VSI/Pro® is the premier math library for signal and image processing on embedded systems. VSI/Pro is fully compliant with the VSIPL (Vector, Signal, and Image Processing Library) standard, as set forth by the VSIPL Forum and now an official Object Management Group (OMG) specification. VSIPL is an open standard that provides an API (Application Programming Interface) for a library of scalar, vector, linear algebra, matrix, and signal processing functions (FFT, Window, Filter, and Convolution) targeted toward High Performance Embedded Computing (HPEC).
VSI/Pro provides excellent performance optimization for the complete range of DSP applications including these platforms:
- PowerPC®/Altivec (e600/e6500/CorIQ) with VxWorks (GCC and DIAB compilers), x86/SSE, and x86/AVX architectures (both 32-bit and 64-bit).
- NVIDIA CUDA for x86-64 systems running Linux.
Key features include:
- Portable, Open standard: VSI/Pro provides a portable, open-standard, high performance out-of-the-box solution that accelerates the development of signal and image processing applications and virtually eliminates the complexities of hand tuning for specific hardware/operating system configurations.
- Signal Processing and Beyond: VSI/Pro supports all functions defined by the VSIPL 1.4 Core Profile plus additional signal and image processing functions making it the most complete and compliant implementation of VSIPL available, with well over 1,000 supported functions.
Based on the VSIPL specification, the library supports a wide range of signal processing and linear system functions including 1D, 2D and 3D FFTs, 1-D and 2-D convolutions and correlations, both FIR and IIR filters and windowing functions (Hanning, Chebyshev, Blackman and Kaiser). Linear algebra support includes vector, matrix-to-vector, and matrix-to-matrix operations.
- Image Extensions: For image processing applications, VSI/Pro offers a set of functions that support high performance image processing on bit images of a number of precisions.
- Performance Oriented and Portable: As a rule of thumb, our highly optimized SIMD (Altivec/SSE) implementations provide a factor of two to eight times performance boost compared to non-SIMD implementations written in ANSI C. RunTime Computing supports standard operating systems: Linux and WindRiver VxWorks, and supports programs written in GCC/G++ on both platforms, as well as the Diab compiler suite for VxWorks on PowerPC. VSI/Pro provides thread-safety features (the de facto MT-1 model) in a number of its release configurations including the VxWorks PPC processor configurations.
- Field Proven: VSI/Pro has been deployed in HPEC applications for over 20 years and still going strong.