AMD Ryzen 9 7950X and Ryzen 5 7600X Review: A Return to Gaming Dominance

DDR5, PCIe 5.0, 5nm, AM5, and 5.7 GHz

AMD Ryzen 9 7950X and Ryzen 5 7600X
(Image: © Tom's Hardware)

Why you can trust Tom's Hardware Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Find out more about how we test.

Zen 4 Microarchitecture and IPC Measurements

AMD says the Zen 4 architecture is an iterative advance over Zen 3, but Zen 5, which arrives in 2024, will be a ground-up redesign. Zen 4 has plenty of advancements, though. As you can see throughout the album above, AMD made several advances, but widening the front end to better feed the execution units and improving branch prediction account for 60% of the IPC gain. AMD also increased the op-cache by 1.5x, moved to a two-branch-per-cycle prediction, improved the load/store units, and doubled the L2 cache capacity. The increased L2 cache capacity results in an additional 2 cycles of L2 latency and adds 4 cycles to L3 latency. AMD says this increased latency isn’t too detrimental because the increased cache capacity provides higher hit rates that largely offset the penalty. 

AMD has enabled support for AVX-512 instructions, giving it a curious advantage over Intel, which pioneered the SIMD instructions but ended up disabling them with Alder Lake. AMD describes its AVX-512 implementation as a 'double-pumped' execution of 256-bit wide instructions. This means that it actually takes two clock cycles to execute an AVX-512 instruction. However, this provides compatibility with AVX-512 and still boosts performance. This approach also saves die area and defrays the frequency and thermal penalties typically associated with Intel's processors when they execute AVX-512 workloads.

Speaking of the die, the die size for the new 6nm I/O die (IOD) is 122mm^2, or roughly the same size as the 124.94mm^2 12nm IOD present on the Ryzen 5000 chips. It has 3.4 billion transistors. Additionally, the Zen 4 compute die (CCD) measures 70mm^2, which is somewhat smaller than the 83.74mm^2 die on the Ryzen 5000 processor. Given that we're looking at a much denser N5 process for Ryzen 7000 compared to the 7nm process for Ryzen 5000, the smaller die has 6.5 billion transistors for the Zen 4 CCD compared to 4.15B transistors for Zen 3 CCDs (a 36% increase for Zen 4).

AMD’s implementation results in lower throughput per clock than Intel's method, but the higher clocks obviously offset at least some of the penalty. AMD says AVX-512 provides a 30% increase in multi-core FP32 workloads over Zen 3 and a 2.5X speedup for multi-core int8 operations. As we saw in our own benchmarks, the approach provides significant performance uplift. 

AMD says the net effect of its Zen 4 architectural enhancements is a 13% increase in IPC over Zen 3. AMD also claims to deliver better power efficiency in a much smaller package than Intel's Alder Lake processors. The company compared its Zen 4 core to Intel's Golden Cove to highlight that it is half the size at 3.84mm2, yet wrings out 47% more power efficiency.

Measuring IPC is tricky, largely because it varies based on the workload. AMD calculated its 13% IPC improvement from 22 different workloads, including gaming, which seems a curious addition due to possible graphics-imposed bottlenecks. AMD also included some multi-threaded workloads. AMD's results show that the IPC improvements vary, with improvements spanning from 39% in wPrime to a 1% improvement in the CPU-z benchmark.

We tested a limited subset of single-threaded workloads to see the clock-for-clock improvements, locking all chips to a static 3.8 GHz all-core clock with the memory dialed into the officially supported transfer rate. As you can see, Zen 4 does deliver solid IPC improvements in a multitude of workloads. The y-cruncher and Geekbench 5 crypto scores experience rather disproportionate gains, but that comes as a result of Zen 4’s support for AVX-512. However, as we saw in the single- and multi-threaded y-cruncher benchmarks, this performance doesn’t scale linearly to higher core loadings.

Ryzen 9 7950X and Ryzen 5 7600X Benchmark Test Setup

We tested the Ryzen 7000 processors with an ASRock X670E Taichi motherboard. We tested all Intel configurations with DDR5 memory, but you can find performance data for DDR4 configurations in our CPU Benchmark hierarchy. We also tested with secure boot, virtualization support, and fTPM/PTT active to reflect a properly configured Windows 11 install. 

Our overclocks were rather straightforward — we enabled the auto-overclocking Precision Boost Overdrive (PBO) feature with 'advanced motherboard' settings and adjusted the scalar setting to 10X. For our overclocked configurations, we enabled the DDR5-6000 EXPO profile for the memory kit. This also automatically enables the AMD-recommended Auto setting for the fabric and a 1:1 ratio for the memory frequency and memory controller (Auto:1:1 is the recommended setting for memory overclocking with Ryzen 7000). 

Swipe to scroll horizontally
Core i9-12900K and Core i5-12600K Test System Configurations
AMD Socket AM5 (X670E)Ryzen 9 7950X, Ryzen 5 7600X
Row 1 - Cell 0 ASRock X670E Taichi
Row 2 - Cell 0 G.Skill Trident Z5 Neo DDR5-6000 - Stock: DDR5-5200 | OC/PBO: DDR5-6000
Intel Socket 1700 DDR5 (Z690)Core i9-12900K, i7-12700K, 15-12600K, i5-12400
Row 4 - Cell 0 MSI MEG Z690 Ace
Row 5 - Cell 0 G.Skill Trident Z5 DDR5-6400 - Stock: DDR5-4400 | OC DDR5-6000
AMD Socket AM4 (X570)Ryzen 9 5950X, 5900X, 5700X, 5600X, 5800X3D

MSI MEG X570 Godlike
Row 8 - Cell 0 2x 8GB Trident Z Royal DDR4-3600 - Stock: DDR4-3200 | OC/PBO: DDR4-3800
All SystemsGigabyte GeForce RTX 3090 Eagle - Gaming and ProViz applications
Row 10 - Cell 0 Nvidia GeForce RTX 2080 Ti FE - Application tests

2TB Sabrent Rocket 4 Plus, Silverstone ST1100-TI, Open Benchtable, Arctic MX-4 TIM, Windows 11 Pro
CoolingCorsair H115i, Custom loop
Overclocking noteAll configurations with overclocked memory also have tuned core frequencies and/or lifted power limits.
Paul Alcorn
Managing Editor: News and Emerging Tech

Paul Alcorn is the Managing Editor: News and Emerging Tech for Tom's Hardware US. He also writes news and reviews on CPUs, storage, and enterprise hardware.

  • -Fran-
    Thanks for the review(s)!

    Good to see more reaffirmation these CPUs don't have a performance problem, but a platform cost (or "cost of entry") problem with them. I hope AMD can alleviate it a bit so they become more of a mainstream crowd fav.

    One small point that I won't really defend much, but buying into the AM5 platform, you buy into several years of support. The huge caveat is you have to trust not only AMD, but the partners to go with it and roll the BIOS updates down the line. This being said, after AM4, I'd imagine both AMD and partners have seen it does matter they do keep supporting newer CPUs and see that as a strength. Maybe partners would rather convince you to buy a new motherboard, but allowing this "mix and match" with generations does help overall sales; or so it is my impression. Plus, we all know which motherboard vendors actually followed through with the updates, so they'll get more sales once B650 launches. Could Tom's have the list of motherboards from the 300-series chipsets that do support Ry5K? That would actually help track which partners are indeed reliable and can be trusted with buying into AM5.

    Regards.
    Reply
  • Alvar "Miles" Udell
    The headline: AMD Ryzen 9 7950X and Ryzen 5 7600X Review: A Return to Gaming Dominance
    The reality: 5800X3D performs better in games than either of those.
    Reply
  • -Fran-
    Alvar Miles Udell said:
    The headline: AMD Ryzen 9 7950X and Ryzen 5 7600X Review: A Return to Gaming Dominance
    The reality: 5800X3D performs better in games than either of those.
    To be pedantic, the title is correct. They now have more than just 1 CPU topping the charts and most (if not all) above Intel offerings.

    You'd be correct if the title was something like "7950X is the new gaming overlord/king/champion*" or something that implies "the CPU is 1st in gaming", which as you clearly noticed, it is not.

    Plus, it depends on the game anyway.

    Regards.
    Reply
  • BogdanH
    I didn't read the article, simply because it's too long -quick view on some of pages gave me impression, that there's a lot of repeating from previous articles.. so why bother.
    Another reason why I didn't read, is the title. When I see a CPU like 7900X/7950X (or Intel's pendant) in conjunction with "gaming", I can already imagine the content. I assume, such title should grab the attention... I'm not sure who's attention, though. Are you trying to convince "gamers" to shell out 800€ for CPU alone? Yes, there's always said, that for gaming alone, it's "wiser" to get 7600X (or 5800X3D) -but such title still imply that 7950X is simply "the right thing"... "if you wish to have it all..". -again, that's my impression, so feel free to diagree.

    Ok, so you say (for example), 7950X is 15% faster (in whatever) than 5950X. Now, some of this performance increase happens thanks to faster new DDR5 memory. And quite a lot performance increase (in my opinion) goes to much higher clock speed -which in turn comes back as heat dissipation. There's also faster PCIe5.0, etc ... Now I wonder, how much has actual CPU improved (compared to 5950X)? I mean IPC. Because if IPC is the same, then I see 7950X as a "brute force" improvement. In sense: Make it faster, no matter the costs (power draw & heat dissipation).
    Yes, I know: 7950X finishes work faster (than 5950X) and so at the end, electricity bill will be lower. That's true if we look strictly from CPU side. But, if we take the cooling (of whole PC) into account, then the total power draw doesn't look that appealing anymore -especially in summer. In short: CPU is more efficient, but whole PC probably isn't.

    I can read many times in forums, that many are already running their PC in eco-mode (to save energy, to make PC more silent, having less heat in room, etc) -they're ready to sacrifice fps by few percent for that. So I assume, what they wish or hope for, is certain performance increase, without affecting power draw -at least not by much.

    I don't blame AMD/Intel/Nvidia for going into high power consumption direction. They know we wish everything faster (than it was in previous generation), so they do it -and many will buy it.. and that's the whole idea,
    However, I do blame media for not putting more investigation/research into efficiency and write about that.

    Just sharing my thoughts (being aware I may be wrong)
    Bogdan
    Reply
  • DavidLejdar
    -Fran- said:
    Thanks for the review(s)!

    Good to see more reaffirmation these CPUs don't have a performance problem, but a platform cost (or "cost of entry") problem with them. I hope AMD can alleviate it a bit so they become more of a mainstream crowd fav.

    ...

    If one wants to go for as cheap a build as possible e.g. just to play CS:GO, then yeah, the DDR5 requirement with AM5 may sure be off-putting. Myself, I will be upgrading in the near future from DDR3 anyhow, and (here) the extra cost for 32 GB DDR5-5200 (instead of DDR4-3200) is around 80 currently. At the same time, B650E has PCIe 5.0 both for GPU (16x) and NVMe at currently around 300-400 cheaper than what motherboards for Raptor Lake with the same connectivity cost (that is the few released so far). And only a handful of Alder Lake MBs have PCIe 5.0 for NVMe, while taking away 8 lanes from the GPU for that though.

    So what I am currently looking at is around 250 for AM5 motherboard and 170 for 32 GB of DDR5 - which isn't as cheap as it can get, but should be plenty good for at least several years, giving me the option to upgrade individual parts later.

    And to me that seems worth it to go for that, instead of saving perhaps 100 bucks with a Raptor Lake MB and DDR4 now, which likely won't support Meteor Lake already and would require me to get a lot of new parts then if I may want to boost performance in a year or two.

    Of course, as you point out, not really a guarantee that even AMD directly may not push AM6 soon if Meteor Lake is taking it all to very new heights. But even if I upgrade the MB sooner than I was expecting, at least I will already have DDR5 to reuse, including having made use of it in the meantime.

    BogdanH said:
    ... . But, if we take the cooling (of whole PC) into account, then the total power draw doesn't look that appealing anymore -especially in summer. In short: CPU is more efficient, but whole PC probably isn't.

    I can read many times in forums, that many are already running their PC in eco-mode (to save energy, to make PC more silent, having less heat in room, etc) -they're ready to sacrifice fps by few percent for that. So I assume, what they wish or hope for, is certain performance increase, without affecting power draw -at least not by much. ...

    Very strictly taken, sure, the cooling uses some power too. But then again, a case fan has a power consumption of up to 6W, and CPU coolers (air or liquid) usually don't consume more than that. So even if all the cooling would take 20W at full load, that is 50 hours of full load to get to 1 kWh. And e.g. in the U.S., it is less than $1 for 4 kWh, isn't it?

    The electricity costs can add up quickly though. E.g. if someone is gaming 50 hours a week at 700W, that's possibly up to 35 kWh right there, coming to 140 kWh a month.

    Myself, I wouldn't know how to have that much time for gaming. So even if my rig would consume 700W, perhaps every other week to play at full load for a total of 10 hours, at the U.S. electricity price that would be less than $2.

    Which isn't to say that it wouldn't be nice if there would be more improvement for power efficiency. But the review mentions that the Ryzen 5 7600X is a very sound choice for gaming (unless one can wait a few months to check out the gaming specific CPU). And that one has quite less Watt than the top tier one. And coupled with perhaps not the top-tier GPU around, e.g. the RTX 3060, which has around 200W, one can have a solid build which comes in at under 500W at full load.
    Reply
  • BogdanH
    DavidLejdar said:
    Very strictly taken, sure, the cooling uses some power too. But then again, a case fan has a power consumption of up to 6W, and CPU coolers (air or liquid) usually don't consume more than that. So even if all the cooling would take 20W at full load...
    -that's 20W (probably less) just to move hot air out of PC case into our room.. which we need to cool in summer days.
    Many say, it's "only 10€/year more" (or whatever number).. but there are millions of PC's running. And if looking that way, we can see see how much energy is wasted.. and is really not about who can afford to pay electricity and who can't.

    Best wishes,
    Bogdan
    Reply
  • chalabam
    Der Bauer has shown that this CPU is 20 degrees hotter than it should be due to bad packaging
    Reply
  • Sluggotg
    Nice new lineup for AMD. Looking forward to the industry moving to PCIE 5 and USB 4. The 7600 is very impressive. (For 300 Bucks!). With Intel's new chips coming out next month we should see some very healthy competition that will hopefully lead to overall lower prices. With the New CPUs and the New Graphics cards all coming out in the next several months, we should be able to do some nice upgrades. Hopefully the Scalpers will fail to corner the market.
    Reply
  • -Fran-
    BogdanH said:
    I didn't read the article, simply because it's too long -quick view on some of pages gave me impression, that there's a lot of repeating from previous articles.. so why bother.
    Another reason why I didn't read, is the title. When I see a CPU like 7900X/7950X (or Intel's pendant) in conjunction with "gaming", I can already imagine the content. I assume, such title should grab the attention... I'm not sure who's attention, though. Are you trying to convince "gamers" to shell out 800€ for CPU alone? Yes, there's always said, that for gaming alone, it's "wiser" to get 7600X (or 5800X3D) -but such title still imply that 7950X is simply "the right thing"... "if you wish to have it all..". -again, that's my impression, so feel free to diagree.

    Ok, so you say (for example), 7950X is 15% faster (in whatever) than 5950X. Now, some of this performance increase happens thanks to faster new DDR5 memory. And quite a lot performance increase (in my opinion) goes to much higher clock speed -which in turn comes back as heat dissipation. There's also faster PCIe5.0, etc ... Now I wonder, how much has actual CPU improved (compared to 5950X)? I mean IPC. Because if IPC is the same, then I see 7950X as a "brute force" improvement. In sense: Make it faster, no matter the costs (power draw & heat dissipation).
    Yes, I know: 7950X finishes work faster (than 5950X) and so at the end, electricity bill will be lower. That's true if we look strictly from CPU side. But, if we take the cooling (of whole PC) into account, then the total power draw doesn't look that appealing anymore -especially in summer. In short: CPU is more efficient, but whole PC probably isn't.

    I can read many times in forums, that many are already running their PC in eco-mode (to save energy, to make PC more silent, having less heat in room, etc) -they're ready to sacrifice fps by few percent for that. So I assume, what they wish or hope for, is certain performance increase, without affecting power draw -at least not by much.

    I don't blame AMD/Intel/Nvidia for going into high power consumption direction. They know we wish everything faster (than it was in previous generation), so they do it -and many will buy it.. and that's the whole idea,
    However, I do blame media for not putting more investigation/research into efficiency and write about that.

    Just sharing my thoughts (being aware I may be wrong)
    Bogdan
    Er... Paul (the article) did include IPC measurements and a couple parragraphs to that. Zen4 is indeed faster, clock for clock, than Zen3. It's just it gets more overall performance from the increased clocks (hence the higher power budget) than raw IPC improvements.

    Regards.
    Reply
  • hotaru251
    so zen 3 they held out entire generation for a 5700x

    and now zen 4 its the 7800x missing...AMD ffs why do you do this?

    and as said before...the cpu are great, but platform isnt worth it with 5800x3d existing.

    (will likely change by time weg et 3d cache zen4 cpus)
    Reply