Application Performance

The Black-Scholes model was used to calculate a theoretical call and put price using the five key determinants of an option's price: stock price, strike price, volatility, time to expiration, and short-term (risk free) interest rate.

The workload is an execution of approximately 300,000 iterations of Monte Carlo simulation using the Black-Scholes basic option pricing formula in Microsoft Excel 2010. In addition, the workload uses Excel lookup functions to compare the put price from the model with the historical market price for 50,000 rows to understand the convergence. The input file is a ~70 MB spreadsheet.

Unfortunately, AMD processors never perform very well in Excel and we found that the AMD E-350 was 31% slower than the Atom 330, which largely contradicts what we have seen in the previous tests.

Our custom WinRAR test is broken into two different tests. One measures the time it takes to compress a single large audio/video file, while the other measures how long it takes to compress a small program containing multiple files.

Both the AMD E-350 and Intel Atom 330 processors are considerably slower than the more power hungry Core i3 mobile and Phenom II X2 desktop processors in this test. When compared to the Atom 330, the AMD E-350 was 11% faster in our large single file test and 22% faster in the multiple file program test.

Using an 88-megapixel image in Adobe Photoshop CS5, we applied the radial blur filter and measured the time it took each processor to complete the task. The AMD E-350 again appears to be at a disadvantage here, as we found it to be 14% slower than the Atom 330.