Harpertown: New 45nm Xeons from Intel
Posted on: 09/17/2007 05:00 AM

Black & Scholes x64 Kernel
In 1973, Black and Scholes developed a model for estimating the value of a stock option, which has been refined over the years to remove several assumptions, thus making techniques based on the model very accurate. Today, financial analysts rely on algorithms based on the Black and Scholes technique to determine the price of a stock option.

This benchmark constitutes of a kernel that implements a derivative of the Black and Scholes technique. The code was developed at SunGard, and utilizes a continuous fraction technique, which is more accurate than the more traditional polynomial approximation technique.

The workload for this benchmark comes in the form of loop iterations internal to the code. The number of steps used in calculating option price, is set to 1e8 (100,000,000) by default. This value can be changed via command line parameter. The number of threads to use can also be specified as a command line parameter.
The reason why the Black & Scholes kernel makes for such a good benchmark is because it is a real world application that is completely scalable. If you have two or thirty-two processors (or cores), it doesn't matter. All that is required is to specify the number of threads and the number of steps and let it run.



The engineers at Intel were saying that the first time they ran the Black & Scholes Kernel on the new Harpertown/Seaburg setup, they thought something was wrong with their binary. It was so much faster than Bensley (with either Clovertown or Woodcrest) that they thought something had to be amiss. After much testing and verification they determined (as I did) that the changes they made to the chipset (snoop filter) and the improvements to the CPU itself (cache, etc) really did make a HUGE difference in this test.

Power Usage



I'm not going to provide too much commentary on the power graphs on subsequent pages because, once you figure out what's going on, they are pretty self explanatory.

"Performance-per-Watt"



The new Harpertown Xeons take advantage of their power managment at idle, and their processing power during the workload to walk away with a pretty solid win in both aspects of this comparison.


Printed from 2CPU.com (http://www.2cpu.com/contentteller.php?ct=articles&action=pages&page=harpertown_new_45nm_xeons_from_intel,6.html)