Prof. José M. F. Moura at Carnegie Mellon University got a huge amount of payment for his patented technology last year (2016). He was actively contributing to IEEE, and this year he is running for the title IEEE President:
On February 17, 2016, CMU announced with Marvell a record $750 Million settlement on infringement of two of my patents (co-inventor, my former PhD student Alek Kavcic), find details here or here. The patented technology is in over 3 Billion chips in the diskdrives of over 60% computers sold in the last 12 years or so.
SPIRAL is a new generation of design tools.
With the growing complexity and diversity of computer platforms, the design of high-performance software implementations of digital signal processing (DSP) algorithms has become an increasingly more difficult task. When high performance is an issue, the designers have to fine tune software implementations to utilize the specific features of the target platform. This requires expert knowledge in both algorithm development and computer architecture, and the hand-coding of the implementations becomes a tedious and time-consuming task. Furthermore, the ever-changing hardware and compiler technology requires frequent re-implementation, since the platforms are often changed or upgraded. These problems are tackled by what are commonly known as automatic software performance tuning systems, which are automatically adapting software implementations to a wide range of platforms. Because of the complexity of the problem, most performance tuning systems implement only basic functions that are used as building blocks in more complex applications. There is a growing interest in automatic tuning of DSP algorithms since DSP applications typically require high-performance algorithm implementations. Many DSP applications include digital filtering and wavelet-based processing, and the number of new applications is increasing fast. In our work, we develop SPIRAL, a generator of Libraries of tuned software implementations of fast DSP transforms. SPIRAL generates fast code for a number of different transforms, including the discrete Fourier transform, the discrete trigonometric transforms, i.e., the discrete cosine and discrete sine transforms (all their sixteen variants), the Walsh-Hadamard transform, the wavelet transform, as well as other digital signal processing kernels like filtering. SPIRAL is now looking also at reconfigurable hardware (e.g., FPGAs) implementations, as well as joint harwdare/ software implementations, of signal processing algorithms.
The work in SPIRAL is featured in a paper in the February 2005 IEEE Proceedings Special Issue on Performance Tuning.
Source: https://users.ece.cmu.edu/~moura/algesignal.html#spiralinfo
http://www.spiralgen.com/spiral-technology/