CPU Benchmark Performance: DDR5 vs DDR4

Traditionally we test our memory settings at JEDEC specifications. JEDEC is the standards body that determines the requirements for each memory standard. In this case, the Core i9 supports the following aligning with those standards:

  • DDR4-3200 CL22
  • DDR5-4800B CL40*

There's an * next to the DDR5 for a couple of reasons. First, when asked, Intel stated that 4800A (CL34) was the official support, however since the technical documents have now been released, we've discovered that it is 4800B (CL40). Secondly, 4800B CL40 technically only applies to 1 module per 64-bit channel on the motherboard, and only when the motherboard has two 64-bit slots to begin with. We covered Intel's memory support variants in a previous article, and in this instance, we're using DDR5-4800B memory in our testing.

(1-1) Agisoft Photoscan 1.3, Complex Test(1-2) AppTimer: GIMP 2.10.18(2-1) 3D Particle Movement v2.1 (non-AVX)(2-2) 3D Particle Movement v2.1 (Peak AVX)(2-3) yCruncher 0.78.9506 ST (250m Pi)(2-4) yCruncher 0.78.9506 MT (2.5b Pi)(2-4b) yCruncher 0.78.9506 MT (250m Pi)(2-5) NAMD ApoA1 Simulation(2-6) AI Benchmark 0.1.2 Total(3-1) DigiCortex 1.35 (32k Neuron, 1.8B Synapse)(3-2b) Dwarf Fortress 0.44.12 World Gen 129x129, 550 Yr(3-3) Dolphin 5.0 Render Test(3-4c) Factorio v1.1.26 Test, 20K Hybrid(4-3a) Crysis CPU Render at 320x200 Low(4-5) V-Ray Renderer(4-7a) CineBench R23 Single Thread(4-7b) CineBench R23 Multi-Thread(5-1a) Handbrake 1.3.2, 1080p30 H264 to 480p Discord(5-1b) Handbrake 1.3.2, 1080p30 H264 to 720p YouTube(5-1c) Handbrake 1.3.2, 1080p30 H264 to 4K60 HEVC(5-2c) 7-Zip 1900 Combined Score(5-3) AES Encoding(5-4) WinRAR 5.90 Test, 3477 files, 1.96 GB(7-1) Kraken 1.1 Web Test(7-2) Google Octane 2.0 Web Test(7-3) Speedometer 2.0 Web Test(8-1c) Geekbench 5 Single Thread(8-1d) Geekbench 5 Multi-Thread(8-2a) AIDA DRAM Read Speed(8-2b) AIDA DRAM Write Speed(8-2c) AIDA DRAM Copy Speed

As explained in our SPEC section, DDR5 memory not only brings bandwidth improvements but also the increased number of channels (4x32-bit vs 2x64-bit) means that the memory can be better utilized as threads pile on the memory requests. So while we don't see much improvement in single threaded workloads, there are a number of multi-threaded workloads that would love the increased performance.

CPU Benchmark Performance: Windows 11 vs Windows 10 Gaming Performance: DDR5 vs DDR4
Comments Locked

474 Comments

View All Comments

  • michael2k - Thursday, November 4, 2021 - link

    Clock/power scales linearly.
    It's only Voltage/power that scales geometrically

    If you have to increase voltage to increase clock then you can say clock/power is geometric.

    So if at a fixed voltage you can go from 2GHz -> 2.5GHz the power usage only goes up by 25%

    If you also bump voltage up, however, from 1.2V -> 1.4V, power usage might go up 36%, so that combined you would see a 61% increase in power usage to hit 2.5GHz.
  • Great_Scott - Thursday, November 4, 2021 - link

    Race to Sleep - still a good idea for desktop usage patterns.
  • factual - Thursday, November 4, 2021 - link

    Alder is actually more efficient than 5950X in most real world scenarios. PC World did a proper real world power consumption comparison and Alder Lake was superior in most cases. Unless AMD cuts prices dramatically, in makes zero sense to buy Ryzen at this moment ... unless you are a mindless fanboi that is!!
  • meacupla - Thursday, November 4, 2021 - link

    I am waiting for AMD to cut prices on their 5600X or 5800X, so I can upgrade from my 2700X.
  • eddman - Thursday, November 4, 2021 - link

    Exactly. I'm looking for the same with my 2600.
  • Spunjji - Friday, November 5, 2021 - link

    "Unless AMD cuts prices dramatically, in makes zero sense to buy Ryzen at this moment ... unless you are a mindless fanboi that is!!"
    Or if, you know, you pay attention to how much a whole system costs and make a decision based on that instead of assuming cheap CPU = cheap system?
  • madseven7 - Saturday, November 6, 2021 - link

    Mindless??!! Why?? Cause I can buy a Ryzen 5000 cpu to drop into my current motherboard to replace my Zen+ cpu (2700x). Mindless cause I refuse to pay $750 for 12900k, $450+ for Asus mb not even the best middle of the road, $330 for 32gb of ddr5 and this doesn't even include the aio360 cooler needed. You do the math.
  • Wrs - Saturday, November 6, 2021 - link

    What puzzles me is why you haven't already dropped a Zen 3 in that. Zen 3 is basically end of the line for that board. I do not know if "Zen 3+" with vertical cache will even come out, much less be available and affordable for someone who shuns ddr5 costs.
  • AlyxSharkBite - Thursday, November 4, 2021 - link

    My argument would be anyone looking at performance per watt on a CPU like this is a bit crazy. I've never considered that important for a CPU you're going to run well out of spec with big cooling anyway.

    I'm far more interested in perf per watt on the mobile version. That's where it's going to matter as you can't just throw more cooling at a laptop. Especially compared to the Ryzen chips that have extremely good perf per watt.
  • EnglishMike - Thursday, November 4, 2021 - link

    I don't think you have to be crazy, you just have to be one of those few for whom it matters -- i.e. those who execute long-running high-CPU load workloads on a regular basis.

    Otherwise, yeah, it's mostly irrelevant, given the performance per watt of more typical workloads -- even gaming -- are pretty much inline with the equivalent Ryzen CPUs.

Log in

Don't have an account? Sign up now