** = Old results marked were performed with the original BIOS & boost behaviour as published on 7/7.

Benchmarking Performance: CPU Legacy Tests

3DPM v1: Naïve Code Variant of 3DPM v2.1

The first legacy test in the suite is the first version of our 3DPM benchmark. This is the ultimate naïve version of the code, as if it was written by scientist with no knowledge of how computer hardware, compilers, or optimization works (which in fact, it was at the start). This represents a large body of scientific simulation out in the wild, where getting the answer is more important than it being fast (getting a result in 4 days is acceptable if it’s correct, rather than sending someone away for a year to learn to code and getting the result in 5 minutes).

In this version, the only real optimization was in the compiler flags (-O2, -fp:fast), compiling it in release mode, and enabling OpenMP in the main compute loops. The loops were not configured for function size, and one of the key slowdowns is false sharing in the cache. It also has long dependency chains based on the random number generation, which leads to relatively poor performance on specific compute microarchitectures.

3DPM v1 can be downloaded with our 3DPM v2 code here: 3DPMv2.1.rar (13.0 MB)

3DPM v1 Single Threaded3DPM v1 Multi-Threaded

x264 HD 3.0: Older Transcode Test

This transcoding test is super old, and was used by Anand back in the day of Pentium 4 and Athlon II processors. Here a standardized 720p video is transcoded with a two-pass conversion, with the benchmark showing the frames-per-second of each pass. This benchmark is single-threaded, and between some micro-architectures we seem to actually hit an instructions-per-clock wall.

x264 HD 3.0 Pass 1x264 HD 3.0 Pass 2

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 due to our back data.

Legacy: CineBench 11.5 MultiThreadedLegacy: CineBench 11.5 Single Threaded

Benchmarking Performance: CPU Office Tests Gaming: World of Tanks enCore
Comments Locked

447 Comments

View All Comments

  • beginning - Thursday, July 11, 2019 - link

    I noticed that at the E3 2019 tech day, AMD recommended DDR4-3600 CL16 RAM. I see that 3200 MHz RAM has been used in the AMD testbench. I read the description about avoiding overclocking but 3600 MHz RAMs come with a factory clock of 3600 MHz, right? I know I am missing something. What am I missing?
  • sknaumov - Thursday, July 11, 2019 - link

    Do you plan to make some tests of these CPUs on older, cheaper and colder motherboards? It would be very interesting to see results of b450 chipset and whether it is possible to use DDR4-3600MHz with tight timings on these older boards. Or at least provide more info about what has more priority for memory speed and timings on AMD platform - CPU or chipset.
  • viperswhip - Thursday, July 11, 2019 - link

    I am going to wait to build a PC for a bit, however, I am super excited by this launch and disappointed by the video card launch. I expect to have an AMD chip since Intel has no answer for this, and we shall see on the video cards, but if I was building today I'd probably get a 2070 RTX super.
  • PProchnow - Friday, July 12, 2019 - link

    Here's is Jus' a good ol' boy trying out. No OC off stock Multi but 3333Mhz RAM
    #1
    https://browser.geekbench.com/v4/cpu/13863634

    Rather a new rig and it is X470 up to the A.A BIOS and it is MSI Gaming Plus.
    OK link #2 is here and I stroked the DDR$ up top 3333Mhz. I also stroked the fan
    to stay sub 70C. Wild OCs will take water at least "in The Home" versus LiqN2 Lab.

    https://browser.geekbench.com/v4/cpu/13865361

    BTW where is the Bragging Thread? My MOBO is the MSI X470 Gaming Plus BIOS A.A makes Ryzen 9 go BTW.
    I have yet to up the MULTI in case you want to know. I wonder what good Ocers will get with the right stuff.

    Single-Core Performance
    Memory Score 6431
    Floating Point Score 5409
    Integer Score 5190
    Crypto Score 6888
    Single-Core Score 5589

    You underst and that RAM set at 1672 is 1/2 the common referred to speed. 3344Mhz is the common nomenclature.

    ***Single-Core Score ***Multi-Core Score
    5589 47755
    Geekbench 4.3.4 Tryout for Windows x86 (64-bit)
    Result Information
    Upload Date July 12 2019 08:16 PM
    Views 2
    System Information
    System Information
    Operating System Microsoft Windows 10 Pro (64-bit)
    Model Micro-Star International Co., Ltd. MS-7B79
    Motherboard Micro-Star International Co., Ltd. X470 GAMING PLUS (MS-7B79)
    Memory 32768 MB DDR4 SDRAM 1672MHz
    Northbridge AMD Ryzen SOC 00
    Southbridge AMD X470 51
    BIOS American Megatrends Inc. A.A0
    Processor Information
    Name AMD Ryzen 9 3900X
    Topology 1 Processor, 12 Cores, 24 Threads
    Identifier AuthenticAMD Family 23 Model 113 Stepping 0
    Base Frequency 3.80 GHz
    Maximum Frequency 4.53 GHz
  • Maxiking - Tuesday, July 23, 2019 - link

    Why would anyone brag about something if

    You can't reach 5.0ghz +
    You can't reach even the boost frequency on a single core
    You can't beat consistently competitor's older 14nm cpu architecture which has been on the market since 2016...
    You can't beat RAM OC'ing records either because over 3733mhz IF gets actually downlocked and due tu that, "faster" ram performs worse unless you OC 7400mhz, which is not possible even with liquid nitrogen.
  • PProchnow - Friday, July 12, 2019 - link

    These are my scores with my Ryzen 9 3900X.
    #1
    https://browser.geekbench.com/v4/cpu/13863634

    Rather a new rig and it is X470 up to the A.A BIOS and it is MSI Gaming Plus.
    OK link #2 is here and I stroked the DDR$ up top 3333Mhz. I also stroked the fan
    to stay sub 70C. Wild OCs will take water at least "in The Home" versus LiqN2 Lab.

    https://browser.geekbench.com/v4/cpu/13865361

    BTW where is the Bragging Thread? My MOBO is the MSI X470 Gaming Plus BIOS A.A makes Ryzen 9 go BTW.
    I have yet to up the MULTI in case you want to know. I wonder what good Ocers will get with the right stuff.

    Single-Core Performance
    Memory Score 6431
    Floating Point Score 5409
    Integer Score 5190
    Crypto Score 6888
    Single-Core Score 5589

    You underst and that RAM set at 1672 is 1/2 the common referred to speed. 3344Mhz is the common nomenclature.

    ***Single-Core Score ***Multi-Core Score
    5589 47755
    Geekbench 4.3.4 Tryout for Windows x86 (64-bit)
    Result Information
    Upload Date July 12 2019 08:16 PM
    Views 2
    System Information
    System Information
    Operating System Microsoft Windows 10 Pro (64-bit)
    Model Micro-Star International Co., Ltd. MS-7B79
    Motherboard Micro-Star International Co., Ltd. X470 GAMING PLUS (MS-7B79)
    Memory 32768 MB DDR4 SDRAM 1672MHz
    Northbridge AMD Ryzen SOC 00
    Southbridge AMD X470 51
    BIOS American Megatrends Inc. A.A0
    Processor Information
    Name AMD Ryzen 9 3900X
    Topology 1 Processor, 12 Cores, 24 Threads
    Identifier AuthenticAMD Family 23 Model 113 Stepping 0
    Base Frequency 3.80 GHz
    Maximum Frequency 4.53 GHz

    Now you can cross ref with others.
  • Meteor2 - Monday, July 15, 2019 - link

    Nice!
  • willis936 - Wednesday, July 17, 2019 - link

    The editor's choice awards are a bit strange to me. Zen 1 didn't receive one even though it was the largest CPU performance increase from a company this century. The i7-4950HQ received an editor's choice silver award even though it had little importance to the industry. And the 3700X, which offers comparable SP performance to competing intel products at a huge discount and smaller power budget gets the same editor's choice level as the i7-4950HQ?
  • willis936 - Wednesday, July 17, 2019 - link

    I know it was a different editor at the time, but the selective excitement is a bit of a bummer. eDRAM was exciting to see at the time and then nothing ever came of it. The enthusiasm of chiplets under the new editor comes through much less. That too is fine. However if the rating system is what it is then I don't think it's much to argue that chiplets are much more disruptive than eDRAM and is already making much larger waves.
  • Maxiking - Monday, July 22, 2019 - link

    AMD fraund getting finally the attention it deserves

    https://www.youtube.com/watch?v=x03FyPQ3a3E

    check at 05m25s

Log in

Don't have an account? Sign up now