Saturday, September 22, 2007

Intel unloads a new salvo

I just stumbled along this link:

Looks like the FX platform may not be so great after all...

It would be nice if AMD had answer for this.

Friday, September 14, 2007

Smoke and mirrors

It's disappointing that AMD feels the need to mislead the market place into thinking that something has been realeased when it really hasn't.

Take for example the 2360 SE and the 2350 parts.

Shortly after the announcement I poked some of my favorite sites that carry such things - to no avail. In fact, one site indicates that the 2350 is ETA: Past Due and that there are -4 parts in stock.


For a company that has in the past been critised for difficulty in delivering - this doesn't help any.

I have also noticed that Dell carries high efficiency quad core chip propoganda on their site, but none of the servers can be configured with any of the new parts.

I don't know about anyone else but I would prefer that a launch date actually mean something.

Sadly, I just purchased two dual quad core E53XX servers from Dell.

Barcelona Benchmarks

An interesting write up recently in tech report on Barcelona...

The bottom line is this - in the highly business oriented benchmark SPECjbb2005 the opterons pulled ahead of their competing Intel parts. In some of the scientific benchmarks such as MyriMatch the Opteron also performed well. However when it comes to raw compute the chips don't perform that well.

Another item of interest is the single threaded performance of the 2300 parts in benchmarks such as POV-Ray. The new chips actually finish last among Intel AND previous generation AMD parts.

This tells me that the plumbing in the new chips is exceptional. The raw core performance seems to be lagging, but the internals must be able to handle IO very, very well to keep pace with Intel.

Overall - they still lag far behind Intel based on these test benchmarks.

For those of us that game this is not good news. As I wrote a while ago gaming performance is largely dictated by the performance of core and does not see much benefit from multiple processors. If the FX-90's don't see a significant boost on raw core performance we will find that most of games will perform worse - not better than they do now.

Wednesday, September 5, 2007


For anyone that is actually still subscribed to this blog... lol you know I've taken a bit of a vacation.

Here are a few updates!

When I built this machine last year I had expected that I would be upgrading to two 8 core processors. This unfortunately has not happened due to AMD seriously slipping on their delivery schedule for the Phenom line. At the moment it looks as if there is going to be a serious wait for those of us who wish to take advantage of 8 cores. I'm really disappointed by these turn of events. So much for the 4x4 becoming a "platform". More information about the release schedule is available here. I think I'm tempted to wait for the FX-91 to launch. I can't really see the benefits of taking a step back in MHz. Of course, clock is not everything but...

When I make the move to 8 cores it will be time for a disk upgrade as well. One of the issues that the current machine faces is that a large number of processes causes excessive I/O and effectively limits the capacity of the machine. Vista indicates a ling queue length. A good example of this is running 3 or four virtual machines in addition to "normal" development tasks. I've been exploring options. At the moment, out and deep come to mind. I'm thinking about adding another array and possibly trying a 3 disk RAID 0 to see if there is better performance. I'm not convinced that will alleviate queing issues though so it might be worth test (how?).

The drivers for the 8800 are now WHQL, there have not been too many issues with it. Upgrading using NVidia's package has been easy. I would not recommend using Windows update to upgrade the NVidia drivers, especially the storage drivers as I have had issues in the past. There is a new board package for the 680a although I'm really not too interested in "upgrading" anything that has to do with the RAID array. As they say "If it ain't broke don't fix it".

Performance monitoring still does not work correctly and I have no idea why.

The recently reported bug involving decreased network performance while playing audio under Vista affects this machine. It's really bad too. When transfering Multi-GB virtual machine images over the network I can get 107 MB/s peak and appx. 90 MB/s average between another Dell server with a RAID 0 array. The same transfer with audio playing will reduce the transfer speed to appx. 16 MB/s average. Terrible.

Overall the system continues to run well and continue to meet and exceed the demands that I place on it.

I'm still on the fence if I will move to the AMD chipset. We'll see if they are able to provide a compelling reason to make a move. Although, it looks like the 680a is largely dead. NVidia has already released a new version of the 680i chipset with more features. To be fair I'm not sure what they could add to the 680a besides SLI drivers that work!