Guest Editors:

Franz Franchetti
Jose M. F. Moura
David A. Padua
Jack Dongarra

Special Issue Papers

Scanning the Issue

By F. Franchetti, J. M. F. Moura, D. A. Padua, and J. Dongarra

Machine Learning in Compiler Optimization

By Z. Wang and M. O’Boyle

This paper discusses machine-learning-based compilation techniques, which have become mainstream.

Domain-Specific Optimization and Generation of High-Performance GPU Code for Stencil Computations

By P. S. Rawat, M. Vaidya, A. Sukumaran-Rajam, M. Ravishankar, V. Grover, A. Rountev, L.-N. Pouchet, and P. Sadayappan

This paper discusses the compilation of a domain-specific language used to target graphics processors.

The Sparse Polyhedral Framework: Composing Compiler-Generated Inspector-Executor Code

By M. M. Strout, M. Hall, and C. Olschanowsky

This paper discusses an inspector–executor approach for sparse polyhedral programs.

SPIRAL: Extreme Performance Portability

By F. Franchetti, T. M. Low, D. T. Popovici, R. M. Veras, D. G. Spampinato, J. R. Johnson, M. Püschel, J. C. Hoe, and J. M. F. Moura

This paper provides an end-to-end discussion of the SPIRAL system, its domain-specific languages, and code generation techniques.

Automating the Development of High-Performance Multigrid Solvers

By C. Schmitt, S. Kronawitter, F. Hannig, J. Teich, and C. Lengauer

This paper discusses domain-specific languages and code generation targeting stencil computations in the context of the German ExaStencil effort.

The Long and Winding Road Toward Efficient High-Performance Computing

By W. Jalby, D. Kuck, A. D. Malony, M. Masella, A. Mazouz, and M. Popov

This paper provides a mainly European perspective on the road to ExaScale.

The Ongoing Evolution of OpenMP

By B. R. de Supinski, T. R. W. Scogland, A. Duran, M. Klemm, S. Mateo Bellido, S. L. Olivier, C. Terboven, and T. G. Mattson

This paper discusses the OpenMP framework’s past, current status, and anticipated future in the face of the evolving CPU and accelerator landscape.

Navigating the Landscape for Real-Time Localization and Mapping for Robotics and Virtual and Augmented Reality

By S. Saeedi, B. Bodin, H. Wagstaff, A. Nisbet, L. Nardi, J. Mawer, N. Melot, O. Palomar, E. Vespa, T. Spink, C. Gorgovan, A. Webb, J. Clarkson, E. Tomusk, T. Debrunner, K. Kaszyk, P. Gonzalez-De-Aledo, A. Rodchenko, G. Riley, C. Kotselidis, B. Franke, M. F. P. O’Boyle, A. J. Davison, P. H. J. Kelly, M. Luján, and S. Furber

This paper shows for the important example of simultaneous localization and mapping (SLAM) the compilation and tuning techniques necessary to reach high performance.

Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators

By J. Dongarra, M. Gates, J. Kurzak, P. Luszczek, and Y. M. Tsai

This paper discusses automatic performance tuning for small linear algebra kernels, which are important building blocks in many engineering and science applications.

Japanese Autotuning Research: Autotuning Languages and FFT

By T. Katagiri and D. Takahashi

This paper discusses the Japanese automatic performance tuning research landscape.

Autotuning in High-Performance Computing Applications

By P. Balaprakash, J. Dongarra, T. Gamblin, M. Hall, J. K. Hollingsworth, B. Norris, and R. Vuduc

This paper discusses how to make automatic performance tuning a standard technique for high-performance computing applications.


Point of View