon, and then respond, and you need to do it faster than everyone else. Everyone else has as close as is possible to the same network latency (e.g. stock exchanges employ huge fibre loops to ensure every endpoint has the same light-speed lag), so if you can run at 5GHz vs. 4GHz of your competitors you can respond to any given packet before they can. It's only a hair faster, but if you're jsut barely first you're still first so your transaction request is the one the stock exchange acts upon and not everyone else's.
You want more cores because each core can run its own worker with its own algorithm (or more workers on the same algorithm to offset by packet arrival). You never want to be operating at a lower frequency than everyone else because it means NOTHING that you have 64 cores if every one of your cores is consistently too slow to beat out everyone else.
You want all those cores on one die because you need to remain consistent in response (i.e. not have one worker working at cross-purposes against another) and inter-socket or worse inter-machine latency will kill you dead in the race to respond.
Processwindow - Monday, October 28, 2019 - link
If high frequency is the ultimate goal and money is not an issue, why staying water.cooling.and not going straight to LN2. LN2 is cheap by wall street standards and it would allow to go higher than 6 GHz for sure. Btw in the great explanation you give regarding the need of high frequency CPU in HFT , I see nowhere optimization of the network card whatever it is and of its firmware.JoeyJoJo123 - Monday, October 28, 2019 - link
>If high frequency is the ultimate goal and money is not an issue, why staying water.cooling.and not going straight to LN2. LN2 is cheap by wall street standards...These kinds of machines are used by automated systems doing stock trading thousands of times per second. (It's why being a day-trader is absolutely worthless because automated software can do your task thousands of times faster and more accurately given historical trends.) LN2 isn't "expensive" but this is a machine that needs to have the highest single-threaded performance possible, with as many cores as possible, yet still run 24/7 to keep up with the market. The system can never sleep, as we're talking potentially hundreds of thousands of dollars lost per few seconds of downtime. And that's why LN2 isn't used--It evaporates and while LN2 cooled systems can overclock higher than non-LN2 systems, it's at such a bleeding edge of instability that it in-and-of-itself will cost the stock-trader money whenever it inevitably gets a cold-bug and needs to reboot or if the thermal transfer between the pot and the IHS cracked at ultra-low temperatures and the temps are starting to rise, or if there's condensation around ICs, or if the power delivery system is starting to fail because it's been ran over-spec for the last 50 days, etc.
Processwindow - Monday, October 28, 2019 - link
What are you talking about? MRI tools in every big hospital in the world is working 24/7 with LN2 . Every semiconductor fab in the world use LN2 in manufacturing environnement. LN2 is not an exotic material.So you tell me you can spend 10s millions of dollar to gain a few ns in HFT but you don't want to go beyond water cooling to gain a few GHz on your CPU Something is wrong here.
Opencg - Monday, October 28, 2019 - link
You clearly don't understand the difference between those machines and these. You just don't have a mind for it. Do not try to argue. Don't even try to think about it man. You are useless.The difference is that those machines were designed with LN2 cooling in mind for sustained operation. Computers were not. Having a skilled overclocker precisely control a benchmark for a (relatively) short time is nothing like having a machine designed to automatically consistently do it over long periods. Developing a computer that could do his would not only be VERY expensive but there is also a risk of it simply not working consistently enough in the end anyway and you are back to square one.
Processwindow - Monday, October 28, 2019 - link
You are the one clearly not understanding the situation. It seems financial companies involved in HFT can spend 10s millions us$ to gain a few ns . But they wouldn't want to spend those same dollars to get 1 or 2 more GHz with special custom LN2 or whatever other ultra low temp cooling system? Something doesn't add up here.Supercell99 - Monday, October 28, 2019 - link
The democrats have banned LN2 in New York as they have deemed it a climate pollutant.xrror - Monday, October 28, 2019 - link
No they haven't you republican jackass, the Earth's atmosphere is 78% nitrogen.eek2121 - Monday, October 28, 2019 - link
Because after a while, the system breaks down under LN2 cooling. There is such a thing as silicon being too cold, you know. Google intel cold bug, for example.ravyne - Monday, October 28, 2019 - link
Have you seen LN2 cooling? It's not really practical for prolonged use -- you have to keep the LN2 flowing, you have to vent the gasses of the expended LN2, you have to resupply the LN2 somehow.But you're missing the most important constraint of all for high-frequency trading, which is the reason they're building this processor into just 1 rack unit -- these machines aren't running on some remote data center, they're running in a network closet or very small data center probably just a floor or two away from a major stock exchange, in the same building. There is only so much space to be had. The space that's available is generally auctioned and can run well into 5-figures per month for a single rack unit. That's why they're building the exotic 1U liquid cooling in the first place, it'd be much easier to cool in even 2 units (there's even off-the-shelf radiators, then).
edzieba - Thursday, October 31, 2019 - link
These machines are installed in exchange-owned and managed datacentres. "No LN2" as a rule would scupper that concept from the start, but even if it were allowed then you still have the problem of daily shipments of LN2 into a metropolitan centre, failover if a delivery is missed, dealing with large volumes of N2 gas generated in a city centre, etc. Just a logistical nightmare in general.eek2121 - Monday, October 28, 2019 - link
It's impossible to cool a system 24/7 with LN2.DixonSoftwareSolutions - Tuesday, October 29, 2019 - link
I think you probably could do something like that. You would want to run it on a beta system in parallel with your production system for a long time to make sure you had the 99.999999% uptime required. You would have to get pretty down and dirty to make it a 24/7 system. Probably a closed loop LN2 system, and I don't even know what kind of machine is required to condense from gas to liquid. You would also probably want heaters on the other components of the motherboard so that only the die was kept at the target low temp, and other components at the correct operating temp. And you would probably have to submerge the entire thing in some dielectric fluid like mineral oil to prevent condensation from building up. It would be expensive no doubt, but if (m/b)illions are on the line, then why not? Also, before embarking on something like this, you would want to make certain that you had tweaked every last bit of your software, both third party software settings and internally authored code, to minimize latency.willis936 - Monday, October 28, 2019 - link
Judging from your description I would argue that a traditional PC is a horrible choice for such a problem, given the money at stake. They should be spinning custom ASICs that have the network stack and logic all put together. Even going through a NIC across a PCIe bus and into main memory and back out again is burning thousands of nanoseconds.29a - Monday, October 28, 2019 - link
I'm also wondering why they don't create custom silicon for this.gsvelto - Monday, October 28, 2019 - link
They do, not all HFT trading houses use software running on COTS hardware. Depending on where you go you can find FPGAs and even ASICs. However, not all of them have the expertise to move to hardware solutions; many are tied to their internal sofware and as such they will invest in the fastest COTS hardware money can buy.edzieba - Thursday, October 31, 2019 - link
An ASIC has a significant (many months to years) lead time between "we need X design" and functioning silicon. Trading algorithms are a constant arms race being updated to counter others' algorithm changes (who then counter your counters, etc) on the days to hours timescales.shtldr - Tuesday, October 29, 2019 - link
If you've got all the money (which you should, in case you are a successful algorithmic trader), why not go ASIC?Dribble - Monday, October 28, 2019 - link
It's not as simple as you need hundreds of threads or you need one. Compiling is an obvious example. You have a mixture of tasks - some take more threads (e.g. you have a large number of files in a makefile you can compile at once), some take less threads (you have a smaller makefile with only a few files), some take one thread (you need to link).A chip like this with 14 cores and very high single thread performance it turns out is ideal for this sort of task.
Compiling is very much not a niche market.
eek2121 - Monday, October 28, 2019 - link
Word (in the article) is that it helps with web browsing as well. So there is that. ;)That being said, I don't look at this CPU as being competitive to AMD offerings simply because you can't buy the thing. However it is nice to see that Intel can do something if they put their mind to it.
bananaforscale - Thursday, October 31, 2019 - link
Well, multiple cores *do* help with web browsing, doesn't mean you need 14@5 GHz. :DMattZN - Tuesday, October 29, 2019 - link
You don't need all those cores running on a single platform to do HFT. In fact, that winds up being a negative because all the cores are competing for memory cycles. Instead what you want to do is mirror (not split, but do a full mirror) the packet stream to a whole bunch of platforms with fewer cores which can then maximally leverage their memory bandwidth and CPU caches. You also filter the packets inside the NIC itself, not with the CPU.You also don't need to have a high-frequency CPU to minimize response time. The CPU is calculating outcomes from likely moves way ahead of time, long before actually receiving any packet telling it what movement actually happened. When the packet comes in, the CPU really only needs to look up the appropriate response from a table that has already been calculated. In fact, the NIC itself could do the table lookup for certain actions and bypass the CPU entirely.
So you want lots of cores, but they don't actually have to be ultra fast. Anyone using something like this processor to try to 'get ahead' in the HFT game is going to be in for a big surprise.
-Matt
Spunjji - Wednesday, October 30, 2019 - link
Thanks for the clarification. I thought that leaning on a single, many-core high-frequency CPU for this sort of task sounded a lot like optimising the wrong part of the whole process.peevee - Monday, October 28, 2019 - link
That's the point. It does not make them much money, the volume is simply not there. It is for INTEL's bragging.eek2121 - Monday, October 28, 2019 - link
They likely auction the chips due to the aggressive binning required. I expect if they could roll out this kind of chip easily, they would have already. Think: 10 chips for every 100,000 can do 4-5 GHz @ 14 cores, 255 watt TDP.lazarpandar - Monday, October 28, 2019 - link
So if you have an absurd amount of money and can't scale with more cores beyond 14...What a stupid product.
Sivar - Monday, October 28, 2019 - link
Why such an angry statement?14 is a very respectable number of cores. 14 at 5GHz is a world exclusive.
I wouldn't even call this a product -- more of a hand-picked specialty part auction, which is perfectly reasonable (if uncommon) for any manufacturer to do. The fact that the parts sold indicates the demand is there. Why ignore the demand?
Spunjji - Wednesday, October 30, 2019 - link
The fact that they sold very few of them indicates that the demand is barely there.FunBunny2 - Monday, October 28, 2019 - link
"Stories of companies spending 10s of millions to implement line-of-sight microwave transmitter towers to shave off 3 milliseconds from the latency time is a story I once heard. "There was reporting, mainstream source (Lewis: https://www.telegraph.co.uk/finance/newsbysector/b... that a broker(s) installed a fiber line from the Chicago office to an exchange in NJ.
“It needed its burrow to be straight, maybe the most insistently straight path ever dug into the earth. It needed to connect a data centre on the South Side of Chicago to a stock exchange in northern New Jersey. Above all, apparently, it had to be secret," Mr Lewis said.
bji - Monday, October 28, 2019 - link
I call BS on that story. Why would you spend hundreds of millions (it must have cost at least that right?) to dig a straight 800+ mile tunnel between Chicago and NYC to get a 13 ms latency just so you could be destroyed by offices in NYC with 5 ms latency. Makes no sense. Your only choice is to move physically close to the source, if lowest latency is the winner then that's the only way to get it and be competitive.Authors happily embellish existing stories, misrepresent details, and just plain old make sh** up to sell books. And then news outlets happily garbage-in, garbage-out these stories to get hits. I'm pretty sure that's what happened with that "story".
eek2121 - Monday, October 28, 2019 - link
Companies have done it. Hell years ago I INTERVIEWED with a company that did it. It would blow your mind to find out what the financial folks will do to accelerate trading. A large portion of stock market trades are automated and driven by machine learning or predictive algorithms. How do I know, that position I interviewed for years ago (2003) was for a software developer for such an algorithm. I didn't get the job, because I didn't have the skills they were looking for at the time, but we did have a very interesting conversation about how their platform worked. It's fascinating how finance pushes everything forward.FunBunny2 - Monday, October 28, 2019 - link
" It would blow your mind to find out what the financial folks will do to accelerate trading."yes, yes it would - here: https://www.marketplace.org/2019/10/07/fight-nyse-...
bji - Monday, October 28, 2019 - link
Yes, I believe that those companies probably often spend lots of money to buy competitive advantages. I am simply stating that they'd not be buying a competitive advantage here (since the real competition is based in NYC had has an insurmountable advantage - the laws of physics not letting signals travel between Chicago and Wall St. faster than 13 ms) so they wouldn't spend the money. They would spend money buying an actual competitive advantage, i.e. offices in NYC.mode_13h - Tuesday, October 29, 2019 - link
> Why would you spend hundreds of millions (it must have cost at least that right?) to dig a straight 800+ mile tunnel between Chicago and NYC to get a 13 ms latency just so you could be destroyed by offices in NYC with 5 ms latency. Makes no sense. Your only choice is to move physically close to the source, if lowest latency is the winner then that's the only way to get it and be competitive.When something doesn't seem to make sense, maybe the error is in your understanding of the situation. Did you ever consider that there are financial markets outside of NYC, and that some people might be trading between markets, or using signals from one market to inform trades in others?
Joel Busch - Tuesday, October 29, 2019 - link
This one is easy to answer, because there are two stock exchanges in play. NYSE in New York and CHX in Chicago. If you can send information from one exchange to the other quicker than others then you have an opportunity for arbitrage.One of my professors is Ankit Singla, he works on c-speed networking, he cited this paper in class https://doi.org/10.1111/fire.12036
They say for example:
"Our analysis of the market data confirms that as of April 2010, the fastest communication route connecting the Chicago futures markets to the New Jersey equity markets was through fiber optic lines that allowed equity prices to respond within 7.25–7.95 ms of a price change in Chicago (Adler, 2012). In Au-gust of 2010, Spread Networks introduced a new fiber optic line that was shorter than the pre-existing routes and used lower latency equipment. This technology reduced Chicago–New Jersey latency to approximately 6.65 ms (Steiner, 2010; Adler,2012)."
I don't have the time to read the whole paper right now, I'll just trust my professor here. If there is actually something wrong with their methodology then I think the world would like to hear it.
rahvin - Monday, October 28, 2019 - link
<<“It needed its burrow to be straight, maybe the most insistently straight path ever dug into the earth. It needed to connect a data centre on the South Side of Chicago to a stock exchange in northern New Jersey. Above all, apparently, it had to be secret," Mr Lewis said>>That's just a bunch of hogwash. You couldn't dig a straight line from Chicago to Jersey. It's just fancy sounding hogwash meant to convince those without the logic or background to see it for the hogwash it is. It's no more true than grimm's fairy tales.
phexac - Wednesday, October 30, 2019 - link
“That's just a bunch of hogwash. You couldn't dig a straight line from Chicago to Jersey. It's just fancy sounding hogwash meant to convince those without the logic or background to see it for the hogwash it is. It's no more true than grimm's fairy tales.“I love how the less a particular poster knows about this issue, the angrier they get and the more certain they sound about the nonsense they spout.
Slash3 - Monday, October 28, 2019 - link
The secret DIMMs look like the same Samsung B-die based G.Skill ARES used in their 9900K blade.https://www.servethehome.com/icc-vega-r-116i-revie...
colonelclaw - Monday, October 28, 2019 - link
I dunno, it may be absolutely terrible value for money, and not even obtainable by pretty much the entire world's population, but I do like it when a tech company does something because they can, not because they should. It's this sort of attitude that keeps us all evolving.nathanddrews - Monday, October 28, 2019 - link
At the end of the day, life is all about bragging rights. I'd never buy this, but I'd love to have it!mooninite - Monday, October 28, 2019 - link
Why would you love to have it? Just because it is an Intel CPU? The same company that has *hardware* security vulnerabilities? A much cheaper Ryzen system is shown to be just as fast as this product...Retycint - Monday, October 28, 2019 - link
It's really amusing to see how some people get so triggered over the mere mention of IntelGreenReaper - Tuesday, October 29, 2019 - link
It's shocking to see support for Intel, even though their name is a shorthand for the intelligence agencies!Retycint - Tuesday, October 29, 2019 - link
It's also very amusing to see you immediately assume I'm an Intel supporter29a - Monday, October 28, 2019 - link
That's a strange take on life.colonelclaw - Monday, October 28, 2019 - link
Exactly! It's just a bit of fun. As a product, it would be useless for my day job, but an absolute hoot in my gaming pc back at home. Who cares that it's pointless, and overpriced by a factor of five? I'm never going to buy it, and neither is anybody else here.kgardas - Monday, October 28, 2019 - link
Nice comparison, but why is ryzen 3xxx missing from your compilation test? Would be most interesting!Slash3 - Monday, October 28, 2019 - link
...it isn't?Slash3 - Monday, October 28, 2019 - link
Nm, I see what you meant.Flunk - Monday, October 28, 2019 - link
Probably part of Intel's deal to loan them the chip.Retycint - Monday, October 28, 2019 - link
Intel wasn't the one who loaned them the chip. Nice try, thoughjabber - Monday, October 28, 2019 - link
Three or fours years ago this might have been exciting...EdgeOfDetroit - Monday, October 28, 2019 - link
I love all the hate from AMD fanbois here who don't understand that for some things, single thread speed is king. And that apparently didn't read the article long enough to see the completely valid application for these yet felt justified in slamming Intel for selling it. Not surprisingly, those were the first comments, as they didn't have to read the article before commenting.ET - Monday, October 28, 2019 - link
I love the Intel fanboys, who must post such a comment even before any AMD fan had said anything, just because they know that the value of money on that thing is atrocious and that it loses to a 12 core AMD consumer CPU is several tests.Retycint - Monday, October 28, 2019 - link
I mean, nobody is buying Lamborghinis based on their cost-to-perf ratio....AMD is irrelevant in this scenario because it doesn't satisfy the same needs. Not every CPU had to be mass-market oriented
nandnandnand - Monday, October 28, 2019 - link
There's nothing to hate. Intel Core i9-9990XE isn't a real product.euler007 - Monday, October 28, 2019 - link
And exotic sports car aren't real products because they don't make millions of them.nandnandnand - Monday, October 28, 2019 - link
Do they auction them off?If you want high single thread performance from Intel, grab a quad-core.
rrinker - Monday, October 28, 2019 - link
IN a way - they absolutely do. You get 'invited' to by one of those limited production supercars, you don't just walk into a dealer and say here's my 2.5 million. You earn the invitation based on how many other cars by that manufacturer you already own. Want a 1 of 250 Ferrari supercar? If you don;t own any other Ferraris, good luck, even if you have plenty of money to pay for it.29a - Monday, October 28, 2019 - link
Everything is for sale it doesn't matter how many Ferraris you have it matters how many $100 bills you have.vladx - Monday, October 28, 2019 - link
There are cars you simply can't buy no matter how much money you have, unless you're part of an exclusive club.29a - Tuesday, October 29, 2019 - link
No there aren't, everything is for sale, you just don't have enough money.shadowx360 - Monday, October 28, 2019 - link
No, speaking as someone that has walked into a Ferrari dealer with someone trying to buy a Ferrari, the other poster is absolutely right. You cannot walk into a Ferrari dealer and pick up a limited model no matter how many dollar bills you have. Even for something like a 488GTB, you will be waiting years unless you buy every option on the car and lease a crappy model like a California to move up in the queue. You can buy used ones in cash but with Ferrari, they rather protect their brand than cater to new money.29a - Tuesday, October 29, 2019 - link
You didn't have enough money.abufrejoval - Tuesday, October 29, 2019 - link
With *enough* money, you can buy Ferrari and make them sell it, too.It's tautological.
Good thing, though: By they time someone controls that amount of money, they'd see the futility.
arashi - Tuesday, October 29, 2019 - link
With enough money you can just buy Ferrari. Everything that has a price tag can be had, just depends on the depth of the wallet.DillholeMcRib - Monday, November 4, 2019 - link
Some of you peeps seem really, REALLY bored. Do you make all these comments while at work?Retycint - Monday, October 28, 2019 - link
This is a niche CPU for an extremely niche market. That is all. Nobody (except people in that tiny niche) is looking to buy this CPU.AshlayW - Monday, October 28, 2019 - link
Sure it is, so go and buy an i3-9350K for (probably) 1% the price, and have the same single-threaded performance. If you want 14-cores, you're likely going to be doing multi-threaded work, you get my drift?This product has a small niche where you work on both types, and somehow need the 5-10% more ST perf the 9990XE has, over, say the 3950X which will boost to 4.7 on a single core at vastly (and this is a huuuge under-statement) lower power draw and price.
Proponents of Intel claim that Single-threaded speed is so important (because, hey, that 5% is all they have these days) but don't seem to understand that Zen2 has absolutely fantastic single-threaded performance. Within 10% of Intel's best, thanks to slightly higher IPC, and the clock speeds on 1T boost get up there in the high 4 GHz area, too.
vanilla_gorilla - Monday, October 28, 2019 - link
>(because, hey, that 5% is all they have these days)And it's 5% on single threaded tasks that are instantaneous on our desktop PC. I don't have any desire to have 5% more performance there. What I want is the +30-50% performance on multithreaded tasks that have real, wall clock times that can be improved, which is what Ryzen delivers. Who cares if an Intel CPU has 5% better javascript when everything I do in my web browser is instantaneous? So instead of 15ms its 13ms? Ok? What blows my mind is when my kernel compiles or video encoding times are shaved off by MINUTES.
Retycint - Monday, October 28, 2019 - link
I love how people are turning this into Intel vs AMD, even when this is an extremely niche CPU for an extremely niche market.>Who cares if an Intel CPU has 5% better JavaScript?
Well apparently people who buy these care. You are irrelevant to the discussion because you were never part of the target market for this anyway
HollyDOL - Tuesday, October 29, 2019 - link
In scenarios where 'winner takes it all' those 5% are more than enough. Previously I worked on algorithmic trading and there it would be worth every cent.ET - Monday, October 28, 2019 - link
> Against AMD counterparts, that 5.0 GHz frequency carves through anything like butter.From the benchmarks, it lost to the 12 cores 3900X on more than one occasion. While it's true that for specific workloads the 9990XE would be much better, on average it seems to definitely not be worth the price. Also, comparisons to Zen 2 EPYC CPUs (or Threadrippers, which will soon be released) would be much more apt.
chris.london - Monday, October 28, 2019 - link
I was thinking the same. Even if I don’t take the power draw into account I am not impressed at all. And at 600W I would expect this to destroy the 3900X, so these results are actually quite embarrassing for Intel. I personally would rather wait for a 16 core Zen 3 AND pay for it than have this one for free.Retycint - Monday, October 28, 2019 - link
Well I'll gladly take this one for free... Infinite perf-to-price ratio (x performance over $0 price)GreenReaper - Tuesday, October 29, 2019 - link
You may however have to factor in a new motherboard, and new cooling as well.yannigr2 - Monday, October 28, 2019 - link
An over 300W chip that loses in so many cases from chips that cost under $500, with less than half power consumption. And Intel is $auctioning$ it. That isn't even funny. It's tragic.AshlayW - Monday, October 28, 2019 - link
600W for performance that's not even going to be that much over a 3950X (if at all?) Intel is a laughing stock at this point. Can't wait to see the 9900KS, and have a good laugh at the last desperate, dying twitches of the Skylake architecture.29a - Monday, October 28, 2019 - link
HFT should be illegal!MrSpadge - Monday, October 28, 2019 - link
Why? And on which basis would you forbid it? I think the better way to deal with this is to attach a tiny tax to each transaction. So if it's really worth it, they may do it. But the government gets its share and can redistribute to something more useful.RBFL - Monday, October 28, 2019 - link
It has no useful purpose for society, the fact it is difficult to identify the people being harmed does not mean that harm is not taking place.I think making people have a 1 second relationship with a share is not unreasonable. Just because someone can do something doesn't mean we have to allow it. We have speed limits, laws against dishonesty and murder and we could just as easily have one against HFT.
The fact that exchanges sell expensive server space to these companies for lower pings, while purportedly being the arbiters of fair play and price transparency is, of course, another big issue.
rahvin - Monday, October 28, 2019 - link
So anything you in your all knowing capacity deem as not useful for society at large it should be illegal? Doesn't that mean gaming should be illegal?I've yet to meet a single one of these people that complain about HFT that actually understand how the market works, how stock trading function and what HFT even is. Most of them simply heard some talking point they regurgitate without any understanding of how the stock market even works let alone how a stock transaction works or what HFT involves.
shadowx360 - Monday, October 28, 2019 - link
It's a mix of ignorance and jealousy, that they can't be the successful ones rolling in dough, and all investing is somehow evil and taking advantage of the common worker. There are some downsides to HFT, namely increased market volatility and cascading problems where a fall in prices can trigger millions of stop losses that compound the issue, but like you said, most have zero clue.RBFL - Tuesday, October 29, 2019 - link
And that statement is based on?I am not jealous of an industry that has basically bought its way to success through lobbying and every time it explodes it expects the rest of us to reboot it, while mysteriously keeping the proceeds prior to the crash. An industry that gives away billions of our dollars of our money to avoid their own prosecution. Where almost no-one goes to jail after egregious lies, fraud, money laundering,....
All investing is not evil, however many of the practices of the industry are. Lobbying against fiduciary duty for the small investor, for example. If you actually look at the share classes available you will undoubtedly see some that no-one who understood what they were being sold would ever buy. Telling people 'they are responsible for their future' while not cleaning up the industry is like throwing sheep to wolves. And no, it is not everyone's responsibility to know every evil practice in every area of life in which they are forced to deal. It is unrealistic for the well educated, let alone the average citizen. It is why we have laws, which are generally reactive rather than proactive and thus mainly address known abuses rather prospective ones.
Alistair - Monday, October 28, 2019 - link
Nice article, except the final page. Why mention "highest ST for HEDT" and "carves through AMD like butter" etc., then you don't even make mention of any MT performance in summary. You could have said, in MT scenarios, it performs about the same as any Intel 18 or AMD 24 core server CPU or some such.Alistair - Monday, October 28, 2019 - link
my meaning is the summary shouldn't just be for what is awesome, but should also summarize all the results... no mention of multi threading performance on the final page at all, because it isn't special?AshlayW - Monday, October 28, 2019 - link
Agreed. This product is a pathetic attempt to push their slight advantage in single-core, and justify the obscene pricing too. It's disgusting, really, tech press seem to lap up these things without understanding that this product is, well, pointless.Intel made like 5 of them. So, AMD could bin a 3950X so damn effectively, you can have 4.7 on all 16-cores, because trust me with that level of binning; it's possible. But they won't, because they actually have people buying thier silicon for datacentres.
Anyway, the ST performance isn't even that much higher. Nothing worth the obscene price. I'll wait for the 3950X, and hope AT will sing its praises as it will likely demolish Intel's entire HEDT at a lower price and half the power use - it's only fair.
xrror - Monday, October 28, 2019 - link
Guys, seriously...I'm an AMD person myself, but give Intel some credit - I doubt (sadly) that AMD could even release a Ryzen 5Ghz base clock part right now. Granted they might be able to bin out a 4.7 one but....
2nd, everyone going on and on about how expensive the 9990XE. Like it's under $3000? That's stupid cheap! Historically these HPC chips are like 1 or 2 cores enabled out of 12 and you pay over 5 or 10grand for them. Look up the old socket 1366 HPC chips like Xeon X5698 some time!
http://www.cpushack.com/2018/07/03/cpu-of-the-day-...
Korguz - Monday, October 28, 2019 - link
" Like it's under $3000? That's stupid cheap! " maybe in your world.. but for the rest of us, that is stupid expensive.xrror - Monday, October 28, 2019 - link
It is stupid cheap for a halo professional performance part from Intel. But even a cheap HPC - $3000 proc - it is more money than I could ever justify personally spending for what would essentially be a glorified gaming rig.Which means, we're not the target market. Even in your world.
Retycint - Monday, October 28, 2019 - link
The whole point of this chip is that it throws price-to-perf out of the window for highest possible ST perf sustainable on all-cores. You know, like what the article describes?But sure, AMD has better value or something, so everyone that buys Intel is stupid, despite the fact that different people have different usage scenarios and, gasp, Intel performs better under certain cases
FreckledTrout - Monday, October 28, 2019 - link
This was fun to read even if it is akin to describing what a brown unicron looks like.airdrifting - Monday, October 28, 2019 - link
Everytime there is a worthless product from Intel or Apple you always see fan boys and smart ass trying to defend it.Single threaded 9900K >=
Multi threaded 2990WX, maybe even 3950X >
1_rick - Monday, October 28, 2019 - link
If you click the link to Case King, they've cut the price to 1799EUR/1996USD (at today's rates).29a - Monday, October 28, 2019 - link
Please get rid of the 3DPM and FCAT benchmarks, the article even admits they are both poorly written.MrSpadge - Monday, October 28, 2019 - link
Ian, what happened to your appetite for chips? Are you ill or is this toasty piece of egineering not tempting enough?xrror - Monday, October 28, 2019 - link
Hey Ian, please again thank ICC for letting you guys have a full run though with one of these systems.While yes, this will never be a practical option for the vast majority of people, it IS one VERY AWESOME datapoint(s) for benchmark purposes. No more hypothetical "but what if 5Ghz Skylake" no - you have actual numbers, it shows the scaling for Intel's current'ish gen out to the extreme end.
I hope you are able to run more on this box to fill out the numbers in Bench - (which you may have already, I haven't actually looked yet).
Again thanks to ICC and Anandtech for this.
MrAndroidRobot - Monday, October 28, 2019 - link
If like to see how the 3900X fairs in comparison given its 12C/24T and holds up well against current TR/HEDT CPUskrumme - Tuesday, October 29, 2019 - link
I cant really tell how this is different from my 8700k from a performance perspective.Looking at the article i think this is cheap marketing. Good move. But anyways it's crazy 14c cpu is now touted for their single thread performance. Seriously one have to wonder the meaning of all this. What am i doing here? Lol
TheJian - Tuesday, October 29, 2019 - link
Please test SLOWER/VERY SLOW not FAST/FASTER for encoding. I would not STORE anything ripped at FAST/FASTER...LOL. Who rips at this crap quality level? Besides, with 14c why wouldn't you want top quality (or fairly close)? It's not much more time and might yield completely different results. Never understood why people keep running tests that are NOT how we would USE the tested device/game etc. Test it like we USE it or quit wasting your (our?) time.Raise your hand if you're ripping your blurays with fast/faster settings...Nobody. You can rip with SLOWER faster than you can create the content on these chips today, so why ruin your vid? L4.1 HIGH, VERY SLOW. Done (and I do 2pass, control other settings too, but you get the point). Nobody is archiving anything with your settings right? Emulate the pirates (seriously, one NFO file can tell you a LOT about these settings) :) They would NUKE your rip. Mediainfo can tell you all the settings also if you don't know where to get an nfo file from the people who've been ripping since the net started...LOL. Just saying...It's like claiming 1440p is the new enthusiast resolution (Ryan did this in his 660ti article...ROFL - see the comment section where I destroyed that crap), which isn't even true TODAY...LOL. YEARS later. Wake me when 1440p hits 10%. Right now it takes 1440p+4k to hit ~6.5% total...ROFL. 1440p is STILL not even 5% yet (4.98...ROFL). 1080p however 65%! Hmm, where should we spend MOST of our time testing then? Ah, UNDER 1440p with 4k being a complete joke still at 1.6%.
https://store.steampowered.com/hwsurvey/Steam-Hard...
Wrong still for 7yrs Ryan Smith, AND counting. Is 10% even good enough to call it the new enthusiast resolution? Maybe Ryan will be right 2020. I digress...Don't even get me started on the complete BS that 4k testing is (1.6% of 130mil steam users say 4k is still dead). Apparently people don't like turning crap down (that devs meant for us to SEE) as much as Ryan etc think. :)
GreenReaper - Tuesday, October 29, 2019 - link
It's true that relatively few systems have a high-resolution screen. In fact I'd go further and say that for general usage of current systems, the combination of 4K+1440p is closer to 3% (with 1440p being ~2.5% of that). That's what I see on my media hosting website.However, enthusiasts *are* the 3%. Or at least a lot of it. Most people use all-in-ones, work laptops, or school netbooks. They may install Steam on them and game on them, because they have to - they probably didn't buy new hardware specifically to do so. Reviews are all about new hardware.
If they *did* want to buy a new piece of video hardware, they may want to know how it'd perform if also buying a 1440p monitor and plug it in, perhaps once prices come down a bit. Or even 4K!
It's also a better way to measure GPU power than running them in a CPU-limited zone (after all, your GPU may end be paired with a future CPU by the time you buy it). The higher-end cards that tend to be reviewed are also intended to potentially last multiple CPU cycles - in reality I suspect most buy something further down the scale and just use it with one CPU, but it's an option.
Your point is fairer with IGP, but that's what IGP level is for. Most serious gamers are not using IGP. And this review doesn't *have* any GPU tests, though, so your comment may be better saved for one that does; it came off as ranting a little too hard about Ryan. :-)
TheJian - Wednesday, November 6, 2019 - link
Of course reviews are about new hardware...But the point is about HOW you test them. Are you acting like I'll MAYBE, if the wind blows right, stars align, etc, in 5yrs, or are you testing for what we will do with it for the next few years NOW? You know, like what I actually BOUGHT it for, NOW. I'm an enthusiast (know pretty much only them, since only deal with IT people pretty much), and have nothing like what they are pushing (no 4k desire for anyone I know, most not on 1440p). It isn't because I can't afford 4k, just don't care (for many reasons currently, lacking gpus for one, you need TWO still). I can afford those two titans every month too, but what for? They'd fry me in my PC room after 30mins of gaming due to heat in my state. So I'm stuck waiting for a 7nm NV card that takes AMD's 7nm a step further in watts heat (or I'll just downclock their no doubt better 7nm version since they waited) so I can play my next monitor (hopefully xmas this year or next) at max details, and of course my current 1920x1200 will be maxed finally by it until I finally see a monitor I want (c'mon dell 30+ with gsync). I'll pay $1200, just make it!I see nothing wrong with "ranting" (not how I see it, but whatever) if you're still right and it is relevant to 95% of users who are STILL not using stuff like they seem to think we do (and you keep testing stuff WRONG over and over). The point is a pattern of reviewing products in ways we don't actually use them. If 95% of users were running 4k monitors, it would be just as stupid to test 720p all day in every review right? Unless you're trying to prove a specific point by doing said test, there is no reason to wash rinse and repeat this. Your review should cover your audience NOW, with a mention of the future maybe as an afterthought (like RTX on day one, hmm, hope they use it). RTX didn't fly off the shelves until more about the features came out. Most people don't care about the future of their tech, they are buying for today's perf or features they need.
No, The same people buy new titans yearly (Multiple Titans in many cases, 4 at a time, 2080ti's also) according to Jen Hsun himself. The bulk of top sales go to the same rich who can afford them yearly easily. Heck I can afford them too (easy with no Visa bills, no car (cash), no cell, no cabletv (just HSI), just don't care to act rich for not much more perf :)
More than 3% buy enthusiast cards. Heck 3% of sales is likely Titans alone, and that card alone is not what I call enthusiasts (Ryan thought it was 660ti back then, it was NOT the top card, probably correct too, but it wasn't built for 1440p he was pushing). Anything over $250, you're probably more than a casual gamer.
NO serious gamer is using igp...LOL. Do you know serious gamers who play 720p with details down? I don't say NEVER test 4k or 1440p, I say there is no need to spend 2/3 of each review of gpus on this crap (you can read many posts of mine in reviews like this). TEST more of what we PLAY at NOW, RIP at quality levels most would want to watch, etc. When the future comes, I'll be on other hardware (probably most enthusiasts huh?)...ROFL. Test a few games a year in a 4k review, no need to do it repeatedly as if it is used by more than a few %. People are FAR more interested in how it works NOW as I use it, than "futureproof" junk I may never use if nobody supports it ever. I'm not against testing a 4k game per review, but not a 4k test for every game in said review. Same for ripping, I humbly ask who watches this crap quality? Why are all the ripping tests in crap qual? They turn off stuff users specifically BUY NV cards for. You know, like acting CUDA wouldn't be used by a NV buyer if they had a choice. Nobody buys NV to do OpenCL...ROFLMAO. You buy for CUDA if you can for your app. I could go on, but you should get the point: TEST IT LIKE WE USE IT, no matter what you're testing today, tomorrow, etc.
My point is fair for ALL single gpu cards, as there isn't one yet that can do 4K on ALL games without turning tons of crap down on a per game basis. Pricing isn't bad, so this is clearly a big deal to people. No point in buying something new, only to degrade it's perf out of the box just to get enough fps to enjoy your game (not as the dev intended you to see it at this point either). But, then, I don't enjoy that game at this point. I need the details ON.
IF, if, but, maybe...blah...How about spending MOST of your time testing what we actually DO with whatever you are reviewing, instead of wasting time on what YOU WISH we used this stuff for. This is why Anandtech is my last resort these days and tomshardware even less used (same site really now).
mode_13h - Tuesday, October 29, 2019 - link
Isn't the myth of high-frequency traders using tuned CPUs a bit overblown? I'm not saying it doesn't happen, but would they really even go so far as to forego ECC memory?MrSpadge - Tuesday, October 29, 2019 - link
I guess you have to be fastest to earn serious money. And there's no "fast" ECC RAM in terms of desktop OC. If with ECC you can get a guaranteed answer too late, it's not going to matter. Better risk the seldom error without ECC - it's probably going to be fine...Bp_968 - Tuesday, October 29, 2019 - link
So I'm a true blood capitalist but I just don't see the utility or reason for existence for "high speed trading". They are making money on the difference between prices at the millisecond level. It offers nothing back to society and seems to exist only due to how stock and commodity trading works.Stocks should exist for public ownership of companies, to provide funding for those companies and hopefully for the stockholders to benefit from the growth and profit of said companies.
It shouldn't exsist as a glorified casino game, which is essentially what "high speed trading" is.
crotach - Tuesday, October 29, 2019 - link
So it's good at compiling stuff?DazFG - Tuesday, October 29, 2019 - link
Would like to see a average performance/Watt chart.abufrejoval - Tuesday, October 29, 2019 - link
The older 3Dmark physics tests don't scale to all available processor cores, so those numbers are misleading. My observation has been that the newer/more demanding the base benchmark, the wider the physics. So e.g. I doubt that Ice Storm actually scores beyond 4 physical cores, while I have seen the physics benchmark correllating to the DX12 graphics (keep forgetting the name) actually pushed all 18 cores in my workstation. I run HWinfo on a secondary screen to monitor what's happening on the system and it cleary reflects that most cores aren't used on these CPU-only physics tests.abufrejoval - Tuesday, October 29, 2019 - link
1.290V at 5 GHz all core may be "amazing" but it should really be "expected": Any chip that requires more voltage and thus power to push electrons through layer interconnects will fail the binning because of heat. And with every little part of 14 cores and their caches needing to qualify, it's easy to see how rare these are.DixonSoftwareSolutions - Tuesday, October 29, 2019 - link
I'm still holding out for the i9-9999XE.Hifihedgehog - Tuesday, October 29, 2019 - link
Agreeing to disagree with you, Ian, after seeing the benchmark results, I would hardly call this the slam dunk and beast it is made out to be. It is good in several benchmarks but it is highly specialized to the point I would argue the 9900KS would be the better choice of the two in nearly all cases for high frequency applications and the 3900X (and by extension 3950X) in multi-core applications. All in all, I am not really impressed and even less so with Threadripper 3000 and Cascade Lake on the verge of release.lejeczek - Tuesday, October 29, 2019 - link
Who cares about tests done on Windows? Who would bother with Chrome compilation on Windows?? Author(s) sees that increasingly more tests are being done with Open Source and clumsily tries to mimic that. But for those interested in real testing - go to phoronix.com and openbenchmarking.orgLots love, xxx.
Urufu - Tuesday, October 29, 2019 - link
Not interested because that's not the real world that people experience every day when using these microprocessors. My apologies for seeming abrupt.lejeczek - Thursday, October 31, 2019 - link
This certainly will sound abrupt - it's for that tiny little world and tiny people in it - the office?? Step outside for a moment and look at big data, clusters, HPC, all sort of servers & services, also academia! Linux & open source everywhere. Why?Might think... some media streaming, transcoding, codecs, etc. you might need that i9-9990XE beast in the office and for windows - sure if you click once here once there to run something - heavy duty transcoding that's Linux all around the clock.
But if one does only pure 'office' and thinks s/he must have this i9-9990XE - well these are the same sort of people who even today when it makes no financial sense whatsoever(do not mention this is not 'office' cpu), who have been happy to pay hefty taxes to Intel for years, those people will do it anyway, will waste money on it, as they do with anything else I'm sure.
But anyway, 'the office' stuff also we do with Linux, easy.
TEAMSWITCHER - Wednesday, October 30, 2019 - link
There is still a metric-sh*t-ton of software development that happens on Windows.MattZN - Tuesday, October 29, 2019 - link
Did you say 600W under full load? For a single CPU socket and only 14 cores? That isn't a wattage that will beget a limited market. That's a wattage that makes the chip D.O.A. No market. At all. Anywhere. Not for 'high frequency trading' or anything else.-Matt
Arc1t3ct - Wednesday, October 30, 2019 - link
I'd like to see the cinebench score for this cpu. It's probably the single most important performance metric for Architects and engineers.ballsystemlord - Wednesday, October 30, 2019 - link
Spelling error:"Blender can take advantage of more cores, and whule the frequency of the 9990XE helps compared to the 7940X, it isn't enough to overtake 18-core hardware."
"while", not "whule":
"Blender can take advantage of more cores, and while the frequency of the 9990XE helps compared to the 7940X, it isn't enough to overtake 18-core hardware."
ballsystemlord - Wednesday, October 30, 2019 - link
What's interesting about this processors benchmarks is that even at 5.0GHz AMD's Zen2 processors are still fairly close. -- Not that I'm trying to attract fanboys, it's just interesting to compare the IPC, memory latency, etc.TitovVN1974 - Wednesday, October 30, 2019 - link
IMHO, Linpack (Intel® Math Kernel Library (Intel® MKL) Benchmarks) with not-too-many cores gives good upper bound estimation of practically obtainable perfomance in engineering and science.ballsystemlord - Wednesday, October 30, 2019 - link
But only for Intel processors...edwardhchan - Wednesday, October 30, 2019 - link
Caseking is selling them for 1799 Euro with stock promised from Nov. 12.... So I guess the demand is low?cschlise - Thursday, October 31, 2019 - link
As I look at this and the struggle to make predictable quantum computing hardware, I see us reaching an inflection point where "traditional" methods will have to adapt a hybrid quantum piece because the features will have shrunk to the point where quantum effects become the norm, vice the exception.cschlise - Thursday, October 31, 2019 - link
What all this testing is showing me is that I should buy a mainstream Ryzen 9 3900X for $530 at newegg right now.yetanotherhuman - Friday, November 1, 2019 - link
Wow. There are times when it doesn't even touch a 3900X. This is not a desirable product.Icehawk - Friday, November 1, 2019 - link
So no latency testing of any kind... which is what this machine is about.Rοb - Friday, November 1, 2019 - link
"... These companies not only pay through the nose for the hardware, but also pay experts and specialists to tune those systems for low latency. That means tweaking the memory, overclocking the processor ...".Financial trading is often done on the Network Card, see NextPlatform's article "Hypercalers Lead The Way To The Future With SmartNICs" or Wikipedia's "Reducing latency in the order chain".
When the network card has received a bit of the packet it's starts reviewing which decisions it is able to make based on a partial packet, further narrowing down it's options as more data is received. If it's lucky it can send an order before the packet is completely received - if it can't it calculates if it's worth bailing out or running late with the others.
The CPUs on HFT machines have fewer CPU cores that can be overclocked since they only need to convert orders to the FPGA. Trading is so fast they implemented 'speed bumps'.:
"The IEX speed bump—or trading slowdown—is 350 microseconds, which the SEC ruled was within the "immediately visible" parameter.".
DillholeMcRib - Monday, November 4, 2019 - link
I dunno, considering my 3900x is being cooled by a 240mm AIO and at boost barely goes over 105W and yet gets up to a toasty 78C I am pretty sure I don't want to even imagine that damn cooling rig it would take to keep Intel's 200W+ monster cool under boost. I don't have that much need or interest in such a thing, and if anyone else does I sure hope you live in a climate that lets you pull in -10C air into your case.WaltC - Wednesday, November 6, 2019 - link
Be kind of fun to test this placeholder from Intel with air cooling pitted against air-cooled AMD competition. Yawn...poor Intel, it's going to be a lot of last gasping from them until they put Ryzens and TR's and EPYCs under X-ray to figure out some aspects of manufacturing a modern CPU...;) I'm sure it's all been very instructive for them.simthanglong - Monday, June 1, 2020 - link
Sim Thăng Long - Sim số đẹp, giá rẻEmail ĐK: [email protected]
User name: simthanglong
Giới thiệu: Sim Thăng Long là một trong những đơn vị cung cấp sim lớn nhất toàn quốc, luôn mang đến sự tin cậy cũng như hài lòng cho mọi khách hàng.
Địa chỉ: 22 Ô Chợ Dừa, Đống Đa, Hà Nội
SĐT: 024 6666 6666
Email: [email protected]
Website: https://simthanglong.vn
File LOGO: https://simthanglong.vn/images/sim-so-dep-simthang...
Headline: Sim Thăng Long - Sim số đẹp chất lượng, giá rẻ nhất Việt Nam
Description: Sim Thăng Long là một trong những thương hiệu luôn quan tâm đến những nhu cầu của khách hàng và cung cấp ra những sim số đẹp và giá rẻ nhất
Hastag: #Simthanglong, #Simsodep, #simgiare
Bài giới thiệu: Sim Thăng Long được xem là hệ thống phân phối sim số đẹp lớn nhất – Uy tín nhất Việt Nam với hơn 12 triệu Sim Số Đẹp, Sim Phong Thủy, Sim Năm Sinh… của tất cả các nhà mạng lớn tại Việt Nam, đáp ứng mọi nhu cầu về sim số đẹp của Quý khách hàng và giao hàng trên toàn quốc. Tất cả những sản phẩm sim tại Sim Thăng Long đều sẽ được đăng ký miễn phí thông tin chính chủ và được cung cấp từ các nhà mạng lớn nhất Việt Nam như Viettel, Vinaphone, Mobifone hay nhà mạng Vietnamobile hoặc Gmobile, iTelecom. Để tìm được sim số đẹp ưng ý, quý khách hàng có thể truy cập website: Simthanglong.vn hoặc liên hệ hotline: 024.6666.6666 để được nhân viên tư vấn cụ thể khi có nhu cầu tìm sản phẩm sim phù hợp. Quý khách hàng cũng có thể tìm đến hệ thống cửa hàng của Sim Thăng Long trên nhiều tỉnh thành khác nhau trên cả nước để được nhân viên bán hàng tư vấn và giúp lựa chọn được số sim ưng ý.
simthanglong - Monday, June 8, 2020 - link
sim phát 868686 với nhà mạng dạng số cùng đủ các khoảng giá tuyệt nhấtsim đuôi 868686 với các đầu số Vietnamobile, Vina, Mobi, Viettel, Gmobile cùng đủ các khoảng giá, ưu đãi tuyệt nhất cho quý khách thỏa sức lựa chọn tại Sim Thăng Long.
mua ngay sim phát 868686 các mạng Vina, Viettel, Vietnamobile, Mobi, Gmobile được để với giá tốt tại Sim Thăng Long ngay nào!!!
Link
https://simthanglong.vn/tim-sim/868686.html
Liên hệ
Hotline: 024.6666.6666
Địa chỉ: Số 22 Ô Chợ Dừa, Đống Đa, Hà Nội.
Danh sách tham khảo sim đuôi 868686
0369868686 ---> 240.300.000₫
0334868686 ---> 130.000.000₫
0335868686 ---> 315.400.000₫
0358868686 ---> 224.300.000₫
0813868686 ---> 221.300.000₫
0838868686 ---> 425.500.000₫
0946868686 ---> 436.500.000₫
0777868686 ---> 306.400.000₫
0705868686 ---> 249.000.000₫
0704868686 ---> 200.000.000₫
0398868686 ---> 216.300.000₫
0764868686 ---> 297.900.000₫
->> Sim Thăng Long cam kết bán Sim số đẹp với giá hấp dẫn nhất - chuẩn số - free đăng ký chính chủ - Giao sim tận tay - Kiểm tra sim rồi gửi tiền.
#Simthanglong, #Simsodep, #Simgiare, #simlocphat