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
Comments Locked

177 Comments

View All Comments

  • boe - Monday, June 3, 2013 - link

    As soon as intel CPUs have video performance that exceeds NVidia and AMD flagship video cards I'll get excited. Until then I think of them as something to be disabled on workstations and to be tolerated on laptops that don't have better GPUs on board.
  • MySchizoBuddy - Monday, June 3, 2013 - link

    So Intel just took the OpenCL crown. Never thought this day would come.
  • prophet001 - Monday, June 3, 2013 - link

    I have no idea whether or not any of this article is factually accurate.

    However, the first page was a treat to read. Very well written.

    :)
  • Teemo2013 - Monday, June 3, 2013 - link

    Great success by Intel.
    4600 is near GT630 and HD4650 (much better than 6450 which sells for $15 at newegg)
    5200 is better than GT640 and HD 6670 (currently sells like $50 at newegg)
    Intel's intergrated used to be worthless comparing with discret cards. It slowly catches up during the past 3 years, and now 5200 is beating a $50 card. Can't wait for next year!
    Hopefully this will finally push AMD and Nvidia to come up with meaningful upgrade to their low level product lines.
  • Cloakstar - Monday, June 3, 2013 - link

    A quick check for my own sanity:
    Did you configure the A10-5800K with 4 sticks of RAM in bank+channel interleave mode, or did you leave it memory bandwidth starved with 2 sticks or locked in bank interleave mode?

    The numbers look about right for 2 sticks, and if that is the case, it would leave Trinity at about 60% of its actual graphics performance.

    I find it hard to believe that the 5800K is about a quarter the performace per watt of the 4950HQ in graphics, even with the massive, server-crushing cache.
  • andrerocha - Monday, June 3, 2013 - link

    is this new cpu faster than the 4770k? it sure cost more?
  • zodiacfml - Monday, June 3, 2013 - link

    impressive but one has to take advantage of the compute/quick sync performance to justify the increase in price over the HD 4600
  • ickibar1234 - Tuesday, June 4, 2013 - link

    Well, my Asus G50VT laptop is officially obsolete! A Nvidia 512MB GDDR3 9800gs is completely pwned by this integrated GPU, and, the CPU is about 50-65% faster clock for clock to the last generation Core 2 Duo Penryn chips. Sure, my X9100 can overclock stably to 3.5GHZ but this one can get close even if all cores are fully taxed.

    Can't wait to see what the Broadwell die shrink brings, maybe a 6-core with Iris or a higher clocked 4-core?

    I too see that dual core versions of mobile Haswell with this integrated GPU would be beneficial. Could go into small 4.5 pounds laptops.

    AMD.....WTH are you going to do.
  • zodiacfml - Tuesday, June 4, 2013 - link

    AMD has to create a Crystalwell of their own. I never thought Intel could beat them to it since their integrated GPUs always has needed bandwidth ever since.
  • Spunjji - Tuesday, June 4, 2013 - link

    They also need to find a way past their manufacturing process disadvantage, which may not be possible at all. We're comparing 22nm Apples to 32/28nm Pears here; it's a relevant comparison because those are the realities of the marketplace, but it's worth bearing in mind when comparing architecture efficiencies.

Log in

Don't have an account? Sign up now