Kernel Tuner: A search-optimizing GPU code auto-tuner
نویسندگان
چکیده
منابع مشابه
Towards a Multivariable Auto-tuner
An MIMO auto-tuning method is develop that can be used by a layman of control. The method is based on MIMO identification and robust control design. The identification part delivers process model and model error bounds. The controller design block performs control synthesis, simulation and robust analysis. All steps can be done automatically. The parameters the user needs to enter are minimal a...
متن کاملA Digital Guitar Tuner
The objective of this paper is to understand the critical parameters that need to be addressed while designing a guitar tuner. The focus of the design lies in developing a suitable algorithm to accurately detect the fundamental frequency of a plucked guitar string from its frequency spectrum. A user-friendly graphical interface is developed using Matlab to allow any user to easily tune his guit...
متن کاملSMAT: An Input Adaptive Sparse Matrix-Vector Multiplication Auto-Tuner
Sparse matrix vector multiplication (SpMV) is an important kernel in scientific and engineering applications. The previous optimizations are sparse matrix format specific and expose the choice of the best format to application programmers. In this work we develop an auto-tuning framework to bridge gap between the specific optimized kernels and their general-purpose use. We propose an SpMV autot...
متن کاملA Tuner that Accelerates Parameters
We propose a tuner, suitable for adaptive control and (in its discrete-time version) adaptive filtering applications, that sets the second derivative of the parameter estimates rather than the first derivative as is done in the overwhelming majority of the literature. Comparative stability and performance analyses are presented.
متن کاملA Nelder-Mead Tuner for Svm
Read at your own risk, as this is a working document and has not yet been checked!
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Future Generation Computer Systems
سال: 2019
ISSN: 0167-739X
DOI: 10.1016/j.future.2018.08.004