SPECworkstation 3

The best place to start for performance is to confirm that this system does get the best SPECworkstation 3 score ever. For users who have never heard of SPECworkstation, it comes from the same people that have the SPEC benchmark that we often use on new processors. The workstation element comes in because this set of benchmarks are designed to test a number of common workstation workloads, such as 3D rendering and animation, molecular modeling and dynamics, medical, oil and gas, construction and architecture, financial services, general operations, and GPU compute. This benchmark combine 30 workloads and ~140 tests into a single package, and results are given as a multiple of a performance compared to a ‘reference’ machine using an Intel Quad-core Skylake processor running a W3100 AMD GPU. This means that this quad-core Intel system gets a value of ‘1’.

SPECworkstation 3 Test Systems
AnandTech CPU GPU DRAM SSD Price
Fujistu Celsius R970 2 x Xeon 8276 RTX 8000 DDR4-2933 PCIe 3.0 $30000+
Armari Magnetar X64T TR3 3990X RTX 6000 DDR4-3200 PCIe 4.0 ~$14200
TR3 3990X 'Stock' TR3 3990X 2080 super DDR4-3200 SATA -
W-3175X 'Stock' Xeon W-3175X 2080 Ti DDR4-2933 SATA -

The current system at the top of the official SPECworkstation 3 standings is a Fujitsu Celsius R970 workstation (D3488-A2). This is the system that Armari has beaten with the X64T. The Fujitsu uses two Intel Xeon Platinum 8276 processors (28-core each, total 56-corepaired with an NVIDIA Quadro RTX 8000 and 384 GB of DDR4-2933. This system, going on list prices for just these components, already comes to $24538. Add in the rest, and some overhead, and this is easily $30000+. By comparison, Armari’s Magnetar X64T workstation is only ~$14200.

The results are as follows. Here we are comparing the Fujitsu official results to Armari’s official results. We also have included our results with the same system (technically classified as ‘estimated results’ because these haven’t been formally submitted to the results database), and a W-3175X system with an RTX 2080 Ti and PCIe 3.0 SSD.

SPECworkstation 3 Results
AnandTech Fujitsu
Celsius
R970*
Armari
Magnetar
X64T*
Our
X64T
Run
3990X
+ 2080
super
3175X
2080 Ti
Media and Entertainment 4.72 7.04 6.84 4.79 3.69
Product Development 6.07 10.85 9.95 3.51 3.35
Life Sciences 5.89 8.24 8.11 - 3.72
Financial Services 8.78 10.55 10.45 9.15 6.59
Energy 5.44 9.09 8.73 4.20 2.86
General Operations 2.27 2.53 2.45 1.55 1.59
GPU Compute 5.40 5.75 5.70 4.63 5.01
 
Geomean 5.17 7.06 6.84 4.08 3.54

*As submitted to SPEC

Within each of these segments, 7-20 sub-tests are performed covering CPU, GPU, and Storage workloads. Our results were a little lower than Armari's, however that can be down to tuning, ambient temperatures, and repeated runs. Our run was within 3%.

Overall, the Magnetar X64T results beat the old Fujitsu results by 37%:

  • CPU: Armari wins by +46%
  • GPU: Armari wins by +12%
  • Storage: Armari wins by +58%

Now, users might wonder how the Armari wins in the GPU tests, given that it has an RTX 6000 compared to the RTX 8000 in the Fujitsu. This is namely down to processor performance – the Fujitsu system processors have a base frequency of 2200 MHz, compared to the Magnetar X64T which can run all processors at 3925 MHz. Even if the Fujitsu was using the CPU in single core mode, and hitting its max turbo of 4000 MHz, the Armari would be using the better IPC of the Zen 2 core against Intel’s Skylake core.

Now each of the above tests are combined scores from sub-tests.

The Intel-based Fujitsu system does have some specific wins in individual tests, such as Maya Storage (+15%), NAMD Storage (+12%) and 7-zip CPU (+75%), however these mostly apply due to the increased memory capacity of the Intel machine.

The AMD-based Armari system has 40 other wins, including Blender CPU (+62%), handbrake CPU (+86%), CFD CPU (+108%), NAMD CPU (+164%), Seismic Data Processing (+230%), LAAMPS storage (+88%), and Creo GPU (+55%).

Full data for the Armari and the Fujitsu systems can be found at these links:

The Armari Magnetar X64T Workstation Rendering Benchmark Performance
Comments Locked

96 Comments

View All Comments

  • Spunjji - Friday, September 11, 2020 - link

    There's nothing more sad than a lack of imagination.
  • Everett F Sargent - Wednesday, September 9, 2020 - link

    "Unfortunately due to how quickly this system was rebuilt for this review, the system I was sent was using DDR4-3200 at CL20, as some of the original memory was accidentally splashed with coolant, and Armari wanted to ensure I wouldn’t have any issues with the system."

    Unfortunately, they could not give one of these systems. In fact, they would have to give me $15K and this system, call it a warranty in reverse. :)
  • PeachNCream - Thursday, September 10, 2020 - link

    That's the sort of trouble you have with using a little company like this as a supplier. They toss together shoddy bits and pieces because they don't retain proper inventory to support builds (and likely cannot afford to do so) and then for press-related reviews, they make absolutely sure there will not be issues with stability. Can we be certain they take the same care with hardware sold to non-journalist buyers or do those customers get the coolant-soaked memory and less stability testing? Who ensures there is adequate quality control in a smaller system builder like this?

    Chasing so-called "world records" in benchmarks in the hopes of increasing productivity by purchasing little-builder-overclocked hardware is asking to shoot your own business operation in the foot when the hardware fails. I would be very reluctant to trust my company's workload on out-of-spec computers cobbled together by a company that can't even be bothered to keep coolant fluids off the memory.
  • Ian Cutress - Thursday, September 10, 2020 - link

    I received this system three or four days ago - I wasn't even in contact with the company a week ago. I suggested a review if a system was ready, and so they scrambled to action. Obviously they weren't going to send me a system that a customer had already ordered, delaying someone with a financial contract, and so they pulled out the system they built for the record and wanted re-test and update so I had the latest components. Best laid plans and all that, combined with a quick turn-around requirement, might lend more readily to non-ideal situations, but given what was done in that time (I was told that included a couple of engineers 7am-11pm the day before), it was actually very well executed.
  • Spunjji - Friday, September 11, 2020 - link

    "...by a company that can't even be bothered to keep coolant fluids off the memory."
    God forbid you ever see what goes on in the large system integrators' build rooms..!

    Accidents happen, it's how they're dealt with that marks a bad supplier from a good one. "Something went wrong and we had to alter the spec" is infinitely better than "Oh well, the fluid's mostly inert, bung the RAM in and hope it works and blame the customer if it goes wrong."
  • Arutius - Friday, September 11, 2020 - link

    I applaud this Company for its honesty and hustle. They are a small organization that cares about what they do. They appreciated Ian being available to them as a small business and are thankful for the exposure. Many readers here work in large organizations and have no appreciation for the real-world stress ( what is the balance of the checkbook today and where will we be in 1 month for cash and sales) on small businesses in this hyper-competitive atmosphere. Try sitting in the chair of the person who personally values each customer, who without they are shortly destined to fail.
  • MrVibrato - Thursday, September 10, 2020 - link

    Yeah, curiously they couldn't replace the "splashed" memory with modules of the same type. There are a small company and i don't expect them to have big inventory. If they don't have stock of these memory modules for at least two or three rigs like these, it tells me this is a cash-strapped operation that probably pays part orders from the advance payments from customers ordering one of their systems. And such vendors are always a major head-ache, because you pay for the system and then you wait and wait and don't get your ordered goods because the vendor struggles to place some order for some component with some supplier, not to mention what could happen if you need to do a RMA or warranty exchange through such a vendor. Mind you, i cannot tell with certainty that Armari is such a company. But this occurence would be a major red flag for me if i were shopping for a boutique workstation (as little sense as that would make, as Peach has explained already; and i would also add uncertainty about the ability to do quick-turnaround on-premises support/service, which larger vendors -while occassionally also being a bitch about- usually don't struggle with in and around large metropolitan areas wherever in the country)
  • MrVibrato - Thursday, September 10, 2020 - link

    Oh well, *There* should be *They*, and

    *it tells me this is a cash-strapped operation*

    should be

    *it tells me this is perhaps a cash-strapped operation*
  • MrVibrato - Thursday, September 10, 2020 - link

    Never mind what i just wrote. I should have checked their website beforehand. Their product range seems to big and too broad to be one of those no-inventory boutique vendors. Mea culpa!
  • Spunjji - Friday, September 11, 2020 - link

    Perhaps check before leaving the big stinky comment full of bold assumptions on the small system integrator's offering?

Log in

Don't have an account? Sign up now