AMD Ryzen 7 2700X Review: Redefining Ryzen

Cache And Memory Performance, IPC

Memory Latency

AMD Measurements
L1 Cache LatencyL2 Cache LatencyL3 Cache Latency
Memory Latency
Latency Improvements13%34%16%
11%

AMD's first-gen processors demonstrated higher memory latency than we expected, affecting the performance of memory-sensitive applications. The company claims it reduced memory latency by 11% this time around, as well as cutting cache latencies by double-digit percentages. We'll start by measuring the memory and Infinity Fabric subsystems, and then move on to IPC tests.

SiSoftware's Sandra is used to measure cache and memory latency with three different access patterns, giving us more granularity than a single test. Sequential access patterns are almost entirely prefetched into the TLB, so that one's a good measure of prefetcher performance. The in-page random test measures random accesses within the same memory page. It also measures TLB performance and represents best-case random performance. The full random test features a mix of TLB hits and misses, with a strong likelihood of misses, so it quantifies worst-case latency.

We tested both the Ryzen 7 1800X and Ryzen 7 2700X on the same X470 motherboard. We include results with the Ryzen 7 2700X at DDR4-2933 for the stock configuration, DDR4-3466 for the overclocked configuration, and DDR4-2666 to normalize it with AMD's Ryzen 7 1800X.

With normalized DDR4-2667 data rates and timings, the Ryzen 7 2700X posts impressive gains over Ryzen 7 1800X, regardless of the data access pattern. As percentages, the 2700X's improvements weigh in at 11.49% for full random, 6.64% for in-page, and 9.35% for the sequential access pattern.

The Infinity Fabric speeds up as we increase memory frequency to the 2700X's default DDR4-2933. This fabric ties the IMC and cores together, so we record even larger improvements of 18% in the full random test, 13.4% with a full random access pattern, and 12.9% with the sequential metric.

AMD isn't fully disclosing the steps it took to improve memory latency, but we suspect the company worked on the Infinity Fabric and integrated memory controller to realize these gains.

Cache Latency And Bandwidth

Regardless of the memory access pattern, the smallest data chunks fit into L1 cache. As the data gets larger, it populates the 2700X's higher tiers of cache, which we outlined in the following table:


L1
L2
L3
Main Memory
Range
2KB - 32KB
64KB - 512KB
1MB - 4MB
8MB - 1GB

% Improvement Over 1800X
L1
L2
L3
In-Page
11.11%
51.72%
26.38%
Full-Random
11.11%
53.5%
25.64%
Sequential
11.11%
13.3%
13.3%

The cache latency reductions that we measured are even better than what AMD suggested we'd see, though its lab might be using different access patterns. Regardless, the apples-to-apples results in our table are downright impressive.

We also see a notable increase in cache bandwidth. Feeding the cores with lower latency and higher throughput is a win-win on the performance front. Intel's S-series processors still have a big single-core L1 bandwidth advantage, but AMD's updated L2 cache is measurably faster than the 1800X in both single- and multi-threaded tests. AMD even enjoys better L2 cache latency than Intel in the sequential test and better L3 cache latency with several data patterns.

To Infinity, And Beyond

The updated Zen+ design fuses two four-core CCXs together with the Infinity Fabric, which is a crossbar that also handles IMC, northbridge, and PCIe traffic. As such, fabric latency is a critical variable that ensures the memory latency gains we observe can actually be delivered to the cores.

SiSoftware Sandra's Processor Multi-Core Efficiency metric helps illustrate the Infinity Fabric's performance. We use the Multi-Threaded test with the "best pair match" setting (lowest latency). The utility measures ping times between threads to quantify fabric latency in every possible configuration. We boil those benchmarks down to latency averages for the different pathways, but head here for a more detailed explanation of the various components.

AMD reduced Ryzen 7 2700X's intra-core latency by 11.8% and the critical cross-CCX latency by 8.3%. We also notice that Ryzen 7 2700X offers significantly improved fabric bandwidth.

Instructions Per Clock

It's important to remember that IPC can vary by workload, so dissimilar tasks may yield different outcomes. We set a static 3 GHz clock rate for the following tests:

Our single-core Cinebench benchmark suggests a 1.6% IPC improvement favoring Ryzen 7 2700X. But while AMD does improve, Intel still holds onto a distinct IPC throughput advantage. Switching to the Multi-Threaded Cinbench test gives Ryzen 7 2700X a 2.7% improvement over its predecessor.

Core i9-7820X employs two 256-bit AVX FMA units per core that operate in parallel, whereas Ryzen's Zen architecture divides 256-bit AVX operations across two FMA units per core. That difference hands the Skylake-X processor a commanding lead in y-cruncher. We do see a 3.9% increase in the 2700X's Multi-Threaded y-cruncher result compared to Ryzen 7 1800X. But the gains in single-threaded AVX performance are marginal.

We see similar results in our single-core cryptographic tests, though Ryzen 7 2700X takes an 8.7% lead over the 1800X in the Multi-Threaded AES-256-ECB encryption workload. AMD's Zen architecture includes two AES cryptographic accelerators for each core, so it isn't surprising to see Ryzen dominate over Intel's S-series CPUs in the AES-256-ECB tests.

MORE: Best CPUs

MORE: Intel & AMD Processor Hierarchy

MORE: All CPUs Content

This thread is closed for comments
138 comments
    Your comment
  • Ninjawithagun
    Once again, Tom's provides an incorrect comparison in this review. Intel's 8700K is comparable to the 2600 or 2600X and NOT the 2700 or 2700X. Just count the number of cores and threads and one should be able to figure that out O.o

    Whine all you want. Just because you down vote me only means you don't know how to read or count :P
  • Sakkura
    146263 said:
    Once again, Tom's provides an incorrect comparison in this review. Intel's 8700K is comparable to the 2600 or 2600X and NOT the 2700 or 2700X. Just count the number of cores and threads and one should be able to figure that out O.o


    The 2700X costs $329, the 8700K costs $359. It is a very reasonable comparison to make.
  • tripleX
    7820X is also there with the same number of cores and threads.
  • tparkhuose
    well i know what im upgrading to now. thanks
  • justin.m.beauvais
    It sure is nice to see an AMD chip up there in the thick of it with Intel's best offerings. Competition has finally officially returned. I'm impressed that AMD gained so much ground and managed to make the price more competitive than the 1800x was. It is slightly disappointing that overclocking remains less impressive than the Intel offerings, but everything else sort of makes up for that.

    I didn't feel like AMD was quite "there" yet with the 1000 Ryzens, but with the 2000 series I feel like we can finally say that they have arrived.
  • Ninjawithagun
    551379 said:
    146263 said:
    Once again, Tom's provides an incorrect comparison in this review. Intel's 8700K is comparable to the 2600 or 2600X and NOT the 2700 or 2700X. Just count the number of cores and threads and one should be able to figure that out O.o
    The 2700X costs $329, the 8700K costs $359. It is a very reasonable comparison to make.


    Incorrect. It has nothing to do with price. Comparing like CPU architectures is the only logical course of action. 6 core/12 thread vs 8 core/16 thread makes no sense. Comparing the Intel 8700K 6 core/12 thread @ $347 to the AMD 2600X 6 core/12 thread @ $229.99 makes the most sense here. Once the proper math is done, AMD destroys Intel in performance vs. cost, especially when you game at any resolution higher than 1080P. The GPU becomes the bottleneck at that point, negating any IPC benefits of the Intel CPUs. I know this how? Simple. I also own a 8700K gaming PC ;-)

    Once again, whine all you want. Just because you down vote me only means you don't know how to read or count :P
  • bfwhsm
    Now, do the tests again with meltdown/spectre applied on intel cpus, as you should.
    And you will see a VERY different story, with 2700k destroying 8700k in almost every measure).

    (check out anandtech's review to get an idea)
  • Ninjawithagun
    2672992 said:
    Now, do the tests again with meltdown/spectre applied on intel cpus, as you should. And you will see a VERY different story, with 2700k destroying 8700k in almost every measure). (check out anandtech's review to get an idea)


    I will definitely check out that review as well. Thanks bfwhsm!
  • tripleX
    2672992 said:
    Now, do the tests again with meltdown/spectre applied on intel cpus, as you should. And you will see a VERY different story, with 2700k destroying 8700k in almost every measure). (check out anandtech's review to get an idea)


    Maybe you should read the comments on the AnandTech article. They all point out that the test results don't match any other site's results.
  • Sakkura
    1440742 said:
    2672992 said:
    Now, do the tests again with meltdown/spectre applied on intel cpus, as you should. And you will see a VERY different story, with 2700k destroying 8700k in almost every measure). (check out anandtech's review to get an idea)
    Maybe you should read the comments on the AnandTech article. They all point out that the test results don't match any other site's results.


    ... because of the different testing procedure that he just referred to.
  • tripleX
    551379 said:
    1440742 said:
    2672992 said:
    Now, do the tests again with meltdown/spectre applied on intel cpus, as you should. And you will see a VERY different story, with 2700k destroying 8700k in almost every measure). (check out anandtech's review to get an idea)
    Maybe you should read the comments on the AnandTech article. They all point out that the test results don't match any other site's results.
    ... because of the different testing procedure that he just referred to.


    Multiple other sites have patched fully, but their results are drastically different than AT. Due to the obvious disparities, AT now says via twitter that it is investigating its results.
  • Blas
    Hi Paul, Igor, great review!
    A point to correct, on page 1: where it says "We still don't have a release date for the less expensive B470- and A470-based motherboards" it should be "We still don't have a release date for the less expensive B450- and A420-based motherboards". (Chipset numbers)
  • East17
    The the multi-core enhancement enabled on the Intel 8700K system or not ?!

    Because we see AMD's 2700X never goes beyond 105 W total power consumption while Intel's 8700K reaches 160W.

    Somehow, the Intel platform is allowed to use up to 65% more power and we believe this is not really a fair comparison.
  • PaulAlcorn
    127850 said:
    Hi Paul, Igor, great review! A point to correct, on page 1: where it says "We still don't have a release date for the less expensive B470- and A470-based motherboards" it should be "We still don't have a release date for the less expensive B450- and A420-based motherboards". (Chipset numbers)


    Thanks! Late nights around NDA time :) We'll fix it.
  • PaulAlcorn
    190859 said:
    The the multi-core enhancement enabled on the Intel 8700K system or not ?! Because we see AMD's 2700X never goes beyond 105 W total power consumption while Intel's 8700K reaches 160W. Somehow, the Intel platform is allowed to use up to 65% more power and we believe this is not really a fair comparison.


    We disabled MCE on all platforms (covered in test setup). I'll follow up with Igor to make sure this isn't a typo.
  • AgentLozen
    JUSTIN.M.BEAUVAUS said:
    I didn't feel like AMD was quite "there" yet with the 1000 Ryzens, but with the 2000 series I feel like we can finally say that they have arrived.


    Those are my thoughts exactly. Last year I was really happy to see AMD make tremendous progress on it's CPU architecture but if I were forced to choose between Intel and AMD, I still would have gone Intel. This was compounded when Coffee Lake came out. It was a no brainer then.

    Today's story paints a picture of how much the Zen architecture has matured in the last year. A year of development has smoothed over the wrinkles in the 1800x and made the 2700x a truly worthy competitor to Intel's 8700K.
  • jpe1701
    Maybe I missed it in the article, but does xfr2 or precision boost 2 work on x370 boards?
  • PaulAlcorn
    1934870 said:
    Maybe I missed it in the article, but does xfr2 or precision boost 2 work on x370 boards?


    It does work on 300-series boards, but performance gains could be limited by power delivery. we cover that right at the top of page 2.
  • Ninjawithagun
    1934870 said:
    Maybe I missed it in the article, but does xfr2 or precision boost 2 work on x370 boards?


    My current understanding is that the X370 motherboards do support XFR2 and Precision Boost 2.0. As long as your motherboard manufacturer has developed and released a compliant BIOS update, you should be good to go. I just installed my 2700X into an AsRock X370 Fatal1ty Professional Gaming motherboard (BIOS update P4.60) and this thing is running crazy fast. Running Prime95 @ 3.92Ghz on all 8 cores and 16 threads. Amazing! I do have a custom watercooling system, so that will definitely help the 2700X maintain full XFR2 and Precision Boost when I need it. Also, was able to increase my DDR4 speeds from 2933Mhz to 3200Mhz with no issues. I will try 3400Mhz and 3466Mhz later this weekend and see if those speeds run stable. So far, extremely happy with my upgrade ;-)
  • darth_adversor
    Just to make sure I understood this correctly (and I apologize if I'm a little slow): any of the 2700X's "stock" benchmarks are ran at DDR4 2667?

    Aside from that, and this is just my .02, I feel like too much emphasis is placed on average framerates on the gaming benchmarks, and not enough on minimum framerates (though I do appreciate that you include both).
  • bfwhsm
    I reiterate: the other reviews may have received some form of patch (check out the test dates for the intel cpus; many date from January 2018)

    but it appears that only anandtech has applied the most recent and comprehensive April Meltdown/Spectre patch from MS.

    While there needs to be time for the dust to fully settle, for now, the message seems clear: after the security patches, AMD trumps Intel in every measure conceivable.
  • logainofhades
    Still no justifiable reason to change my 6700k, for something else, as my rig is mostly just gaming. Would be interested in F@H performance, of this CPU, though.
  • PaulAlcorn
    659338 said:
    Just to make sure I understood this correctly (and I apologize if I'm a little slow): any of the 2700X's "stock" benchmarks are ran at DDR4 2667? Aside from that, and this is just my .02, I feel like too much emphasis is placed on average framerates on the gaming benchmarks, and not enough on minimum framerates (though I do appreciate that you include both).



    We tested the stock 2700X at the supported DDR4-2933.

    We do use average framerates for comparative purposes during benchmark analysis, but minimum fare rates, while useful, can be deceiving at times. They only represent the single worst frame during any given recording, and sometimes you can get an errant result.

    To circumvent this, we use 99th percentile values, converted into an FPS measurement, for our final set of charts on the last page. This is a good metric that quantifies overall smoothness, so we use it for all cost analysis and the overall view of gaming performance relative to other processors.
  • mossberg
    146263 said:
    Once again, Tom's provides an incorrect comparison in this review. Intel's 8700K is comparable to the 2600 or 2600X and NOT the 2700 or 2700X. Just count the number of cores and threads and one should be able to figure that out O.o


    Price bracket is what the vast majority of reviews are based on. It has always been that way.