System Results (15W)

When testing a laptop system, there are various angles to consider on how to test: either user experience benchmarks, that are mostly single threaded and give a good boost to how systems implement a deal of turbo, or sustained benchmarks that test how the system performs when you push it. Intel has gone out of its way to emphasise the former for the next generation of mobile CPUs: they would prefer that reviewers stick to very user experience-like tests, rather than say, rendering programs. The problem there is that outside a number of canned benchmarks, it can be difficult. Users, and especially creators, that typically spend a lot on a premium device, might actually be doing sustained benchmarks.

Given the time that we had to test, we were actually limited in what we could arrange.

Application Loading (GIMP 2.10.4)

3DPM v2.1 (non-AVX)

3DPM v2.1 (AVX2 / AVX-512)

On AVX-512, the Ice Lake part destroys the competition.

Blender 2.79b (cpu-bmw27)

POV-Ray 3.7.1

CineBench R20 ST

CineBench R20 MT

7-zip 1805 Combined

WinRAR 5.60b3

AES Throughput (minus AES instructions)

These last two tests are typically our more memory sensitive tests, and the LPDDR4X-3733 really does win out over the LPDDR3-2133 in the other systems.

Power Results (15W and 25W) Synthetic and Legacy Results (15W)
Comments Locked

261 Comments

View All Comments

  • zodiacfml - Friday, August 2, 2019 - link

    Yes and No. Intel at 10nm should have made AMD nervous but products only at 4 cores, there is nothing or little benefit with 10nm. I reckon, AMD's 7nm mobile parts will mostly start at 6 cores.
  • Kevin G - Thursday, August 1, 2019 - link

    Those 3D particle movement tests seem to be too good to be true. There should be a gigantic jump due to an optimized AVX-512 code path and ICL's enhanced caching structure but it is beyond that in the comparison. I'm not actually suspecting the ICL system given the disclosures in the article (odd that the note about AVX-512 intrinistics for the 3DPM test is mentioned around SPEC compiler settings) but rather the other test systems. Where the Whisky Lake or Kaby Lake systems power or thermal constrained at all? On those Hauwei laptops, were you able to set their fan to a fixed 100% to match that of the ICL system?
  • Ian Cutress - Thursday, August 1, 2019 - link

    The AVX-512 tests were similar when we compared Cannon Lake to Kaby Lake at the same frequency. Against unoptimized SSE code, AVX-512 is killer.
  • Kevin G - Friday, August 2, 2019 - link

    Getting a bit more than double the performance from AVX2 vs. AVX-512 should be possible using some of the new Ice Lake extensions and the obvious doubling of SIMD width. But going from a score of 1802 in Whiskey Lake 25W to 9242 for Ice Lake 25W, over a factor of 5! Ice Lake would have to remove some other bottleneck that the 3DPM test hits really hard (division?).

    Looking back at your previous reviews ( https://www.anandtech.com/show/13400/intel-9th-gen... ), you can see a similar speed up from AVX-512 between the i9 9900K and the i9 7820X but that is explained from Skylake-X having both double the SIMD width and double the number of SIMD execution units. The client version of Ice Lake shouldn't have the same AVX-512 throughput as Sky Lake server.
  • CSMR - Thursday, August 1, 2019 - link

    > the one area where Ice Lake excels in is graphics. Moving from 24 EUs to 64 EUs, plus an increase in memory bandwidth to >50 GB/s, makes for some easy reading.

    I don't understand the comparison here and in this article. If you say a high-end intel processor update excels in graphics, you should compare to previous high-end processors (e.g. i7-8559U with Iris Plus 655). These have 48EUs not 24 and have 128MB EDRAM at 100 GB/s unlike the Ice Lake.

    I am very interested in how the best Ice Lake processors compare to the best previous-gen processors, not how they compare to mediocre previous-gen processors.

    Could the article be updated with some appropriate comparisons?
  • eastcoast_pete - Thursday, August 1, 2019 - link

    Agree on adding the best previous generation graphics to the comparison. Also, while the over 1 TFlops for the 64EU Gen 11 sounds (and is) impressive (within the Intel iGPU world) , didn't the 48EU with Crystal Well get close to that already?
  • Rudde - Thursday, August 1, 2019 - link

    The first apu with 1TFlops performance statement is full of asteriks. First, you have to exclude AMD; second, you have to exclude Intel Iris gpus with eDRAM.
  • Phynaz - Thursday, August 1, 2019 - link

    AMD mobile chips are hot garbage
  • eva02langley - Friday, August 2, 2019 - link

    Your opinion is not a fact... and it is garbage for real.
  • Phynaz - Friday, August 2, 2019 - link

    Hahaha. It’s a fact. It’s why they have 0% market share.

Log in

Don't have an account? Sign up now