High Performance Compilers



Polyhedral Optimization of TensorFlow Computation Graphs



We present R-Stream·TF, a polyhedral optimization tool for neural network computations. R-Stream·TF transforms computations performed in a neural network graph into C programs suited to the polyhedral representation and uses R-Stream, a polyhedral compiler, to parallelize and optimize the computations performed in the graph. R-Stream·TF can exploit the optimizations available with R-Stream to generate a highly optimized version of the computation graph, specifically mapped to the targeted architecture. During our experiments, R-Stream·TF was able to automatically reach performance levels close to the hand-optimized implementations, demonstrating its utility in porting neural network computations to parallel architectures.

Article

Automatic Code Generation and Data Management for an Asynchronous Task-based Runtime



Publication Source: 5th Workshop on Extreme-scale Programming Tools (ESPT-2016) at The International Conference for High Performance Computing, Networking, Storage and Analysis (SC16)

Hardware scaling and low-power considerations associated with the quest for exascale and extreme scale computing are driving system designers to consider new runtime and execution models such as the event-driven-task (EDT) models that enable more concurrency and reduce the amount of synchronization. Further, for performance, productivity, and code sustainability reasons, there is an increasing demand for autoparallelizing compiler technologies to automatically produce code for EDT-based runtimes. However achieving scalable performance in extreme-scale systems with auto-generated codes is a non-trivial challenge. Some of the key requirements that are important for achieving good scalable performance across many EDT-based systems are:  (1) scalable dynamic creation of task-dependence graph and spawning of tasks, (2) scalable creation and management of data and communications, and (3) dynamic scheduling of tasks and movement of data for scalable asynchronous execution. In this paper, we develop capabilities within R-Stream - an automatic source-to-source optimization compiler - for automatic generation and optimization of code and data management targeted towards Open Community Runtime (OCR) - an exascale-ready asynchronous task-based runtime. We demonstrate the effectiveness of our techniques through performance improvements on various benchmarks and proxy application kernels that are relevant to the extreme-scale computing community.
Article

Report of the 2014 Runtime Systems Summit



Publication Source: U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research (ASCR)

This report summarized runtime system challenges for exascale computing, that follow from the fundamental challenges for exascale systems. Some of the key exascale challenges that pertain to runtime systems include parallelism, energy efficiency, memory hierarchies, data movement, heterogeneous processors and memories, resilience, performance variability, dynamic resource allocation, performance portability, and interoperability with legacy code. In addition to summarizing these challenges, the report also outlined different approaches to addressing these significant challenges that have been pursued by research projects in the DOE-sponsored X-Stack and OS/R programs. It also included a chapter on deployment opportunities for vendors and government labs to build on the research results from these projects.
Article

Report of the 2014 Programming Models & Environments Summit



Publication Source: U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research (ASCR)

Programming models and environments play the essential roles in high performance computing of enabling the conception, design, implementation and execution of science and engineering application codes. This report presents the topics discussed and results from the 2014 DOE Office of Science Advanced Scientific Computing Research (ASCR) Programming Models & Environments Summit, and subsequent discussions among the summit participants and contributors to topics in this report.
Article

Polyhedral Compilation for Energy Efficiency



Publication Source: 2016 IEEE High Performance Extreme Computing Conference (HPEC '16), Waltham, MA, USA.

In the last decade, the scope of software optimizations expanded to encompass energy consumption on top of the classical runtime minimization objective. In that context, several optimizations have been developed to improve the software energy efficiency. However, these optimizations commonly rely on long profiling steps and are often implemented as unstable runtime systems, which limits their applicability. We propose in this paper a new energy model and two associated energy optimizations that can be performed at compilation time, without having to profile the compiled programs. The model predicts the energy consumption of programs at compilation time using the precise software representation available in the polyhedral model. The energy model is then used at the core of two compiler optimizations to generate more efficient programs. The model and the two optimizations have been implemented in the R-Stream compiler.
Article

1 2 3 7