By: Doug Siebert (foo.delete@this.bar.bar), May 16, 2007 4:58 pm
Room: Moderated Discussions
Great article, David!
I'd personally be pretty surprised if 8 socket servers don't become commoditized to the extent 4 socket servers are today in a few years.
True the 8 bit wide path in a fully connected system and lack of effective snoop solution will hurt bandwidth heavy workloads, but those are often (but certainly not always) more amenable to parallelization and thus less likely to really benefit from an 8 socket server versus a pair of 4 socket servers.
I think the RAS concerns are overblown, that didn't stop people migrating from mainframes to minis, from minis to Unix servers, and more recently from Unix to x86 Windows and Linux servers. Always there are some apps that really require higher RAS left behind (well I guess minis are pretty much gone except for VMS, but Unix servers grew larger and more reliable to cover that segment)
So while there are certainly some apps that you'll want a mid/high end POWER, IPF or Sparc server for, a lot of them will be able to move to a 32 core 8 socket Opteron system. When there are commodity systems that offer the same or in most cases better performance for less than half the price, you have the opportunity in many cases to increase your RAS by clustering two cheaper lower RAS systems instead of buying one higher RAS system. Those applications already using clustering on Unix for the highest levels of RAS will stay there for the forseeable future, or until beancounters overrule the tech guys and tell them they can get by with cheaper systems because the sales guy promised them the required number of 9s knowing they'd have their commission in the bank long before the new system goes live :)
This success will force Intel to respond. Obviously CSI will be built to handle larger scale systems given it will support IPF as well, but I'll bet Intel has always been planning on crippling it on the x86 side at a level chosen to avoid revenue loss to Opteron while preserving as big of a 'higher end' side as IPF-only as possible. I forget, when is AMD supposed to be introducing the improved HT that handles up to 32 socket systems? (presumably with some sort of directory or vastly improved snooping, along with higher RAS)
This is just another step along the path to IPF being completely squeezed out of the market by the middle of the next decade.
I'd personally be pretty surprised if 8 socket servers don't become commoditized to the extent 4 socket servers are today in a few years.
True the 8 bit wide path in a fully connected system and lack of effective snoop solution will hurt bandwidth heavy workloads, but those are often (but certainly not always) more amenable to parallelization and thus less likely to really benefit from an 8 socket server versus a pair of 4 socket servers.
I think the RAS concerns are overblown, that didn't stop people migrating from mainframes to minis, from minis to Unix servers, and more recently from Unix to x86 Windows and Linux servers. Always there are some apps that really require higher RAS left behind (well I guess minis are pretty much gone except for VMS, but Unix servers grew larger and more reliable to cover that segment)
So while there are certainly some apps that you'll want a mid/high end POWER, IPF or Sparc server for, a lot of them will be able to move to a 32 core 8 socket Opteron system. When there are commodity systems that offer the same or in most cases better performance for less than half the price, you have the opportunity in many cases to increase your RAS by clustering two cheaper lower RAS systems instead of buying one higher RAS system. Those applications already using clustering on Unix for the highest levels of RAS will stay there for the forseeable future, or until beancounters overrule the tech guys and tell them they can get by with cheaper systems because the sales guy promised them the required number of 9s knowing they'd have their commission in the bank long before the new system goes live :)
This success will force Intel to respond. Obviously CSI will be built to handle larger scale systems given it will support IPF as well, but I'll bet Intel has always been planning on crippling it on the x86 side at a level chosen to avoid revenue loss to Opteron while preserving as big of a 'higher end' side as IPF-only as possible. I forget, when is AMD supposed to be introducing the improved HT that handles up to 32 socket systems? (presumably with some sort of directory or vastly improved snooping, along with higher RAS)
This is just another step along the path to IPF being completely squeezed out of the market by the middle of the next decade.
Topic | Posted By | Date |
---|---|---|
Barcelona Article Online | David Kanter | 2007/05/16 03:20 AM |
Barcelona Article Online | PiedPiper | 2007/05/16 05:12 AM |
Yes, I left out a sentence there. Fixed (NT) | David Kanter | 2007/05/16 12:07 PM |
Barcelona Article Online | anonymous | 2007/05/16 06:01 AM |
Barcelona Article Online | Anonymous | 2007/05/16 06:28 PM |
Barcelona Article Online | anonymous | 2007/05/16 07:52 PM |
Barcelona Article Online | Anonymous1 | 2007/05/16 07:08 AM |
Barcelona Article Online | Dean M | 2007/05/16 11:09 AM |
Barcelona Article Online | David Kanter | 2007/05/16 12:38 PM |
Barcelona Article Online | Dean M | 2007/05/16 02:10 PM |
Barcelona Article Online | IntelUser2000 | 2007/05/16 02:59 PM |
Barcelona Article Online | Linus Torvalds | 2007/05/16 03:24 PM |
Barcelona Article Online | David Kanter | 2007/05/16 04:57 PM |
Barcelona Article Online | Michael S | 2007/05/17 05:07 AM |
Barcelona Article Online | IntelUser2000 | 2007/05/18 08:58 PM |
8 socket servers | Doug Siebert | 2007/05/16 04:58 PM |
8 socket servers | Michael S | 2007/05/17 05:20 AM |
8 socket servers | Joe Chang | 2007/05/17 07:38 AM |
8 socket servers | Alex Jones | 2007/05/17 09:35 AM |
8 socket servers | Jose | 2007/05/23 08:23 AM |
8 socket servers | Michael S | 2007/05/23 11:37 AM |
8 socket servers | anonymous | 2007/05/26 03:49 PM |
8 socket servers | Joe Chang | 2007/05/27 01:46 PM |
8 socket servers | Doug Siebert | 2007/05/23 09:56 PM |
8 socket servers | Joe Chang | 2007/05/24 04:33 AM |
8 socket servers | Anonymous | 2007/05/24 11:18 AM |
8 socket servers | Doug Siebert | 2007/05/24 10:47 PM |
8 socket servers | Linus Torvalds | 2007/05/25 10:35 AM |
8 socket servers | Nick | 2007/05/25 02:29 AM |
Performance estimation seems odd | Hotar | 2007/05/17 01:54 AM |
Performance estimation seems odd | David Kanter | 2007/05/17 08:38 AM |
microops vs macroops on page 4 | Peter Lund | 2007/05/17 12:04 PM |
microops vs macroops on page 4 | David Kanter | 2007/05/21 04:51 PM |
microops vs macroops on page 4 | EduardoS | 2007/05/21 05:42 PM |
microops vs macroops on page 4 | dess | 2007/05/21 07:00 PM |
Barcelona Article Online | Peter Lund | 2007/05/17 12:25 PM |
macro-op vs. micro-op | dess | 2007/05/21 07:24 AM |
macro-op vs. micro-op | David Kanter | 2007/05/21 04:38 PM |
macro-op vs. micro-op | dess | 2007/05/21 06:15 PM |
macro-op vs. micro-op | David Kanter | 2007/05/22 12:11 AM |
macro-op vs. micro-op | dess | 2007/05/22 03:56 AM |
macro-op vs. micro-op | Gipsel | 2007/05/22 05:05 AM |
macro-op vs. micro-op | dess | 2007/05/22 05:52 AM |
macro-op vs. micro-op | anonymous | 2007/05/22 06:14 AM |
macro-op vs. micro-op | dess | 2007/05/22 06:44 AM |
macro-op vs. micro-op | EduardoS | 2007/05/22 02:19 PM |
macro-op vs. micro-op | dess | 2007/05/24 08:52 AM |
Stop comparing apples to oranges | EduardoS | 2007/05/22 02:30 PM |
Stop comparing apples to oranges | dess | 2007/05/22 04:09 PM |
Stop comparing apples to oranges | dess | 2007/05/22 04:30 PM |
Stop comparing apples to oranges | EduardoS | 2007/05/22 04:31 PM |
Stop comparing... apples to oranges? | dess | 2007/05/24 09:30 AM |
Stop comparing apples to oranges | anonymous | 2007/05/22 08:12 PM |
Stop comparing apples to oranges | EduardoS | 2007/05/23 02:50 PM |
macro-op vs. micro-op | anonymous | 2007/05/22 06:08 AM |
macro-op vs. micro-op | dess | 2007/05/22 06:40 AM |
macro-op vs. micro-op | anonymous | 2007/05/22 06:48 AM |
macro-op vs. micro-op | dess | 2007/05/21 08:30 PM |
macro-op vs. micro-op | anonymous | 2007/05/22 06:44 AM |
macro-op vs. micro-op | dess | 2007/05/24 09:38 AM |
macro-op vs. micro-op | Michael S | 2007/05/22 05:26 AM |