Jump To:
Leopard Sample Code: Performance
Current Intel and PowerPC processors include 128-bit vector engines to perform single-instruction multiple-data (SIMD) operations. These vector engines offer tremendous speed advantages, especially for highly parallel operations such as processing audio, graphics, or video. Developers can use these vector engines directly or take advantage of the functionality offered by the Accelerate framework.

Document Descriptions
On Off
Display

Sort by
Title
Sorted by
Date
SIMD Primer (HTML) (DMG) (ZIP)
Introduction to using SIMD/SSE
2008-06-06
vDSP Examples (HTML) (DMG) (ZIP)
vDSP sample code
2007-05-10
Test64BitMultiprec (HTML) (DMG) (ZIP)
Implements (PPC) A*Y+B where A & B are arrays of 64-bit words and Y is a 64-bit integer
2006-06-09
dist_fft (HTML) (DMG) (ZIP)
Gigaelement FFTs on Apple G5 clusters
2004-08-23
VelEng FFT (HTML) (DMG) (ZIP)
G4 Velocity Engine implementation of Fast Fourier Transform (FFT) and associated convolution/correlation routines.
2003-01-14
VelEng Multiprecision (HTML) (DMG) (ZIP)
An implementation of arbitrary precision arithmetic using the PowerPC Velocity-Engine (G4) vector instructions.
2003-01-14
VelEng Wavelet (HTML) (DMG) (ZIP)
This demonstrates a Velocity Engine (G4) implementation of wavelet processing of color images
2003-01-14