A New Programming Language For Image-processing Algorithms

Halide is a new programming language designed to make it easier to write high-performance image processing code on modern machines. Its current front end is an embedding in C++. Hardware targets include x86-64/SSE, ARM v7/NEON, and CUDA. Created by researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) Halide was used to rewrite several common image-processing algorithms whose performance had already been optimized by seasoned programmers. The Halide versions were typically about one-third as long but offered significant performance gains — two-, three-, or even six-fold speedups. In one instance, the Halide program was actually longer than the original — but the speedup was 70-fold. The paper is available here and the source will be posted within the next couple of days on github and the projects home here.

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

KINGSTAR Soft Motion - Replace Your Motion Control Hardware with Precision-Performance Software in Half the Cost & Time

KINGSTAR Soft Motion - Replace Your Motion Control Hardware with Precision-Performance Software in Half the Cost & Time

KINGSTAR Soft Motion is an open and standards-based, real-time software-only solution that streamlines motion control automation. Soft Motion runs directly on the 64-bit PC, uses the NIC card for I/O, and uses the powerful EtherCAT protocol to free you from the shackles of proprietary and costly hardware. With Soft Motion, motion control engineers can design, develop and integrate real-time PC-based machine controllers in a "plug-and-play" environment for consolidated, inexpensive and scalable motion control.