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.

All of our benchmark results can also be found in our benchmark engine, Bench.

3D Particle Movement v1

3DPM is a self-penned benchmark, taking basic 3D movement algorithms used in Brownian Motion simulations and testing them for speed. High floating point performance, MHz and IPC wins in the single thread version, whereas the multithread version has to handle the threads and loves more cores. This is the original version, written in the style of a typical non-computer science student coding up an algorithm for their theoretical problem, and comes without any non-obvious optimizations not already performed by the compiler, such as false sharing.

Legacy: 3DPM v1 MultiThreadedLegacy: 3DPM v1 Single Threaded

CineBench 11.5 and 10

Cinebench is a widely known benchmarking tool for measuring performance relative to MAXON's animation software Cinema 4D. Cinebench has been optimized over a decade and focuses on purely CPU horsepower, meaning if there is a discrepancy in pure throughput characteristics, Cinebench is likely to show that discrepancy. Arguably other software doesn't make use of all the tools available, so the real world relevance might purely be academic, but given our large database of data for Cinebench it seems difficult to ignore a small five minute test. We run the modern version 15 in this test, as well as the older 11.5 and 10 due to our back data.

Legacy: CineBench 11.5 MultiThreaded

Legacy: CineBench 11.5 Single Threaded

Legacy: CineBench 10 MultiThreaded

Legacy: CineBench 10 Single Threaded

x264 HD 3.0

Similarly, the x264 HD 3.0 package we use here is also kept for historic regressional data. The latest version is 5.0.1, and encodes a 1080p video clip into a high-quality x264 file. Version 3.0 only performs the same test on a 720p file, and in most circumstances the software performance hits its limit on high-end processors, but still works well for mainstream and low-end. Also, this version only takes a few minutes, whereas the latest can take over 90 minutes to run.

Legacy: x264 3.0 Pass 1

Legacy: x264 3.0 Pass 2

The 1950X: the first CPU to score higher on the 2nd pass of this test than it does on the first pass.

Benchmarking Performance: CPU Office Tests CPU Gaming Performance: Civilization 6 (1080p, 4K, 8K, 16K)
Comments Locked

347 Comments

View All Comments

  • sorten - Friday, August 11, 2017 - link

    Swole? Threadripped?
  • Rottie - Friday, August 11, 2017 - link

    AMD Ryzen CPU is not fast enough. Apple is not ready for AMD Ryzen CPU, sorry AMD. I love AMD but I hated Intel even though I have a Skylake based MacBook Pro. :(
  • Deshi! - Friday, August 11, 2017 - link

    One small correction, Ryzen has 24 PCIE lanes, not 16. it has 16 for graphics only, but saying only 16 may make people (like me) wonder if you can't run an NVME at x4 and still have the graphics card at 16x, which you totally can do.
  • Deshi! - Friday, August 11, 2017 - link

    This is under Feeding the beast section btw, where you said "Whereas Ryzen 7 only had 16 PCIe lanes, competing in part against CPUs from Intel that had 28/44 PCIe lanes,"
  • fanofanand - Tuesday, August 15, 2017 - link

    He already answered this question/statement to someone else. there are 20 lanes from the CPU, 16 of which are available for graphics. I don't think his way of viewing it seems accurate, but he has stated that this is how PCIe lanes have been counted "for decades"
  • WaltC - Friday, August 11, 2017 - link

    Nice review, btw! Yes, going all the way back to Athlon and the triumph of DDR-Sdram over Rdram, and the triumph of AMD's x86-64 over Itanium (Itanium having been Intel's only "answer" for 64-bit desktop computing post the A64 launch--other than to have actually paid for and *run* an Intel ad campaign stating "You don't need 64-bits on the desktop", believe it or not), and going all the way back to Intel's initial Core 2 designs, the products that *actually licensed x86-64 from AMD* (so that Intel could compete in the 64-bit desktop space it claimed didn't exist), it's really remarkable how much AMD has done to enervate and energize the x86 computing marketplace globally. Interestingly enough it's been AMD, not Intel, that has charted the course for desktop computing globally--and it goes all the way back to the original AMD Athlon. The original Pentium designs--I owned 90MHz and 100MHz Pentiums before I moved to AMD in 1999--were the high-point of an architecture that Intel would *cancel* shortly thereafter simply because it could not compete with the Athlon and its spin-off architectures like the A64. That which is called "Pentium" today is not...;) Intel simply has continued to use the brand. All I can say is: TGF AMD...;) I've tried to imagine where Intel would have taken the desktop computing market had consumers allowed the company to lead them around by the nose, and I can't...;) If not for AMD *right now* and all the activity the company is bringing to the PC space once again, there would not be much of a PC market globally going on. But now that we have some *action* again and Intel is breaking its legs trying to keep up, the PC market is poised to break out of the doldrums! I guess Intel had decided to simply nap for a few decades--"Wake me when some other company does something we'll have to compete with!" Ugh.
  • zeroidea - Friday, August 11, 2017 - link

    Hi Ian,
    On the Civ 6 benchmark page, all results after the GTX 1080 are mislabeled as GTA 6.
  • Ahmad Rady - Friday, August 11, 2017 - link

    Can you try to test this CPU using windows server?
    This is a MCM CPU looks like 4 CPUs attached to each other.
    I think windows 10 Pro can't get the most of this CPU unless we have windows 10 Pro for WS
  • Pekish79 - Friday, August 11, 2017 - link

    Vray has a Rendering Benchmark too maybe you could use both
  • Pekish79 - Friday, August 11, 2017 - link

    I went to check both page of Vray and Corona Benchmark

    Corona match more or less the graphic and Vray has the following

    AMD 1950 : 00:46-00:48 sec
    I9 7900: 00:54-00:56 sec
    I7 6950: 01:00-01:10 sec
    I5 5960: 01:23-01:33 sec

Log in

Don't have an account? Sign up now