Quick Sync Performance

The 128MB eDRAM has a substantial impact on QuickSync performance. At a much lower TDP/clock speed, the i7-4950HQ is able to pretty much equal the performance of the i7-4770K. Running Haswell's new better quality transcode mode, the 4950HQ is actually 30% faster than the fastest desktop Haswell. This is just one of many reasons that we need Crystalwell on a K-series socketed desktop part.

CyberLink Media Espresso 6.5 - Harry Potter 8 Transcode

CPU Performance

I spent most of the week wrestling with Iris Pro and gaming comparisons, but I did get a chance to run some comparison numbers between the i7-4950HQ CRB and the 15-inch MacBook Pro with Retina Display running Windows 8 in Boot Camp. In this case the 15-inch rMBP was running a 2.6GHz Core i7-3720QM with 3.6GHz max turbo. Other than the base clock (the i7-4950HQ features a 2.4GHz base clock), the two parts are very comparable as they have the same max turbo frequencies. I paid attention to turbo speeds while running all of the benchmarks and for the most part found the two systems were running at the same frequencies, for the same duration.

To put the results in perspective I threw in i7-3770K vs. i7-4770K results. The theory is that whatever gains the 4770K shows over the 3770K should be mirrored in the i7-4950HQ vs. i7-3720QM comparison. Any situations where the 4950HQ exceeds the 4770K's margin of victory over Ivy Bridge are likely due to the large 128MB L4 cache.

Peak Theoretical GPU Performance
  Cinebench 11.5 (ST) Cinebench 11.5 (MT) POV-Ray 3.7RC7 (ST) POV-Ray 3.7RC7 (MT) 7-Zip Benchmark 7-Zip Benchmark (Small) x264 HD - 1st Pass x264 HD - 2nd Pass
Intel Core i7-4770K 1.78 8.07 - 1541.3 23101 - 79.1 16.5
Intel Core i7-3770K 1.66 7.61 - 1363.6 22810 - 74.8 14.6
Haswell Advantage 7.2% 6.0% - 13.0% 1.3% - 5.7% 13.0%
Intel Core i7-4950HQ 1.61 7.38 271.7 1340.9 21022 14360 73.9 14.0
Intel Core i7-3720QM 1.49 6.39 339.1 1178.3 19749 12670 66.2 12.9
Haswell Advantage 8.1% 15.5% 24.8% 13.8% 6.4% 13.3% 11.6% 8.5%
Crystalwell Advantage 0.9% 9.5% - 0.8% 5.1% - 5.9% -4.5%

I didn't have a ton of time to go hunting for performance gains, but a couple of these numbers looked promising. Intel claims that with the right workload, you could see huge double digit gains. After I get back from Computex I plan on poking around a bit more to see if I can find exactly what those workloads might be.

Compute Performance Pricing
POST A COMMENT

177 Comments

View All Comments

  • whyso - Saturday, June 1, 2013 - link

    They are completely different systems making power consumption values irrelevant. Reply
  • codedivine - Saturday, June 1, 2013 - link

    Hi folks. Can you post the OpenCL extensions supported? You can use something like "GPU Caps viewer" from Geeks3d. Reply
  • tipoo - Saturday, June 1, 2013 - link

    Interesting that the compute is punches above it's game performance weight. I wonder if they could put more EUs in a chip, maybe a larger eDRAM, and put it on a board as a compute card. Reply
  • lmcd - Saturday, June 1, 2013 - link

    They already have a compute card called Xeon Phi if I remember correctly. Reply
  • Klimax - Sunday, June 2, 2013 - link

    Different Arch (X86 in Phi) Reply
  • tipoo - Sunday, June 2, 2013 - link

    I'm aware, but the Xeon Phi requires completely different programming than a GPU like this which can just use OpenCL. Reply
  • Soul_Master - Saturday, June 1, 2013 - link

    What's your point for comparing desktop GPU with middle-range mobile GPU? CPU on both devices are not equal. Reply
  • Soul_Master - Saturday, June 1, 2013 - link

    Sorry. I misunderstood about i7 4950HQ process, a high-end quad-core processor for laptops. Reply
  • Ryan Smith - Sunday, June 2, 2013 - link

    It's what we had available. We wanted to test a DDR3 version of GK107, and that's what was on-hand. Reply
  • tipoo - Saturday, June 1, 2013 - link

    Hmm, so it's heavily hinted at that the next rMBP will ditch discreet graphics. The 5200 is good, but that would still be a regression in performance. Not the first time Apple would have done that, there was the Radeon cut out of the Mini, the 320M to the 3000, even the bottom rung of the newest iMac with the 640m. I wonder if it would at least be cheaper to make up for it. Reply

Log in

Don't have an account? Sign up now