Topical perspective on massive threading and parallelism

Unquestionably computer architectures have undergone a recent and noteworthy paradigm shift that now delivers multi- and many-core systems with tens to many thousands of concurrent hardware processing elements per workstation or supercomputer node. GPGPU (General Purpose Graphics Processor Unit) technology in particular has attracted significant attention as new software development capabilities, namely CUDA (Compute Unified Device Architecture) and OpenCL™, have made it possible for students as well as small and large research organizations to achieve excellent speedup for many applications over more conventional computing architectures. The current scientific literature reflects this shift with numerous examples of GPGPU applications that have achieved one, two, and in some special cases, three-orders of magnitude increased computational performance through the use of massive threading to exploit parallelism. Multi-core architectures are also evolving quickly to exploit both massive-threading and massive-parallelism such as the 1.3 million threads Blue Waters supercomputer. The challenge confronting scientists in planning future experimental and theoretical research efforts – be they individual efforts with one computer or collaborative efforts proposing to use the largest supercomputers in the world is how to capitalize on these new massively threaded computational architectures – especially as not all computational problems will scale to massive parallelism. In particular, the costs associated with restructuring software (and potentially redesigning algorithms) to exploit the parallelism of these multi- and many-threaded machines must be considered along with application scalability and lifespan. This perspective is an overview of the current state of threading and parallelize with some insight into the future.

Figure optionsDownload high-quality image (261 K)Download as PowerPoint slideHighlights
• Massively threaded GPU technology is disruptive because it can deliver 10–1000× increased computational performance over conventional technology.
• The scale of massively parallel systems has changed. Instead of using hundreds of processing elements, new architectures hundreds of thousands of processing elements.
• Utilizing new massively parallel systems will likely require a software investment.
• Computation-dependent projects that do not invest in multi-threaded software will not benefit from modern massively parallel hardware risking both stagnation and loss of competitiveness.