SaaS data loss: The problem you didn’t know you had
SeaMicro servers ahoy!
Coming a bit sooner will be a version of SeaMicro's microserver motherboard that plugs into its SM10000-EX chassis launched in January. That was the version of the SeaMicro box that sported Intel's "Sandy Bridge" Xeon E3-1200 v1 processors.
The Opteron-based mobo for the SeaMicro microserver chassis
When AMD acquired SeaMicro for $334m a month later, Papermaster confirmed El Reg's contention that AMD was not trying to get into the server manufacturing business, but was interested in the "Freedom" 3D torus/mesh interconnect at the heart of the SM10000 machines as well as the load balancing and I/O virtualization ASICs that are also part of the system. In any event, AMD has promised that it would get an Opteron-based SeaMicro mobo into the system by the end of the year, and there is it. Exactly what processor AMD is putting in there is unclear, but a variant of the Opteron 3200 seems likely or the Opteron 3300 if this is the chip that comes out the door first from AMD in the Piledriver generation.
The point of all this talk about "ambidextrous systems" and the SeaMicro interconnect is to prove that AMD is looking at using different kinds of processing elements on a die or within systems with peppy interconnects. "It is not a pure feeds and speeds race," Papermaster proclaimed at the end of his keynote. "It is how you bring the solution together. You have to have a systems view." ®
COMMENTS
Re: What does ''emergency schedule handling'' mean
I think this is where the execution queue handler has to be either flushed or interrupted and higher priority instructions than the existing items in the queue executed instead. For example, when a high priority hardware interrupt is triggered it needs to use the processor resources with low latency rather than waiting around for a lower level process to complete.
It used to be "simple" when the persistent process chip state was just a few registers - add a higher number of registers, such as those in the non-core specialist functions, and execution queuing and things get "interesting".
Re: Refinement
The problem is the consumer lines have been pushing sales as of late since the business market is skittish about the economy, and the simple fact is unless you take Windows 8, already shaping up to be one of the most hated Microsoft OSes since WinME, then you are SOL when it comes to anything based on the Bulldozer module design, and this is coming from someone who has built nothing but AMD for years and is typing this on a Thuban.
The problem is every version of Windows OTHER than Windows 8 has a scheduler that treats the BD module as TWO cores, this is wrong. What it is actually is more like a single core with hardware assisted hyperthreading thanks to only having half the FP, why is this bad? Lets say you have two heavy loads..the SMART way to execute on a BD module would be one load on module1/2 and the other on 3/4, that way each load would have its own FP unit. What you will get in any Windows OTHER than Windows 8 is that Windows will schedule BOTH loads on 1/2, which means they are fighting over a single FP unit and the whole thing just drags. This is why in many tests with Win 7 a Thuban or Deneb will beat a BD with the same amount of cores, sometimes even beating BD chips with MORE cores.
Frankly this is a server chip that NEVER should have been released on the desktop, desktop loads are more and more multimedia which is FP city which is exactly what BD is worst at. Instead what they should have done is kept Thuban and Liano for the desktop while working on a new design, pushed out a new Brazos quad for mobile, and kept the BD/PD design for servers where most loads are integer and not FP heavy.
As someone who has been building and selling AMD systems exclusively as well as having my entire family on AMD if they haven't come up with a better design by the time I run out of AM3+ chips I'll have no choice but go Intel, my customers and I are skipping win 8 and there simply is no selling point for BD on Win 7.
Refinement
AMD seems to be refining the cores and processes to where they should have been when BD was released. If Piledriver and Steamroller provide the 15% projected performance goal then AMD is back on track and sales will grow significantly. Trinity was a great performance bump so AMD has learned a few things.
IT infrastructure monitoring strategies
Agentless Backup is Not a Myth
Top 10 SIEM implementer’s checklist
Steps to Take Before Choosing a Business Continuity Partner
Enabling efficient data center monitoring
