A Technique for Finding Optimal Program Launch Parameters Targeting Manycore Accelerators

by   Alexander Brandt, et al.
Western University

In this paper, we present a new technique to dynamically determine the values of program parameters in order to optimize the performance of a multithreaded program P. To be precise, we describe a novel technique to statically build another program, say, R, that can dynamically determine the optimal values of program parameters to yield the best program performance for P given values for its data and hardware parameters. While this technique can be applied to parallel programs in general, we are particularly interested in programs targeting manycore accelerators. Our technique has successfully been employed for GPU kernels using the MWP-CWP performance model for CUDA.


page 1

page 2

page 3

page 4


KLARAPTOR: A Tool for Dynamically Finding Optimal Kernel Launch Parameters Targeting CUDA Programs

In this paper we present KLARAPTOR (Kernel LAunch parameters RAtional Pr...

Comprehensive Optimization of Parametric Kernels for Graphics Processing Units

This work deals with the optimization of computer programs targeting Gra...

Cross-Platform Performance Portability Using Highly Parametrized SYCL Kernels

Over recent years heterogeneous systems have become more prevalent acros...

Auto-Tuning High-Performance Programs Using Model Checking in Promela

The paper combines research approaches that traditionally have been disj...

A Learned Performance Model for Tensor Processing Units

Accurate hardware performance models are critical to efficient code gene...

Extracting Clean Performance Models from Tainted Programs

Performance models are well-known instruments to understand the scaling ...

Web-based Structural Identifiability Analyzer

Parameter identifiability describes whether, for a given differential mo...

Please sign up or login with your details

Forgot password? Click here to reset