Computer Architecture

Processors stall on OLTP workloads about half the time--almost no ?matter what you do
MitchAlsup <MitchAlsup(a)aol.com> wrote: We saw this develop with the interplay between Alpha and HP, Alpha taking the speed deamon approach, while HP took the brainiac approach. Alpha had more layers of cache with thinner slices at each level. HP tried to avoid even the second level of cache (7600 Snak... 23 Apr 2010 20:37

Processors stall on OLTP workloads about half the time--almost nomatter what you do
I have several times referred to a paper by Patterson, et al, circa 1996 that concludes that most architectural cleverness is useless for OLTP workloads, but I have been unable to deliver a specific citation. It turns out that Patterson is the second author and the technical report from Berkeley is from 1998: ... 23 Apr 2010 20:37

c.arch dinner in silicon valley next week?
It seems like the ash clouds are settling, which means that I'll probably get to attend my usual conference near Monterey in the second half of next week. I'm flying in to SFO on saturday and intend to hang around until Wed morning; anyone want to meet up for dinner one of those preceding days, like Tue even... 26 Apr 2010 09:07

c.arch dinner in silicon valley next week?
Andy "Krazy" Glew wrote: I'm driving down with a friend on Tuesday, staying in SF Tuesday night. Tuesday a likelihood. Both are OK, we'll be in the area until leaving for Monterey Wed morning. Terje If Monday looks better, I might be able to change plans. PS I'm taking the train back on Friday... 23 Apr 2010 20:37

Processors stall on OLTP workloads about half the time--almost nomatter what you do
On Fri, 23 Apr 2010 08:50:33 +0100, Quadibloc <jsavard(a)ecn.ab.ca> wrote: Hmm. While I think that maximal monothreaded performance is what is generally needed But that would be "per core" and there's no reason not to offer 4 or 8 cores on a single chip. In the consumer space, existing software will use ... 23 Apr 2010 20:36

Processors stall on OLTP workloads about half the time--almostno matter what you do
Anne & Lynn Wheeler wrote: Robert Myers <rbmyersusa(a)gmail.com> writes: I had thought the idea of having lots of threads was precisely to get the memory requests out. You start a thread, get some memory requests out, and let it stall, because it's going to stall, anyway. Cache size and bandwidth ... 25 Apr 2010 22:17

Processors stall on OLTP workloads about half the time--almost no matter what you do
Robert Myers <rbmyersusa(a)gmail.com> writes: I had thought the idea of having lots of threads was precisely to get the memory requests out. You start a thread, get some memory requests out, and let it stall, because it's going to stall, anyway. Cache size and bandwidth and memory bandwidth are another ... 1 May 2010 08:42

Processors stall on OLTP workloads about half the time--almostno matter what you do
On 4/22/2010 3:04 AM, Morten Reistad wrote: In article<86666a83-4bed-472c-aacd-9fc6ef47e9e6(a)k33g2000yqc.googlegroups.com>, MitchAlsup<MitchAlsup(a)aol.com> wrote: On Apr 21, 11:02 am, Robert Myers<rbmyers...(a)gmail.com> wrote: Even though the paper distinguishes between technical and commercial workl... 27 Apr 2010 13:18

Processors stall on OLTP workloads about half the time--almost no matter what you do
I like interrupt coalescing - when it is done well anyway - when it is done badly, it does rather nasty things to latency. And I've seen a small, but measurable number of folks who want very, very low latency on their "online transactions." This write-up is probably old enough to be off on the syntax/constants (a... 2 May 2010 23:02

Looking for Sponsorship
Poker Player ( intermediate )Interests:Sponsorship Information. 1-5 year contract. This contract will let us represent you as our sponsor. We represent you on and off the road your comapany and logos on the bus and any telvised final table gear you may have us wear as we tour casino's and play championship eve... 20 Apr 2010 15:40