The Silver Lining of the Late AMD Opteron A1100 Arrival
by Johan De Gelas on January 14, 2016 1:19 PM EST- Posted in
- Cloud Computing
- AMD
- Arm
- Opteron
- Opteron A1100
Feature Rich
But not all servers are compute limited. Quite a lot of server tasks are I/O limited. Think static webserving, reverse proxys (Varnish server), in memory key value stores (Memcached), all kind of network servers and "cold" storage servers.
| Low End Server SoCs: feature comparison | |||
| Feature | Opteron A1100 | Atom C2000 | Xeon-D |
| Max. RAM Capacity | 4 x 32 GB RDIMM | 4x 16 GB RDIMM | 4 x 32 GB RDIMM |
| PCIe | 8 gen 3.0 lanes | 16 gen 2.0 lanes | 24 gen 3.0 lanes 8 gen 2.0 lanes |
| SATA | 14x SATA3 | 2x SATA3 4xSATA2 |
6x SATA3 |
| Ethernet | Dual 10 Gb | Dual 1 Gb | Dual 10 Gb |
| USB | Not Integrated | 4x USB 2.0 | 4x USB 3.0 4x USB 2.0 |
With 14 SATA ports and two real 10 Gb Ethernet ports, AMD's A1100 is a great place to start to build a storage device. Considering that quite a few storage devices now use a quadcore A15, which is limited to 4 GB of RAM (16 GB with PAE tricks), an octal core A57 that can address 128 GB opens up new opportunities. The quad core A1120 will do nicely even though it might consume up to twice as much (25W) as Annapunra Labs Alpina AL5140 SoC (Quad A15 at 1.7 GHz), which needs around 10W. In a storage device with 16 disks, 10W should not be a deal breaker, especially if you can offer more caching, faster encryption and higher overall performance.
The specs do not look bad for a caching server either, as 32 GB RDIMMs are less expensive per GB than 8 GB RDIMMs now.
Software Support, or Why it Took So Long
The other big question is of course why A1100 took so long. The answer to that is actually pretty simple. Some of the building blocks like fine tuned ACPI and PCI Express support for ARM CPUs were not initially adapted to the server world, and AMD needed to wait for those to come along to give A1100 a fighting chance.
Just look at the slide with software support and see the comment "supports ACPI and PCIe". That would look pretty odd on an announcement of an x86 server CPU, but it is relatively new for a 64 bit ARM server environment. You might ask yourself how our Applied X-Gene server worked well with Ubuntu server nine months ago. The X-Gene server ran a specially adapted version of Ubuntu. That is fine as a temporary solution, but unless the modifications go "mainstream linux", each new version must be adapted again to make it work with your server. Costly and time consuming, so AMD went the other way, making sure that the necessary improvements were part of the official Linux kernel.
For the Ubuntu fans: the A1100 runs on top of ubuntu 15.10. According to AMD, it is fully functional but at the moment without support of Canonical.
Facebook
Twitter
RSS
37 Comments
View All Comments
eldakka - Friday, January 15, 2016 - link
With 14 SATA ports, I wonder how this would perform as a ZFS-based NAS server?beginner99 - Friday, January 15, 2016 - link
True but you could just stick an expansion card into a Xeon-D server, if you need the CPU speed.beginner99 - Friday, January 15, 2016 - link
This thing probably sucks but that isn't surprising. I never ever got the micro server hype. It does also not make sense when you can run stuff on VMs on beefier CPUs and get better performance/watt and $.The_Assimilator - Friday, January 15, 2016 - link
"But there is more than meets the eye or we would not bother to write this article."And then at the end:
"So the new AMD SoC has no performance/watt advantage and no price/performance advantage over Intel's offerings."
AMD has failed, again.
Minion4Hire - Friday, January 15, 2016 - link
That's not the end. You have failed to read two entire pages if you think that is the end of the article.duploxxx - Friday, January 15, 2016 - link
no it does not suck. it is based on ARM while it is not fully comparable to a x86 socket.AMD had to release this socket on the default A57 to pave the road for there next gen k12 arm.
With this platform they are able to give initial go for drivers/support etc.
bill.rookard - Friday, January 15, 2016 - link
I would disagree with that comment about performance per watt. In certain fairly common use cases, such as a storage server compared to the C2000 series you would not only have to add a raid card to the Intel setup, but also provide for dual 10gb nic ports. Both of those cards will add both cost and wattage to the total overall system...Xeus32 - Friday, January 15, 2016 - link
Dear Anandtech,I'm very disappointed about this review.
I have from long time a Atom server and the basic concept of power consuming used in the standard review is not right when you are evaluating a system below 50W.
A single hard disk can consume from 5W (if you use low performance , high density disk ex: western digital red 2.5”) to 10W (if you use high performance hard disk).
We need also the RAM that for each bank have a power consumed more or less of 3W.
In my system ( ATOM with 2GB DDR2 RAM, LSI controller and 3 Hard disk 3.5” Raid 5) the power consumed of the only motherboard is around 35W and the hard disks have the same consumption. The power consume of the CPU is reported as 10W.
I don’t want speak about this processor but 40W or 20W is the same thing for me because if we add 4 hard disks to our hypothetical system, the power consumed from the storage is greater than the CPU.
JohanAnandtech - Saturday, January 16, 2016 - link
20W more or less per server node is a lot in a system like the HP Moonshot where have 40+ nodes in a high density system. It means that your 1 KW cluster now needs 1.8 KW.And I do make the point that it less of an issue in a storage rich system and that AMD might have a chance there.
mosu - Friday, January 15, 2016 - link
So an upgrade to A72, 14nm and USB 3.0 or 3.1 with actual SATA and PCI will make a great chip someday, now that the road was opened.Maybe a 16 core A72 will do even better...