It will be quieter than a rackmount server since there's more room for bigger, slower-turning fans that move the same rate of air, but at full load is still likely to be quite loud.
I had one of the (now 2 gens) old Z6xx series workstations issued by work, and I ended up buying a second hand one from eBay to replace it when I moved jobs.
It was dead silent. I could hammer all the cores, RAM and disks, and not hear anything from it.
At one point I had 4 of them under my desk, and there was more noise from the MacBook Pro.
According to the SSG website, Autodesk Maya will fully support the SSG, including the 2TB memory.
"ProRender plug-in for Maya has full support for the out-of-core rendering feature found on the Radeon™ Pro SSG which allows the application to tap into the full 2TB of memory found locally on the card. This allows users with very large models to render fully accelerated by the GPU. "
The fact that "2TB is addressable" is irrelevant. Putting NAND on the board doesn't improve latency/bandwidth nearly enough to function like vram. Nvidia has also supported unified virtual memory since Pascal, meaning you can address your cpu's ram in GPU code. The "SSG" card still has the 2tb of flash on a PCIe interface, so not much difference from existing systems beyond marketing. I'd expect very few real world perf wins.
These days if you need proper compute, you need to focus on the GPU. NVIDIA 10 series GPUs are 10x the throughput of high end intel CPUs, and less than 1/10th the cost. It’s not even funny anymore. It’s a shame you can’t even have 4 GPUs in such an expensive and bulky workstation. Back to the drawing board, HP.
Very few applications can make use of such a large amount of GPU cores - and all of them would need much more CPU cores than this provides to coordinate the work.
Any applications that can would be either run on clusters of servers to really parallelise the work, or is so custom you may as well buy a threadripper and a custom case.
Hell most apps can barely take advantage of multi core CPU.
You got that last sentence right: I’m not aware of any apps which can take advantage of even half this many cores. Intel is deficient in terms of memory bandwidth, so most things begin to flatten out at 8 physical cores or so, and take a nosedive when you attempt to use all of them.
While you are right that there are very few apps able to take advantage of quad GPUs, for anyone who does serious number crunching it’s not a problem at all to use all of them using popular deep learning frameworks. They aren’t just for deep learning, you can do a lot more with them. And e.g. PyTorch will automatically parallelize certain things across multiple GPUs for you, with near linear speed up.
Yeah - my use case is kind of specialised, but I could use them all, asking as I can use NUMA to pin memory to physical CPUs.
I wpild be interested to see how pytorch scales GPU wise, relative to CPU clock speed. I am sure there is a point where it will fall off, but not having a 4 GPU system I can't check :)
It’s basically linear as long as CPU can feed the GPU with data. That’s because there’s no cross-GPU communication during the expensive part of the computation (ie forward and backward pass of a neural network). You shove data in, GPU computes gradient, you apply weight updates and redistribute new weights (which are usually not that large). Running the same workload on even the highest end general purpose CPU is glacial compared to even a modestly priced Pascal GPU. That said, there is a limitation: you can’t really have more than 16GB per GPU today, no matter how much you pay, and GPUs can’t do branchy workloads like SQL, compression, etc.
CST will use them for EM simulation, with near linear performance increase for added GPU. I have 4 Teslas in my Microway workstation. Fortunately it also allows for the addition of a decent graphics card, so I can run 3x 4k monitors.
I somewhat disagree. Maybe there are few compiled applications that can use those resource, but it's easy to write code that uses all of them.
I have a 40 core CPU machine with a GTX 1080 Ti GPU. I run deep learning models with 90% GPU utilization and those 40 cores are barely used.
I would love to have 3 more GPUs to run in parallel to test different neural network architectures. Sometimes I'll run a CPU script at the same that processes machine learning data that uses all 40 cores.
I would use 4000 CPU cores and 10 GPUs in a machine if I could get them and I don't even do machine learning full time. I'm personally happy to see this trend of more core counts.
If you run algorithms from sklearn or just plain numpy it would make great use of the CPU. I was surprised to see the CPU just as useful as the GPU, maybe even more, in my ML projects.
If you are talking about srlf-build, there is reason to avoid that for people who can afford. It is called warranty. Hardware rig like this goes through testing and the support package usually is pretty good. I don't have first-hand experience, but I know Oracle would send engineers onsite to troubleshoot if required. Unless you are ready to tackle the build, the testing, and the support of the hardware rig, you want to avoid. You don't have to be Dropbox or Netflix (I don't believe they build custom servers like facebook and Google does, perhaps they buy from other vendors or from opencompute project).
Indeed, we recently asked invoices for a new machine for deep learning with 768GB memory, modern Xeon CPUs and the latest generation nVidia Tesla. The HP offer costed nearly twice as much as Dell's.
Because there is huge demand due to smartphone production. Up to 2015 prices were OK, you could buy a 8GB DDR3 non-ECC dimm for $20. Now you need like $50.
I've got an HP Z640 workstation with dual E5-2690 v4's and it is basically silent under full load. It has no problem running all 28 cores at 3.2GHz which is the max all-core speed for that processor.
Only 8x8GB since I'm working on CPU limited simulation tasks. One of the CPUs and 4 of the DIMMs is on a daughter board in the Z640, which makes the whole thing even more impressive. It's a fairly compact machine. Storage is just a single SSD and single HDD. Graphics is a low end Quadro just to get the 4x mini-DisplayPort. The HP Z8xx series would probably be a better choice if a person is going to go crazy on the rest of the hardware. But that's just conjecture on my part based on the fact that my current processors are running near TDP (but aren't being throttled down based on the monitoring I have done.)
Electric grid dynamic/transient event (disturbance) simulations. It's essentially modeling the response of electromechanical equipment (generators and large loads), large solid state devices (utility scale renewables and fast-switching reactive devices), lumped load models, and protective devices to events on the electric system. The simulations run in ~1ms timesteps over 10-30 seconds of real world time (which can take 4-20 minutes of CPU time). Each event is independent and they parallelize pretty much linearly. Python multiprocessing is the lifeblood of this work.
Edit: I guess I should be clear and say that the simulations themselves are running on a commercial software package (Fortran based) and I'm simply setting them up, spinning them off, and then processing all of the resulting data in Python.
Neat. I do a lot of RF simulations. Even though it's 60 Hz vs 60 GHz, I suppose a massive electrical grid has the same distributed effects that can cause standing waves and stability issues.
I have a z820 32 cores, 128GB of RAM, 3 nVidia GeForce GT 710 cards, and 3 x 5TB drives. You're not missing much with the z640. I have a z620 as well. The z620 just has 2 fewer PCI-E slots. The difference is the same for the z840 and z640.
I just assume that the larger Z8 chassis might handle the heat a little better? The Z6 works for my use, but the CPUs are definitely running on the hot side.
Maybe. With a bunk front fan on my z820, everything still runs relatively cool at maybe a max of ~55C (2 CPUs, 3 GPUs, 16 sticks of RAM) according to sensors util in RHEL.
Can you explain the 3x Nvidia 710s? The only reasoning I can think of is running ~6 monitors silently, but the heatsink-only cards aren't usually used in prebuilts so I'm a little confused.
Who needs something like this? What is your job? What do you use it for?
Really curious. I deploy code to a large production server cluster, my friends in academia submit code to large scientific computing clusters, but I don't know of anyone with this much power in their own desktop. I guess I've been in video edit suites with machines much more powerful than the average PC, but not this crazy.
You see workstations like this in what I'd call "interactive simulation." Stuff where you're designing something complex via simulation and want to be able to rapidly evaluate changes. For example ANSYS (hybrid finite element simulation and CAD) works best on a single workstation and you want it to be fast so you can make quick changes. Or when your geometry is so complex it doesn't fit in any reasonable amount of memory and your code doesn't support distributing it (which is very hard for a lot of simulation types). The (Sauber? I think HP sponsors them) F1 car from the image in the article is a good example of someone who might one one of these.
A lot of battle-tested engineering software doesn't do distributed-memory parallelism well. I've personally used MCNP and GEANT4 (particle physics software) on a 48 core, 1 TB RAM workstation. It's interesting browsing the web while the computer is running gigantic calculations in the background on two [physical] CPUs, hooray for the process scheduler doing a good job.
May I suggest compiling software? For people without access to distributed build and test a box like this is really nice. I do have access to a huge distributed build farm but even then I use a beefy HP workstation because the software that drives the build farm is itself a bit of a pig, and massively multithreaded.
I'm an OpenShift Consultant for Red Hat. Super awesome to be able to run or build from scratch a 9 node HA OpenShift cluster without incurring an AWS or other infrastructure costs.
My usage is for building IaaS software. With a machine like this, I can have VMs with VTX passthrough turned on, and simulate a cloud, without a rack of physical servers.
As a remote employee it allows me to most of my development locally, and then use larger environments for a shorter period of time later on.
Combine 3 or 4 of them, and I can have an actual cloud running under my desk, for testing things like kubernetes deployments, with enough capacity for a few concurrent test environments.
As I said above they run basically silent, so I can use them in a shared office space without annoying my neighbors.
I've been building out cloud IaaS demos (VMware, KVM, the works) for a decade now and since the beginning I've always needed basically the most amount of RAM and cores that could be shoved into a single physical box. Otherwise, I'd wind up swapping to disk or doing double-nested VMs with mere MBs of RAM and that was horrific before SSDs were cost-effective either. Nobody else besides doing weather simulations / HPC or video editing seems to need this much compute either.
I've been hearing of people buying Mac Pros for cloud demos so they can run VMs on them locally because they're among the most compact, compute and memory dense systems you can buy.
Interesting, thanks for sharing. My instinct would have been to rent a few dedicated boxes from a OVH for something like that. What made you decide to go with local boxes?
It lets me defer the inevitable Chrome Tab Bankruptcy. But seriously, having a heavy build system with lots of dependencies will easily max out a desktop like this.
dreamworks gives their artists machines like these so they can see the results of physics simulations on their animations in real-time while eduting instead of waiting for a bake step including things like hair and cloth
Security reviews. Powerful enough to run multiple VMs to simulate caching server, web server, app server, and database tier while simultaneously recording and as necessary tampering with all network communications while running static and dynamic code inspection tools across multiple VMs. Load it up with some high-end GPUs as well for hash cracking. Memory is a big deal as well. I work with some programs that if you are running anything under 64 GB of RAM you could be waiting all day for results and 256 GB is preferred but can still be sketchy as that may not leave enough for VMs. If you are a researcher doing fuzzing, again, this sort of power is key to reduce a fuzzing run from maybe a month or two on a a high-end laptop to a few minutes.
Running inadequate machines waste time of otherwise expensive engineers. The other day I was giving a live demo of an interception proxy and accidentally clicked on a very large HTTP response. The machine I was using only had 32 GB of RAM so I had to open task manager and kill the app so I could re-start it because the meeting would have been over by the time it loaded due to disk caching.
Do you need it to be local for GUIs, or for confidentiality reasons, or it's just cheaper? I assumed most people needing beefy VM hosts would remotely access servers in datacenters (whether cloud or company-owned).
I used one a couple of years ago for image processing. TIFF stitching workloads were still a "go get a cup of coffee" timescale but it was amazingly fast for everything else.
I use a 2x12 core Xeon v2, 128GB RAM. I work full time on OS kernels, mainly FreeBSD. It helps a ton for building kernels, world, packages, and running lots of VMs. Thinking of doing the Talos II as the next step.
Imagine doing web dev in a language where you refresh the webpage to see if it worked vs having to run a long build. The former is better, even though it's not really as good as careful reading of your changes, but there are many times throughout the day when you just want the compiler to bark at you to clear any stupid type or syntax errors. The faster your machine and more parallel the build, the closer you get to that web dev experience.
I've got a workstation - not quite that spec but not far off it. I work in game development, and we work on a multiplayer game. Being able to run multiple instances of the game is crucial, (game server, plus 2,3,4 clients, sometimes with rendering, sometimes without). On top of that, our codebase is gigantic, and takes about 40 minutes to build on our workstations (slowly growing). On my i7 at home, it takes well over 2 hours.
I don't have one, but I nearly every day wish I had. I work on database, currently a lot of performance stuff. It's really annoying to do performance work on consumer HW - not enough memory (32GB is the biggest I have seen in portable laptops, and that's what I have) for interesting loads, regular thermal throttling screwing up benchmarks, single socket systems having drastically different performance characteristics than bigger NUMA ones...
Having access to machines remotely can replace some of that, but it definitely costs time.
My desktop is a 2690v4 with 128GB RAM. As a computational physicist I have access to a number of supercomputers to do larger simulations on, but queue time on them can be a hassle for 'smaller' jobs that a regular desktop can't handle. So having a decent middle ground machine is very useful for low resolution testing of jobs you'll throw at the supercomputer later.
Compiling C++ codebases. I have a 170 KLOC codebase that compiles in 20 minutes on a single core. Ideally you'd have at least 40 cores to make changing headers bearable at all.
I do 'small data' analysis and having a machine powerful enough to not have to deal with clusters is a godsend and saves me so much time. With 64 gigs and a dozen cores most of my needs are handled. And if I had 128 gb and 24 cores I'd be able to do even more.
Not a user of such behemoths myself, but in my organisation we've got a lot of GIS people and a few design/architect folks that work a lot with huge datasets, complex models etc that require a fairly large amount of horsepower.
It's funny the things that need a lot of beans to run; I was sitting with one of the GIS guys and he just clicked a button which then caused all 24 cores on his rig to flatline for about 4 minutes. The end result? A map of our city suddenly had a few boxes drawn over the top of it. As it turns out he was pulling in data from half a dozen sources to map out areas where there was government run housing that experienced higher than average levels of emergency services call outs. Apparently, in the past doing that manually would probably have taken several people about a week to do and wouldn't have been as accurate.
Seconded - HP Z series are very good quality workstations - very less noise and great Linux compatibility. You can find them cheap as HP refurbs if you want warranty like new, otherwise eBay has them for quite cheap too.
If I wanted to build something like this myself, are the motherboards fairly commodity? Or do you get into bizarre non-ATX custom form factors with bespoke cases and PSUs to match?
I've built plenty of gaming rigs, but have never been interested in this world until recently... and would appreciate any insight :)
For something at this level of sophistication, you'd typically use an integrated case/cooling/motherboard combination from a company like SuperMicro. You could always buy a board and mate it up with another case, it will likely be a SuperMicro board...
CAD, 3D workloads, 4K/8K video editing, stuff like that. They're great for running dozens of VMs especially if you're running with SSDs and a non-integrated RAID card. The integrated RAID chip on the z820/z620 is horrible.
I used to use them as hardware for a test and development OpenStack cloud. On a decent spec'd Z620 I could simulate a full OpenStack cloud, and even boot quite a few VMs inside it for end to end testing.
Do you generally run openstack on host OS itself or within VM? Or to clarify - I have noticed some problems when Openstack runs inside virtualized environment, but if it directly runs on host OS itself, it seems to be fine.
With OpenStack it is generally recommended to run it on bare metal boxes. Likely, the issues you're running into are network based (or running an SDN over an SDN).
You install VirtualBox or Ganeti on it, create 100 VMs for various purposes for your company. Build Agents, Spikes/PoCs, any and all purposes. Its like a cheap local cloud.
I honestly have no idea why "home" servers are so bloody loud. My desktop is more powerful than any of the machines at my company and it doesn't sound like a jet turbine--even at full load. And even when our servers aren't fully spun up, the fans are so loud and droning even at lower RPMs!
Is it an issue of "overpowered" fans (for really hot rooms), or is it really just an issue of "cheap as crap" fans by OEMs?
It's the physics of the volume of air that is being moved by the fan. A 2U tall fan has to spin twice as fast to move the same volume of air as a 4U tall fan. A 4U is roughly the same dimensions as a full height desktop or workstation. They probably employ lots of 2U servers.
Same here. I'd use mine to just do regular stuff my laptop handles right now. But I'd know I'm browsing facebook on a freaking supercomputer. And that'd make me happy :P
I've purchased whole racks full of servers that didn't have as much compute power and cost a heck of a lot more than this. I use a nice mobile Titan but it is nothing compared to this.
What crazy times we live in. I can't justify buying one of these. I keep tying to come up with a good reason. I suppose YouTube would finally run smoothly.
The TSV technology that the 128GB DDR4 LR-DIMMs uses is still very new (Samsung is the main vendor at this point). It is only recently that the price of 64GB LR-DIMMs are getting close to the price of 32GB RDIMMs. As a side note, you also need special Xeon models to get the full 1.5TB per socket with the 128GB DIMMs now.
If the prices of one of these new are a bit out of your budget, but you still want a relatively powerful workstation, take a look at used machines from a few of generations ago.
Last year I picked up a Dell T3600 with a Xeon E5-2670 (V1 - 8C/16T) and 32GB ECC RAM for €400 delivered. It's not completely silent (maybe HP are better in that regard based on comments here?), but it doesn't make much noise - at least compared to what you'd expect from the power it gives.
I now work from home, and having previously primarily used laptops, this thing feels like a beast.
Yes if you want something that needs the fastest CPU you probably don't want this machine, but in that case you are probably willing to spend a lot more. The laptop I upgraded from had a score of 250, so for me it's a big difference.
I checked prices for sourcing my own hardware on the same platform, but it would have been a lot more expensive. The problem here in Europe is there is less second hand enterprise hardware available (if I remember correctly, a compatible motherboard alone would have been ~€200, and the RAM was about the same) and importing something from outside Europe means you need to pay customs fees, which in my country adds ~30% to the price.
Exactly. In Europe, the UK seems to be the biggest market for used enterprise hardware, so take a look at ebay.co.uk. Usually they will ship to the continent for not too much (~£20), and if you have a VAT number you can get that taken off (20%).
Have you considered connecting to a VM with your laptop? Now that you have the huge thing in your home the latency would be minimal and you can stash it in you garage.
I have it under my desk, it's quiet compared to desktops from a couple of generations ago, but loud compared to modern laptops (i.e. that are usually silent). I like the ability to run dual 4K displays which my laptop can't :)
I just built myself a dual E5-2696v4 workstation last week. ebay/taobao has loads of very affordable E5-2696v4, they are not ES/QS junks but the official version provided to manufacturers. I paid $1,000 for each processor.
Supermicro X10DAI motherboard is just a piece of art, as usual. They sell you this brand new beauty for $350 - it is more like running a charity given the fact that those so called "high end" consumer grade motherboard with one socket and 8 DIMM slots can easily cost you $500 or more.
RAM is pretty expensive now, 128G DDR4-2133P ECC REG RAM cost around $1,000 on taobao.com, unless you buy some shitty brands to save a couple hundred $. Then you need a EEB case, a solid reliable PSU and two heatsinks, that is another $250 to spend.
I can't afford a 3T RAM HP workstation, but the good news is every programmer in fact can afford a 44 cores dual E5-2696v4 workstation like the one I just built. ;)
How's the buying experience for computer hardware on taobao?
I bought everything for a dual Xeon 2670v1 system (starting with Dell T5600 as base) from ebay and it came out to $1000 last year including $150 for 64GB of ECC RAM.
Very happy with it but could definitely use an upgrade now.
Dual E5-2696v4 seems like the current sweet spot for DIY.
> How's the buying experience for computer hardware on taobao?
pretty happy with my experience. vendors posted the stuff on the same day, delivered within 24 hours as I live in Shanghai. it might be different story if you live in other countries as the refund policy says you can return the stuff within 7 days with no questions asked, you probably can't do that within the 7 days time frame if the package need to be posted overseas.
> I bought everything for a dual Xeon 2670v1 system (starting with Dell T5600 as base) from ebay and it came out to $1000 last year including $150 for 64GB of ECC RAM.
I also have a dual E5-2670v1 system, actually I am posting from it now. I found a single E5-2696v4 is going to be 40-50% faster than the dual E5-2670v1, dual 2696v4 almost triples the CPU performance for my workload. this has been confirmed by both cinebench score and benchmark results of an in-house application I developed. RAM bandwidth is not going to be a big jump.
> Dual E5-2696v4 seems like the current sweet spot for DIY.
Dual E5-2696v3 with some firmware/bios hack to push all cores running at higher speed is probably more $ efficient. You can get a faster system that is $500 cheaper. ;)
I've been using Z840. Great developer machine for deep learning and heavy CPU + GPU related stuff. One of few workstations that had enough power to put in two (old) TitanX in its days. Newer one looks even better.
125 comments
[ 1.7 ms ] story [ 306 ms ] threadInstead of just buying a quieter computer (or upgrading it)?
How is it so problematic to have cables running along the molding and around a corner?
In fact, why bother worrying about the noise anyway? Some people function much better with white noise in the background.
It was dead silent. I could hammer all the cores, RAM and disks, and not hear anything from it.
At one point I had 4 of them under my desk, and there was more noise from the MacBook Pro.
Surprised the Radeon Pro SSG isn't an option. It's basically the WX 9100 with 2TB of flash memory slapped on that you can use as VRAM:
https://pro.radeon.com/en/product/pro-series/radeon-pro-ssg/
It requires special application support, you are 100% unlikely to ever discover an app in the wild that can use it.
"ProRender plug-in for Maya has full support for the out-of-core rendering feature found on the Radeon™ Pro SSG which allows the application to tap into the full 2TB of memory found locally on the card. This allows users with very large models to render fully accelerated by the GPU. "
https://www.nvidia.com/en-us/data-center/dgx-station/
Any applications that can would be either run on clusters of servers to really parallelise the work, or is so custom you may as well buy a threadripper and a custom case.
Hell most apps can barely take advantage of multi core CPU.
While you are right that there are very few apps able to take advantage of quad GPUs, for anyone who does serious number crunching it’s not a problem at all to use all of them using popular deep learning frameworks. They aren’t just for deep learning, you can do a lot more with them. And e.g. PyTorch will automatically parallelize certain things across multiple GPUs for you, with near linear speed up.
I wpild be interested to see how pytorch scales GPU wise, relative to CPU clock speed. I am sure there is a point where it will fall off, but not having a 4 GPU system I can't check :)
I have a 40 core CPU machine with a GTX 1080 Ti GPU. I run deep learning models with 90% GPU utilization and those 40 cores are barely used.
I would love to have 3 more GPUs to run in parallel to test different neural network architectures. Sometimes I'll run a CPU script at the same that processes machine learning data that uses all 40 cores.
I would use 4000 CPU cores and 10 GPUs in a machine if I could get them and I don't even do machine learning full time. I'm personally happy to see this trend of more core counts.
Sure you can write code that nominally use all the cores, but I do not think that the performance increase is going to be linair to the core count.
It's not even down to CPU core count - it would be limited by the speed of a single core.
I was hoping transistor become so cheap, 8GB should be the norm and 16GB for mainstream, anyone with serious needs could get 128GB+ or even 1TB.
Instead our memory prices has been trending upwards, slightly improved energy efficiency and still no ECC.
Why? I thought memory were supposed to be commodity.
Edit: I guess I should be clear and say that the simulations themselves are running on a commercial software package (Fortran based) and I'm simply setting them up, spinning them off, and then processing all of the resulting data in Python.
Really curious. I deploy code to a large production server cluster, my friends in academia submit code to large scientific computing clusters, but I don't know of anyone with this much power in their own desktop. I guess I've been in video edit suites with machines much more powerful than the average PC, but not this crazy.
A lot of battle-tested engineering software doesn't do distributed-memory parallelism well. I've personally used MCNP and GEANT4 (particle physics software) on a 48 core, 1 TB RAM workstation. It's interesting browsing the web while the computer is running gigantic calculations in the background on two [physical] CPUs, hooray for the process scheduler doing a good job.
As a remote employee it allows me to most of my development locally, and then use larger environments for a shorter period of time later on.
Combine 3 or 4 of them, and I can have an actual cloud running under my desk, for testing things like kubernetes deployments, with enough capacity for a few concurrent test environments.
As I said above they run basically silent, so I can use them in a shared office space without annoying my neighbors.
I've been hearing of people buying Mac Pros for cloud demos so they can run VMs on them locally because they're among the most compact, compute and memory dense systems you can buy.
I had access to racks of hardware to do a lot of testing but they were in Colorado, while I am in EU which made latency a real problem.
Running inadequate machines waste time of otherwise expensive engineers. The other day I was giving a live demo of an interception proxy and accidentally clicked on a very large HTTP response. The machine I was using only had 32 GB of RAM so I had to open task manager and kill the app so I could re-start it because the meeting would have been over by the time it loaded due to disk caching.
Basically 3D rendering.
Imagine doing web dev in a language where you refresh the webpage to see if it worked vs having to run a long build. The former is better, even though it's not really as good as careful reading of your changes, but there are many times throughout the day when you just want the compiler to bark at you to clear any stupid type or syntax errors. The faster your machine and more parallel the build, the closer you get to that web dev experience.
Having access to machines remotely can replace some of that, but it definitely costs time.
It's funny the things that need a lot of beans to run; I was sitting with one of the GIS guys and he just clicked a button which then caused all 24 cores on his rig to flatline for about 4 minutes. The end result? A map of our city suddenly had a few boxes drawn over the top of it. As it turns out he was pulling in data from half a dozen sources to map out areas where there was government run housing that experienced higher than average levels of emergency services call outs. Apparently, in the past doing that manually would probably have taken several people about a week to do and wouldn't have been as accurate.
I've built plenty of gaming rigs, but have never been interested in this world until recently... and would appreciate any insight :)
[0] http://www.techspot.com/review/1155-affordable-dual-xeon-pc/
[1] http://www.techspot.com/review/1218-affordable-40-thread-xeo...
Is it an issue of "overpowered" fans (for really hot rooms), or is it really just an issue of "cheap as crap" fans by OEMs?
Image processing needs as many cores and RAM as you can give it, and local will beat AWS-esque until we get fiber everywhere.
And those who comment who use them, just so you know I am jealous of you :).
What crazy times we live in. I can't justify buying one of these. I keep tying to come up with a good reason. I suppose YouTube would finally run smoothly.
I am kind of playing /w configurations to see what I can get.
Tounge firmly pressed in cheek..
Last year I picked up a Dell T3600 with a Xeon E5-2670 (V1 - 8C/16T) and 32GB ECC RAM for €400 delivered. It's not completely silent (maybe HP are better in that regard based on comments here?), but it doesn't make much noise - at least compared to what you'd expect from the power it gives.
I now work from home, and having previously primarily used laptops, this thing feels like a beast.
that stuff was $150-200 delivered if you buy from taobao.com.
people also need to realize that dual e5-2670v1 has a cinebench score of 2,000, that is just slightly highly than a single ryzen 1800x.
I checked prices for sourcing my own hardware on the same platform, but it would have been a lot more expensive. The problem here in Europe is there is less second hand enterprise hardware available (if I remember correctly, a compatible motherboard alone would have been ~€200, and the RAM was about the same) and importing something from outside Europe means you need to pay customs fees, which in my country adds ~30% to the price.
https://hardwareisboring.blogspot.com/2016/06/hp-z440.htm
And yes, completely silent. Only hear the GPU (upgraded to 1070gtx) when playing demanding games.
Supermicro X10DAI motherboard is just a piece of art, as usual. They sell you this brand new beauty for $350 - it is more like running a charity given the fact that those so called "high end" consumer grade motherboard with one socket and 8 DIMM slots can easily cost you $500 or more.
RAM is pretty expensive now, 128G DDR4-2133P ECC REG RAM cost around $1,000 on taobao.com, unless you buy some shitty brands to save a couple hundred $. Then you need a EEB case, a solid reliable PSU and two heatsinks, that is another $250 to spend.
I can't afford a 3T RAM HP workstation, but the good news is every programmer in fact can afford a 44 cores dual E5-2696v4 workstation like the one I just built. ;)
I bought everything for a dual Xeon 2670v1 system (starting with Dell T5600 as base) from ebay and it came out to $1000 last year including $150 for 64GB of ECC RAM.
Very happy with it but could definitely use an upgrade now.
Dual E5-2696v4 seems like the current sweet spot for DIY.
pretty happy with my experience. vendors posted the stuff on the same day, delivered within 24 hours as I live in Shanghai. it might be different story if you live in other countries as the refund policy says you can return the stuff within 7 days with no questions asked, you probably can't do that within the 7 days time frame if the package need to be posted overseas.
> I bought everything for a dual Xeon 2670v1 system (starting with Dell T5600 as base) from ebay and it came out to $1000 last year including $150 for 64GB of ECC RAM.
I also have a dual E5-2670v1 system, actually I am posting from it now. I found a single E5-2696v4 is going to be 40-50% faster than the dual E5-2670v1, dual 2696v4 almost triples the CPU performance for my workload. this has been confirmed by both cinebench score and benchmark results of an in-house application I developed. RAM bandwidth is not going to be a big jump.
> Dual E5-2696v4 seems like the current sweet spot for DIY.
Dual E5-2696v3 with some firmware/bios hack to push all cores running at higher speed is probably more $ efficient. You can get a faster system that is $500 cheaper. ;)
I wonder how easy it is to receive Taobao merchandise in Europe. It appears you have to go through an agent.