Benchmarking Performance: CPU Legacy Tests

Our legacy tests represent benchmarks that were once at the height of their time. Some of these are industry standard synthetics, and we have data going back over 10 years. All of the data here has been rerun on Windows 10, and we plan to go back several generations of components to see how performance has evolved.

Legacy: CineBench 11.5 MultiThreadedLegacy: CineBench 11.5 Single ThreadedLegacy: 3DPM v1 MultiThreadedLegacy: 3DPM v1 Single ThreadedLegacy: CineBench 10 MultiThreadedLegacy: CineBench 10 Single ThreadedLegacy: x264 3.0 Pass 1Legacy: x264 3.0 Pass 2

Benchmarking Performance: CPU Office Tests Comparing Skylake-S and Skylake-X/SP Performance Clock-for-Clock
Comments Locked

264 Comments

View All Comments

  • Tuna-Fish - Tuesday, June 20, 2017 - link

    Just a tiny nitpick about the cache hierarchy table:

    TLBs are grouped with cache levels, that is, L1TLBs are with the L1 caches and the L2 TLB is with the L2 cache, as if the level of TLB is associated with the level of cache. This is not how they work -- any request only has to have it's address translated once, when it's loaded from the L1 cache. If there is a miss when accessing the L1 TLB, the L2 TLB is accessed before the L1 cache is.
  • PeterCordes - Monday, July 3, 2017 - link

    This common mistake bugs me too! The transistors for the TLB's 2nd level are probably not even near the L2 cache. (And the L2 cache is physically indexed / physically tagged, so it doesn't care about translations or virtual addresses at all). The multi-level TLB is a separate hierarchy from the normal caches.

    I also commented earlier to point out several other errors in [the uarch details](http://www.anandtech.com/comments/11550/the-intel-... e.g. mixing up the register-file sizes with the scheduler size.
  • yeeeeman - Tuesday, June 20, 2017 - link

    What this review shows just how good of a deal AMD Ryzen CPUs are. I mean, R7 1700 is like 300$ and it keeps up in many of the tests with the big boys from Intel.
  • Carmen00 - Tuesday, June 20, 2017 - link

    Small typo on the first page, Ian: "For $60 less than the price of the Core i7-7800X...". But the comparison shows $389 vs $299, which is a $90 difference. Otherwise a fantastic, in-depth review, thank you very much!
  • Ian Cutress - Tuesday, June 20, 2017 - link

    Official MSRPs haven't changed. What distributors do with their stock is a different story.
  • Carmen00 - Wednesday, June 21, 2017 - link

    I'm talking about the MSRPs. There's a table ("Comparison: Core i7-7800X vs. Ryzen 7 1700") on Page 1 with the MSRPs as $299 and $389, a $90 difference. The text just above this table says that there's a $60 difference, but 389-299=90, not 60. So either the text is incorrect, or the MSRPs in the table are incorrect.
  • Tephereth - Tuesday, June 20, 2017 - link

    Missing temps and in-game benchmarks... u're the only one in the whole web that has an 7800x to test, so please post those :(
  • Gothmoth - Tuesday, June 20, 2017 - link

    after reading a dozend reviews i say:

    great now we have the choice between two buggy platforms.... well done.
    i am not going to be a bios betatester for AMD or Intel.

    these two release are the worst in many years i would say.

    i hope AMD has threadripper ironed out.
  • AntDX316 - Tuesday, June 20, 2017 - link

    The new processors are in totally another level/league/class. It dominates in everything and more except a couple benches.
  • AnandTechReader2017 - Tuesday, June 20, 2017 - link

    Of course they are, Ryzen is mainstream, Thread Ripper is the competitor.
    Thread Ripper will be quite interesting, the scaling of the "infinity fabric" will come to the fore and show if AMD's new architecture is a worthy competitor.

Log in

Don't have an account? Sign up now