Power Consumption

For our power consumption readings, we run a Prime 95 load and slowly ramp up the number of threads in play, taking power data from the internal CPU registers that report for when turbo modes or thermal modes should activate. Depending on the CPU access, we can get data that varies from the full package down to individual cores, uncore, integrated graphics and DRAM controllers.

For the Ryzen CPUs, the API pulls out the total package power consumption first.

 Power: Total Package (Idle) Power: Total Package (1T)Power: Total Package (Full Load)

At idle, all the CPUs are pretty much equivalent. The cores are fully idle here, leaving the rest of the chip active enough for tick-over. As we ramp up the load, the higher-frequency Ryzen CPUs move towards their 65W TDP, with the Ryzen 3 1300X almost being spot on at 64.2W. The Intel CPUs are clocked higher, but only have two cores to contend with.  The Ryzen 3 1200 is clocked lower than the Ryzen 3 1300X, hitting a better efficiency point in the Zen design. This ultimately bodes well for upcoming quad-core SKUs in laptops.

Power: Cores Only (1T Load)Power: Cores Only (Full Load)

One of the odd things about the power consumption of the Ryzen 3 CPUs is the difference between how much power the cores internally measure compared to the full power consumption of the package measured as a whole, including the Infinity Fabric, DRAM controllers, IO and such. For the Ryzen 3 1200 for example, at full load the package has a power consumption of 40.43 W total, but the cores only count for 23.05W, leaving 17.38W on the table for the non-core elements in the chip. If we compare that to the Ryzen 5 1500X, we have 68.79W for the package and 49.69W for the cores, a 19.1W difference. For the Ryzen 7 1700X, it becomes 81.51W for the package and 62.10W for the cores, a 19.4W difference.

On the high-end chips, the difference is a smaller portion of the full power consumption, but on the Ryzen 3 processors the cores are only 57% of the power consumption, leaving 43% for the rest of the chip. A lot of this power could be the inter-CCX infinity fabric path, which means that packages like EPYC are giving away a lot of power to IF. If it is more other features, it could spell a number of problems for upcoming mobile chips, limiting the lower bounds of the power consumption. Naturally, I actually want to get my hands on to an EPYC processor in my own lab to see if we can pin down what is happening here.

Gaming Performance: Grand Theft Auto (1080p, 4K) Conclusion and Performance Per Dollar Graphs
Comments Locked

140 Comments

View All Comments

  • Ian Cutress - Thursday, July 27, 2017 - link

    AMD doesn't use the R3 / R5 / R7 nomenclature - that's for graphics.
  • Gothmoth - Thursday, July 27, 2017 - link

    i don´t care about gaming or heating my house with a cpu..... so ryzen makes more sense for me. :)

    x299 was such a disappointment.
  • MrCommunistGen - Thursday, July 27, 2017 - link

    Ian, first off, thanks for the benchmark numbers! I look forward to seeing the rest once they are completed.

    As far as data is concerned, is there a chance that the DigiCortex results have the wrong numbers next to a couple CPUs?

    I'm specifically looking at the i3 7100 being the fastest Intel CPU at 0.63, compared to the rest of the offerings clustering together at 0.37-0.38. To me it looks like the 0.63 should be the i5 7400 and the 7100 should be with the other dual cores.

    On another note, it looks like the RoTR Geothermal Valley scene really HATES AMD's HyperThreading - at least on Nvidia hardware/drivers. At first I thought there might be another set of numbers transposed somewhere since the Ryzen 3 CPUs perform SO MUCH better than the 1500X. But I looked back at the 1600X review and the numbers seem consistent -- bad performance on HyperThreaded AMD on a GTX 1080. Prophet's Tomb seems to behave better. Just shows how much architecture and software optimizations for said architecture can either oppose or compliment each other.

    As for small typos, there's also a couple spots where the 1200 is referred to as "1200X". There was another one I found during my initial read that I can't find now that I'm commenting.
  • MrCommunistGen - Thursday, July 27, 2017 - link

    Not the typo I was looking for, but I just noticed that the intro/description for Civ6 looks like it has a typo I've missed in previous articles:
    "...but every edition from the second to the sixth, including the fifth as voiced by the late Leonard Nimoy, it a game that is easy to pick up, but hard to master."

    "it a game" should probably be "is a game"

    Not a criticism, just trying to help out where I can. :)
  • MrCommunistGen - Thursday, July 27, 2017 - link

    Gah... brain fart this morning. Please read my references to AMD "HyperThreading" as "SMT"... smh
  • Ian Cutress - Thursday, July 27, 2017 - link

    i3 7100 should be 0.363x on DigiCortex. I've corrected three 7100 results today in our database from my personal master copy. I think I'll have to go through them all and double check.

    RoTR Geothermal on 1080p with a GTX 1080 really loves quad cores without hyperthreading, AMD or Intel. I'm not sure what it is with that test on that benchmark - in our KBL-X review, all the i5s got top results by a good margin. I think it's been optimized specifically for quad-core, or there's something iffy in the game code/drivers.

    Appreciate the typo point outs for sure. These things are always last minute and you can never have too many eyes on it. :)
  • DanGer1 - Thursday, July 27, 2017 - link

    The review is lacking, especially the value charts. Ryzens come with a cooler, their motherboards cost less and they are overclock-able. Adjusting the cost for the motherboard and the cooler changes the value charts significantly in R3's favor. Overclocking on stock air makes makes performance and value a no contest in favor of the R3s.
  • MajGenRelativity - Thursday, July 27, 2017 - link

    Intel's processors also come with a cooler.
  • wallysb01 - Thursday, July 27, 2017 - link

    Basic 1511 boards that would go into i3/Pentium builds are really not much more, if at all, than the lower end AM4 boards. Plus, the Intel stuff has an iGPU and if you're buying a low end desktop, you probably don't care a lot about heavily multithreaded workloads. So, I'd actually argue the i3/Pentiums are getting under sold in the value charts.

    Its kinda funny how the landscape has switched, in that Intel might actually be the better low-end, value winner, while AMD is the best mid/mid-high end value winner.
  • Gothmoth - Thursday, July 27, 2017 - link

    +1 for overclocking.
    the tested intel cpus are sure not k models.

    as for intel having internal GPU.. i never used them not even on my cheapest system builds.

Log in

Don't have an account? Sign up now