Since 1986 - Covering the Fastest Computers in the World and the People Who Run Them

Language Flags

Author » Michael Wolfe

Michael Wolfe has developed compilers for over 30 years in both academia and industry, and is now a senior compiler engineer at The Portland Group, Inc.

The Heterogeneous Programming Jungle

Mar 19, 2012 |

<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/green_mb.bmp” alt=”” width=”109″ height=”91″ />There are several approaches being developed to program heterogeneous systems, but none of them have proven to successfully address the real goal. This article will discuss a range of potentially interesting heterogeneous systems for high performance computing, why programming them is hard, and why developing a high level programming model is even harder.

Read more…

Arm Yourselves for Exascale, Part 1

Nov 9, 2011 |

Today’s largest HPC systems are dominated by processors using two instruction sets, x86 and Power, controlled by three vendors: Intel, AMD and IBM. These processors have been typically designed for the highest single thread performance, but suffer from high cost and power demand. As we build even larger and higher performance systems moving towards exascale, we might explore other avenues for delivering cost-efficient compute performance and reducing the power consumed by these systems.

Read more…

Compilers and More: Exascale Programming Requirements

Apr 14, 2011 |

In his third column on programming for exascale systems, Michael Wolfe shares his views on what programming at the exascale level is likely to require, and how we can get there from where we are today. He explains that it will take some work, but it’s not a wholesale rewrite of 50 years of high performance expertise.

Read more…

Compilers and More: Programming at Exascale

Mar 8, 2011 |

There are at least two ways exascale computing can go, as exemplified by the top two systems on the latest TOP500 list: Tianhe-1A and Jaguar. The Chinese Tianhe-1A uses 14,000 Intel multicore processors with 7,000 NVIDIA Fermi GPUs as compute accelerators, whereas the American Jaguar Cray XT-5 uses 35,000 AMD 6-core processors.

Read more…

Compilers and More: Hardware/Software Codesign

Nov 2, 2010 |

There is a growing feeling that merely taking the latest processor offerings from Intel, AMD or IBM will not get us to exascale in a reasonable time frame, cost budget, and power constraint. One avenue to explore is designing and building more specialized systems, aimed at the types of problems seen in HPC, or at least at the problems seen in some important subset of HPC. Of course, such a strategy loses the advantages we’ve enjoyed over the past two decades of commoditization in HPC; however, a more special purpose design may be wise, or necessary.

Read more…

Compilers and More: Knights Ferry Versus Fermi

Aug 5, 2010 |

In May, Intel announced the Many Integrated Core (MIC) architecture, with a development kit codenamed Knights Ferry. NVIDIA has announced and started to deliver its next-generation architecture, Fermi. PGI’s Michael Wolfe presents an in-depth comparison of the two designs.

Read more…

Compilers and More: A Computing Larrabee

Oct 29, 2009 |

Larrabee looks an awful lot like an x86 cluster node; anyone who has experience building HPC clusters has pretty good intuition about the design tradeoffs that make for a balanced and effective system. So it can be interesting to explore the Larrabee architecture, to look at the design choices Intel made, and what alternatives they might have considered or might consider in the future.

Read more…

Compilers and More: OpenCL Promises and Potential

Sep 10, 2009 |

OpenCL was introduced with great fanfare and promise. Given all the hype, what can we expect from OpenCL? Is it really simple? Is it portable? Will it replace other parallel programming models? Michael Wolfe addresses these questions and more.

Read more…

Compilers and More: A GPU and Accelerator Programming Model

Dec 9, 2008 |

If you are familiar with current approaches to programming accelerators, you are either discomforted by the complexities, or excited at the levels of control you can get. Can we come up with a different model of GPU and accelerator programming — a model that allows HPC programmers to focus on domain science instead of on computer science?

Read more…

Compilers and More: Optimizing GPU Kernels

Oct 30, 2008 |

Michael Wolfe’s latest column focuses on programming the GPU, taking a look at a simple single-precision matrix multiplication, equivalent to the BLAS SGEMM routine.

Read more…