Energy costs nowadays represent a significant share of the total costs of ownership of High Performance Computing (HPC) systems. In this paper we provide an overview on different aspects of energy efficiency measurement and optimization. This includes metrics that define energy efficiency and a description of common power and energy measurement tools. We discuss performance measurement and analysis suites that use these tools and provide users the possibility to analyze energy efficiency weaknesses in their code. We also demonstrate how the obtained power and performance data can be used to locate inefficient resource usage or to create a model to predict optimal operation points. We further present interfaces in these suites that allow an automated tuning for energy efficiency and how these interfaces are used. We finally discuss how a hard power limit will change our view on energy efficient HPC in the future.
1 December 2006 in ACM Transactions on Architecture and Code Optimization
Several programming languages guarantee that array subscripts are checked to ensure they are within the bounds of the array. While this guarantee improves the correctness and security of array-based code, it adds overhead to array references. This has been an obstacle to using higher-level languages, such as Java, for high-performance parallel computing, where the language specification requires that all array accesses must be checked to ensure they are within bounds. This is because, in practice, array-bounds checking in scientific applications may increase execution time by more than a factor of 2. Previous research has explored optimizations to statically eliminate bounds checks, but the dynamic nature of many scientific codes makes this difficult or impossible. Our approach is, instead, to create a compiler and operating system infrastructure that does not generate explicit bounds checks. It instead places arrays inside of Index Confinement Regions (ICRs), which are large, isolated, mostly unmapped virtual memory regions. Any array reference outside of its bounds will cause a protection violation; this provides implicit bounds checking. Our results show that when applying this infrastructure to high-performance computing programs written in Java, the overhead of bounds checking relative to a program with no bounds checks is reduced from an average of 63% to an average of 9%.