Improvements to the Cache Hierarchy

The biggest under-the-hood change for the Ryzen 2000-series processors is in the cache latency. AMD is claiming that they were able to knock one-cycle from L1 and L2 caches, several cycles from L3, and better DRAM performance. Because pure core IPC is intimately intertwined with the caches (the size, the latency, the bandwidth), these new numbers are leading AMD to claim that these new processors can offer a +3% IPC gain over the previous generation.

The numbers AMD gives are:

  • 13% Better L1 Latency (1.10ns vs 0.95ns)
  • 34% Better L2 Latency (4.6ns vs 3.0ns)
  • 16% Better L3 Latency (11.0ns vs 9.2ns)
  • 11% Better Memory Latency (74ns vs 66ns at DDR4-3200)
  • Increased DRAM Frequency Support (DDR4-2666 vs DDR4-2933)

It is interesting that in the official slide deck AMD quotes latency measured as time, although in private conversations in our briefing it was discussed in terms of clock cycles. Ultimately latency measured as time can take advantage of other internal enhancements; however a pure engineer prefers to discuss clock cycles.

Naturally we went ahead to test the two aspects of this equation: are the cache metrics actually lower, and do we get an IPC uplift?

Cache Me Ousside, How Bow Dah?

For our testing, we use a memory latency checker over the stride range of the cache hierarchy of a single core. For this test we used the following:

  • Ryzen 7 2700X (Zen+)
  • Ryzen 5 2400G (Zen APU)
  • Ryzen 7 1800X (Zen)
  • Intel Core i7-8700K (Coffee Lake)
  • Intel Core i7-7700K (Kaby Lake)

The most obvious comparison is between the AMD processors. Here we have the Ryzen 7 1800X from the initial launch, the Ryzen 5 2400G APU that pairs Zen cores with Vega graphics, and the new Ryzen 7 2700X processor.

This graph is logarithmic in both axes.

This graph shows that in every phase of the cache design, the newest Ryzen 7 2700X requires fewer core clocks. The biggest difference is on the L2 cache latency, but L3 has a sizeable gain as well. The reason that the L2 gain is so large, especially between the 1800X and 2700X, is an interesting story.

When AMD first launched the Ryzen 7 1800X, the L2 latency was tested and listed at 17 clocks. This was a little high – it turns out that the engineers had intended for the L2 latency to be 12 clocks initially, but run out of time to tune the firmware and layout before sending the design off to be manufactured, leaving 17 cycles as the best compromise based on what the design was capable of and did not cause issues. With Threadripper and the Ryzen APUs, AMD tweaked the design enough to hit an L2 latency of 12 cycles, which was not specifically promoted at the time despite the benefits it provides. Now with the Ryzen 2000-series, AMD has reduced it down further to 11 cycles. We were told that this was due to both the new manufacturing process but also additional tweaks made to ensure signal coherency. In our testing, we actually saw an average L2 latency of 10.4 cycles, down from 16.9 cycles in on the Ryzen 7 1800X.

The L3 difference is a little unexpected: AMD stated a 16% better latency: 11.0 ns to 9.2 ns. We saw a change from 10.7 ns to 8.1 ns, which was a drop from 39 cycles to 30 cycles.

Of course, we could not go without comparing AMD to Intel. This is where it got very interesting. Now the cache configurations between the Ryzen 7 2700X and Core i7-8700K are different:

CPU Cache uArch Comparison
  AMD
Zen (Ryzen 1000)
Zen+ (Ryzen 2000)
Intel
Kaby Lake (Core 7000)
Coffee Lake (Core 8000)
L1-I Size 64 KB/core 32 KB/core
L1-I Assoc 4-way 8-way
L1-D Size 32 KB/core 32 KB/core
L1-D Assoc 8-way 8-way
L2 Size 512 KB/core 256 KB/core
L2 Assoc 8-way 4-way
L3 Size 8 MB/CCX
(2 MB/core)
2 MB/core
L3 Assoc 16-way 16-way
L3 Type Victim Write-back

AMD has a larger L2 cache, however the AMD L3 cache is a non-inclusive victim cache, which means it cannot be pre-fetched into unlike the Intel L3 cache.

This was an unexpected result, but we can see clearly that AMD has a latency timing advantage across the L2 and L3 caches. There is a sizable difference in DRAM, however the core performance metrics are here in the lower caches.

We can expand this out to include the three AMD chips, as well as Intel’s Coffee Lake and Kaby Lake cores.

This is a graph using cycles rather than timing latency: Intel has a small L1 advantage, however the larger L2 caches in AMD’s Zen designs mean that Intel has to hit the higher latency L3 earlier. Intel makes quick work of DRAM cycle latency however.

Talking 12nm and Zen+ Translating to IPC: All This for 3%?
POST A COMMENT

541 Comments

View All Comments

  • klatscho - Monday, May 21, 2018 - link

    I second that. Reply
  • Maxiking - Monday, May 21, 2018 - link

    LOL, the benchmarks are now updated, Ryzen+ absolutely outperformed in games by 8700k even with Meltdown and Spectre patches. So nothing new, Ryzen is still bad. Reply
  • klatscho - Monday, May 21, 2018 - link

    If your usecase is 1080p gaming I would agree, however the difference becomes marginal as resolution increases. Also keep in mind that the 8700k currently retails for about $20 more than the 2700x and doesn't include a cooler, which means it is overall about $50 dearer... Reply
  • peevee - Tuesday, May 22, 2018 - link

    "and the speed is limited to how the system reads from a drive that spins at 7200 or 5400 times per second"

    It is PER MINUTE. As in RPM.
    Reply
  • cvearl - Friday, June 08, 2018 - link

    My 2600 X at stock does 177 in single core cinebench. But that is with h100i V2 cooler. With the default cooler it gets the same score as you 173. The cooler the chip the higher the Boost. Also out-of-the-box XMP in the Bios Works 3200 no problem. In fact cl14. Out of the box versus my 1600 X in the exact same system it is 15% faster across the board. Reply
  • virpuain@gmail.com - Tuesday, June 19, 2018 - link

    Nice review.
    On thing that bothers me is the inclusion of Winrar for this review without a note stating it is a underperforming compression tool. It is know that 7zip can compress almost twice as fast as Winrar.
    Not that but also the lack of consistency in between compressions tests as instead of compressing and decrompressing a set file you are taking different procedures for each benchmark. I mean the job is to compress/decompress, let the user know how it does and why it does that.
    Reply
  • 0ldman79 - Monday, July 23, 2018 - link

    I realize they probably don't have an FX 6300 and 83xx system for comparison.

    The FX 8350 scores 23719 MIPS on the 64 MB 7zip test, a good deal higher than the Kaveri or Bristol Ridge. I need to bench my 6300 just for giggles.
    Reply
  • mrinmaydhar - Friday, July 27, 2018 - link

    Try and run a S.M.A.R.T. test on the drives. The virtual adapter is unable to provide any data and causes a Blue-Screen. At least the last time I used the Enmotus version did. Reply
  • prateekprakash - Friday, August 03, 2018 - link

    "We’ll cover these in the next few pages, as well as the results from our testing.
    Overclocking"

    Where is the overclocking result?
    Reply
  • kithylin - Tuesday, September 04, 2018 - link

    YET ANOTHER REVIEW THAT DOESN'T SHOW US THERMALS! HOW HARD IS IT TO SHOW US HOW HOT A CHIP RUNS ON AIR COOLING FFS, NO ONE SHOWS THERMALS ON THESE DAN CHIPS, THIS IS THE 20'TH REVIEW IN GOOGLE AND NO THERMALS! Reply

Log in

Don't have an account? Sign up now