A question we have seen fairly consistently on STH is how would AMD Ryzen CPUs fare compared to their Intel Xeon E-2100/ E-2200 series competition. This is not exactly a fair comparison since the Ryzen platforms do not have a win at a major (top 10) server OEM. Still, there are now a handful of platforms that have a BMC for management duties. Ryzen CPUs can support ECC memory as well, although that also requires motherboard support.
AMD Ryzen 5 1600 AF Overview
Key stats for the AMD Ryzen 5 1600 AF: 6 cores / 12 threads with a 3.2GHz base clock and 3.6GHz turbo boost. There is 16MB of onboard L3 cache. The CPU features a 65W TDP. These are $85 list price parts.
Here is the lscpu output for the Ryzen 5 1600 AF:
Regular STH readers may remember we had an AMD Ryzen 5 1600 review around three years ago. A lot has changed. This is a 12nm chip, not the 14nm that we originally reviewed. We get a bump to 3.6GHz turbo and DDR4-2933 speeds. The cores are now Zen+. Effectively, this is an AMD Ryzen 2600 that loses 200MHz base and 100MHz turbo clocks with a massive price drop ($85 v. $200.)
This is far from the highest performing chip. On the other hand, for $85, this is a great option. Since we are reviewing this in the context of server parts, we wanted to see if this 6-core $85 part can perform well enough to justify moving to smaller vendor platforms that are not supported by wide arrays of OSes.
Just as a quick note before we get too far here, one will note we have the “AF” numbers we are focusing on today. We also have an original 14nm Ryzen 5 1600 re-tested along with a current-gen Ryzen 5 3600.
Test Configuration
For our review, we are using the ASRock X470D4U server platform.
- Motherboard System: ASRock X470D4U
- CPU: AMD Ryzen 5 1600 (AF)
- Memory: 2x Crucial 16GB ECC UDIMMs
- OS SSD: Intel S3610 480 GB
We first saw the ASRock Rack X470D4U at Computex. This is an mATX platform that is designed to take these consumer-focused chips and integrate them into cost-sensitive server segments.
We are going to have reviews of both the X470D4U and the 10Gbase-T version of the board in the near future on STH with some deeper insights into the platform.
After doing the reviews that will be published soon, we think that the Ryzen 5 1600 AF is a good match for this platform if you want to create a low-cost Core i3/ Xeon E-2200 competitor. There are, of course, some big caveats there.
Next, we are going to take a look at benchmarks before getting to some of the market analysis.
John,
Why didn’t you include a Ryzen 5 2600 in the mix?
The 1600 AF is often likened to a 2600 from a performance point of view.
I’d like to have seen the 16c Ryzen. BinkyTo I don’t see the point of the 2600. The 1600AF is so close and the 3600 is newer and better at the price. Maybe for completeness but I can’t see buying a 2600 over a 1600AF or 3600.
BinkyTo and Nate77,
I am reviewing the X470D4U class boards, and ran the benchmarks for this article. The trio of CPUs we had available to us were the original 1600, the 1600 AF, and the 3600; the idea being to cover each of the three Zen generations and simply make sure all was well from a software compatibility standpoint. Performance can scale up (or down) with core count if you move away from the 6C solutions within any of the three generations of the Ryzen CPUs, so we wanted to make sure that all three generations were tested.
It’s a bit like iOS it’s not supported by the big server vendors such as Dell EMC, HPE, Inspur, and Lenovo and when your server workloads depends on vendors like Dell EMC, HPE, Inspur, Lenovo and Apple you know that your in deep sh*t. It’s a bit like when your IT depends on ORACLE. It’s a good thing that companies like AsRock, Gigabyte, Tyan, etc.. give us the opportunity to not be in the hands of corporate companies like the NSA and CIA(Cisco and Juniper) or Intel, Dell EMC, HPE, Inspur, Huawei, Lenovo, Apple etc.., with these big brands you are in certified sh*t.
Just completed a new build with E2246G. Software vendor support was main reason why I chose intel. Though I may consider a pfsense box with this CPU.
Gee whiz. If you were writing an article about a jellied eel, you’d still start the wrap up page with “These chips are not released in a vacuum instead, they have competition on both the Intel and AMD sides.”.
“ ASRock Rack has an X570 version of this Ryzen server platform coming, but the chipset uses much more power.”
So we’re getting a X570D4U soon? That’s the first I’ve heard of that.
Ramblinreck47 I think they’re talking about the X570D4I-2T which is the mITX x570 version https://www.asrockrack.com/general/productdetail.asp?Model=X570D4I-2T#Specifications
It isn’t the same, but it’s the successor in x570. I think mITX is better than mATX since it’ll fit more cases.
Personally I would build with a Ryzen 2700E if I could get something like that with integrated graphics. That is one of the reasons the E2176G and E2278G are so compelling, coupled with broad based support for Intel.
jingram, I eagerly await the desktop version of the Renoir 8-core CPU, since removing the need for the additional expense of a GPU should make the AMD solution much more compelling for business class workstations. Plus, assuming the desktop Renoir CPUs use the same die as their mobile counterparts (there is precedent for this in the previous generation APUs) then this future 8-core desktop APU will be a fully monolithic die, rather than chiplet based like the 3rd gen Ryzen 3000 desktop parts. This could result in slight upticks in performance even compared to non-APU processors thanks to reduced intra-die latency.
Very cool review. Obviously the lack of OEM support is going to be an important factor, but with performance and value like this, I hope product managers at OEMs are seriously looking at Ryzen solutions. This kind of media attention should hopefully raise awareness.
It will be interesting to see how this lines up with other sub-$100 AMD cpus like the Athlon 3000G and Ryzen 3 3100.
Ya’ll doing some great stuff STH. Keep at it.
Where do you find an AMD Ryzen 5 1600 AF sold or quoted at $85?
Domih, they are found on Amazon but go in and out of stock every few days.
Unfortunately the current price is almost $150. It would be a monster at the original price.
The price spikes are real. I believe our review unit was purchased for the $85 price around three weeks ago, and I personally purchased another in early April for $90, but they’ve been popular chips and the availability and pricing are suffering as a result.
Too bad these X470 asrock rack boards are unobtainium now
I was surprised to see this combination, the 1600 isn’t on the QVL for ASRock. The CPU I’d like to see is the new ryzen 3300. The low tdp and performance looks promising.
Great review and really, really useful. I’m done my math for such configuration, it is also very useful to have all that CPUs compared on one place. Thanks!
Mike B,
The 1600AF isn’t on the QVL, but the 2600 is and they are essentially the same chip. Plus with the low cost of the 1600AF, we thought it was worth investigating. We actually benchmarked the X470D4U with a 1st gen 1600, the 1600 AF, and the 3600, and all three worked perfectly. The idea was to validate the functionality of all three Zen generations, and the users can extrapolate from those 6-core results to decide if they want more or less cores.
Will the results are definitely compelling.
I’m planning on using this ASRock board in a near future FreeNAS build. At this point I just need to find whether the 1600AF or 3300x makes more sense (cores vs clock).
Mike B,
I’m currently running some FreeNAS testing on this board for an upcoming article, running the Ryzen 5 3600. The next article isn’t about CPU performance so it isn’t the focus of my testing, but I can assure you the 3600 is nearly asleep during my testing. For what I am doing now, I could easily lose 2 of the cores and not be affected.
If you are doing more CPU intensive things like multiple streams of PLEX transcoding, the choice of CPU would perhaps make more difference.
power consumption test?
Does 1600AF consume a lot when it idles?
Could you compare power consumption? e.g. idle
1600AF vs 9100 vs others??
Thanks.
There is no power consumption figures at all, so the article is mostly about nothing.