Benchmarking Performance: SPECwpc v2.1

Anyone can run wPrime (why would you?) or Geekbench, but more often than not these pre-built synthetic tests are not representative of any user’s workload. This applies even more to professional environments or prosumer workloads, where time is money: if someone interested in hardware cannot pinpoint exactly how the new hardware is going to benefit them, that is $20 of billable time down the drain.

One of the difficulties of a benchmark reviewer is finding relevant benchmarks for the audience at hand. I’ve discussed what AnandTech is and our audience to several high profile software vendors who are in the business of supplying professional grade, critical programs that top technology companies use to produce the next $700 smartphone. These engineers are our readers, and it only seems best that we benchmark something that can assist them in accelerating our workflow. Unfortunately, the almost blanket response from these ISVs is negative, even if the request is for a limited software license in exchange for repeated discussion of the software on AnandTech (and third party benchmark data to assist their customers in hardware purchasing). My last discussions with two major ISVs led to a ‘interesting but we don’t see the value’ response and a ‘we’re doing our own in-house thing’ response respectively. No-one wants to know. Unless you work at one of these companies and want to get in touch.

The fall-back position in this case is to call on SPEC for their Workstation benchmark series. SPECwpc has existed in one form or another for several years, using pre-compiled binaries for a mix of medical, oil-and-gas, engineering, visualization and system level benchmarks. There are over 30 benchmarks, some running multiple copies to keep all the cores busy, and repeated runs offer very good consistency. A full run can take over six hours, making a sizeable increase to even our CPU workflow.

We’re reporting almost all of the subset scores in our benchmarking. Some tests require a GPU, and so we maintain the same RX 460 graphics card on each processor we test, along with the same screen resolution and driver. Ideally we would use professional graphics cards, like AMD’s FirePro range or NVIDIA’s Quadro range, however we currently use four identical RX 460 cards to keep the benchmarks on our test beds continually flowing, and sourcing four of the same pro card on long-term loan is actually fairly difficult.

Because SPECwpc takes so long and is fairly new, we only have results for a few processors so far. This should expand as we continue using this test. We’re likely to limit this test to HEDT processors and above, along with one or two mainstream processors (i7-K, Ryzen 7). For this review, out of the two Intel processors in the title, we only had time to run it on the Core i9-7980XE.

SpecWPC v2.1 - Part 1, Media-2: HandBrake

SpecWPC v2.1 - Part 1, Media-3: LuxRender

SpecWPC v2.1 - Part 1, Media-4: Maya

SpecWPC v2.1 - Part 2, Development-1: Rodinia

SpecWPC v2.1 - Part 2, Development-2: CalculiX

SpecWPC v2.1 - Part 2, Development-3: WPCcfd

SpecWPC v2.1 - Part 2, Development-4: Catia

SpecWPC v2.1 - Part 2, Development-5: Creo

SpecWPC v2.1 - Part 2, Development-6: Showcase

SpecWPC v2.1 - Part 2, Development-7: SNX

SpecWPC v2.1 - Part 2, Development-8: SW

SpecWPC v2.1 - Part 3, Life Sciences-1: Lammps

SpecWPC v2.1 - Part 3, Life Sciences-2: namd

SpecWPC v2.1 - Part 3, Life Sciences-3: Medical

SpecWPC v2.1 - Part 4, Financial-1: Monte Carlo

SpecWPC v2.1 - Part 4, Financial-2: Black Scholes

SpecWPC v2.1 - Part 4, Financial-3: Binomial

SpecWPC v2.1 - Part 5, Energy-1: FFTW

SpecWPC v2.1 - Part 5, Energy-2: Convolution

SpecWPC v2.1 - Part 5, Energy-3: Energy-03

SpecWPC v2.1 - Part 5, Energy-4: srmp

SpecWPC v2.1 - Part 5, Energy-5: Kirchhoff Migration

SpecWPC v2.1 - Part 5, Energy-6: Poisson

SpecWPC v2.1 - Part 6, General-1: 7-Zip

SpecWPC v2.1 - Part 6, General-2: Python

SpecWPC v2.1 - Part 6, General-3: Octave

Benchmark Overview Benchmarking Performance: PCMark 10
Comments Locked

152 Comments

View All Comments

  • ddriver - Monday, September 25, 2017 - link

    You are living in a world of mainstream TV functional BS.

    Quantum computing will never replace computers as we know and use them. QC is very good at a very few tasks, which classical computers are notoriously bad at. The same goes vice versa - QC suck for regular computing tasks.

    Which is OK, because we already have enough single thread performance. And all the truly demanding tasks that require more performance due to their time staking nature scale very well, often perfectly, with the addition of cores, or even nodes in a cluster mode.

    There might be some wiggle room in terms of process and material, but I am not overly optimistic seeing how we are already hitting the limits on silicon and there is no actual progress made on superior alternatives. Are they like gonna wait until they hit the wall to make something happen?

    At any rate, in 30 years, we'd be far more concerned with surviving war, drought and starvation than with computing. A problem that "solves itself" ;)
  • SharpEars - Monday, September 25, 2017 - link

    You are absolutely correct regarding quantum computing and it is photonic computing that we should be looking towards.
  • Notmyusualid - Monday, September 25, 2017 - link

    @ SharpEars

    Yes, as alluded to by IEEE. But I've not looked at it in a couple of years or so, and I think they were still struggling with an optical DRAM of sorts.
  • Gothmoth - Monday, September 25, 2017 - link

    and what have they done for the past 6 years?

    i am glad that i get more cores instead of 5-10% performance per generation.
  • Krysto - Monday, September 25, 2017 - link

    The would if they could. Improvements in IPC have been negligible since Ivy Bridge.
  • kuruk - Monday, September 25, 2017 - link

    Can you add Monero(Cryptonight) performance? Since Cryptonight requires at least 2MB of L3 cache per core for best performance, it would be nice to see how these compare to Threadripper.
  • evilpaul666 - Monday, September 25, 2017 - link

    I'd really like it if Enthusiast ECC RAM was a thing.

    I used to always run ECC on Athlons back in the Pentium III/4 days.Now with 32-128x more memory that's running 30x faster it doesn't seem like it would be a bad thing to have...
  • someonesomewherelse - Saturday, October 14, 2017 - link

    It is. Buy AMD.
  • IGTrading - Monday, September 25, 2017 - link

    I think we're being to kind on Intel.

    Despite the article clearly mentioning it in a proper and professional way, the calm tone of the conclusion seem to legitimize and make it acceptable that Intel basically deceives its customers and ships a CPU that consumes almost 16% more power than its stated TDP.

    THIS IS UNACCEPTABLE and UNPROFESSIONAL from Intel.

    I'm not "shouting" this :) , but I'm trying to underline this fact by putting it in caps.

    People could burn their systems if they design workstations and use cooling solutions for 165W TDP.

    If AMD would have done anything remotely similar, we would have seen titles like "AMD's CPU can fry eggs / system killer / motherboard breaker" and so on ...

    On the other hand, when Intel does this, it is silently, calmly and professionally deemed acceptable.

    It is my view that such a thing is not acceptable and these products should be banned from the market UNTIL Intel corrects its documentation or the power consumption.

    The i7960X fits perfectly in its TDP of 165W, how come i7980X is allowed to run wild and consume 16% more ?!

    This is similar with the way people accepted every crapping design and driver fail from nVIDIA, even DEAD GPUs while complaining about AMD's "bad drivers" that never destroyed a video card like nVIDIA did. See link : https://www.youtube.com/watch?v=dE-YM_3YBm0

    This is not cutting Intel "some slack" this is accepting shit, lies and mockery and paing 2000 USD for it.

    For 2000$ I expect the CPU to run like a Bentley for life, not like modded Mustang which will blow up if you expect it to work as reliably as a stock model.
  • whatevs - Monday, September 25, 2017 - link

    What a load of ignorance. Intel tdp is *average* power at *base* clocks, uses more power at all core turbo clocks here. Disable turbo if that's too much power for you.

Log in

Don't have an account? Sign up now