Memory Hierarchy Utilization Research Articles

Grain graphs

Average programmers struggle to solve performance problems in OpenMP programs with tasks and parallel for-loops. Existing performance analysis tools visualize OpenMP task performance from the runtime system's perspective where task execution is interleaved with other tasks in an unpredictable order. Problems with OpenMP parallel for-loops are similarly difficult to resolve since tools only visualize aggregate thread-level statistics such as load imbalance without zooming into a per-chunk granularity. The runtime system/threads oriented visualization provides poor support for understanding problems with task and chunk execution time, parallelism, and memory hierarchy utilization, forcing average programmers to rely on experts or use tedious trial-and-error tuning methods for performance. We present grain graphs , a new OpenMP performance analysis method that visualizes grains -- computation performed by a task or a parallel for-loop chunk instance -- and highlights problems such as low parallelism, work inflation and poor parallelization benefit at the grain level. We demonstrate that grain graphs can quickly reveal performance problems that are difficult to detect and characterize in fine detail using existing visualizations in standard OpenMP programs, simplifying OpenMP performance analysis. This enables average programmers to make portable optimizations for poor performing OpenMP programs, reducing pressure on experts and removing the need for tedious trial-and-error tuning.

In-Memory Big Data Management and Processing: A Survey

Growing main memory capacity has fueled the development of in-memory big data management and processing. By eliminating disk I/O bottleneck, it is now possible to support interactive data analytics. However, in-memory systems are much more sensitive to other sources of overhead that do not matter in traditional I/O-bounded disk-based systems. Some issues such as fault-tolerance and consistency are also more challenging to handle in in-memory environment. We are witnessing a revolution in the design of database systems that exploits main memory as its data storage layer. Many of these researches have focused along several dimensions: modern CPU and memory hierarchy utilization, time/space efficiency, parallelism, and concurrency control. In this survey, we aim to provide a thorough review of a wide range of in-memory data management and processing proposals and systems, including both data storage systems and data processing frameworks. We also give a comprehensive presentation of important technology in memory management, and some key factors that need to be considered in order to achieve efficient in-memory data management and processing.

Characterizing task-based OpenMP programs.

Programmers struggle to understand performance of task-based OpenMP programs since profiling tools only report thread-based performance. Performance tuning also requires task-based performance in order to balance per-task memory hierarchy utilization against exposed task parallelism. We provide a cost-effective method to extract detailed task-based performance information from OpenMP programs. We demonstrate the utility of our method by quickly diagnosing performance problems and characterizing exposed task parallelism and per-task instruction profiles of benchmarks in the widely-used Barcelona OpenMP Tasks Suite. Programmers can tune performance faster and understand performance tradeoffs more effectively than existing tools by using our method to characterize task-based performance.

A Methodology for Speeding Up Fast Fourier Transform Focusing on Memory Architecture Utilization

Several SOA (state of the art) self-tuning software libraries exist, such as the Fastest Fourier Transform in the West (FFTW) for fast Fourier transform (FFT). FFT is a highly important kernel and the performance of its software implementations depends on the memory hierarchy's utilization. FFTW minimizes register spills and data cache accesses by finding a schedule that is independent of the number of the registers and of the number of levels and size of the cache, which is a serious drawback. In this paper, a new methodology is presented, achieving improved performance by focusing on memory hierarchy utilization. The proposed methodology has three major advantages. First, the combination of production and consumption of butterflies' results, data reuse, FFT parallelism, symmetries of twiddle factors and also additions by zeros and multiplications by zeros and ones when twiddle factors are zero or one, are fully and simultaneously exploited. Second, the optimal solution is found according to the number of the registers, the data cache sizes, the number of the levels of data cache hierarchy, the main memory page size, the associativity of the data caches and the data cache line sizes, which are also considered simultaneously and not separate. Third, compilation time and source code size are very small compared with FFTW. The proposed methodology achieves performance gain about 40% (speed-up of 1.7) for architectures with small data cache sizes where memory management has a larger effect on performance and 20% (speed-up of 1.25) on average for architectures with large data cache sizes (Pentium) in comparison with FFTW.

Data and computation transformations for multiprocessors

Effective memory hierarchy utilization is critical to the performance of modern multiprocessor architectures. We have developed the first compiler system that fully automatically parallelizes sequential programs and changes the original array layouts to improve memory system performance. Our optimization algorithm consists of two steps. The first step chooses the parallelization and computation assignment such that synchronization and data sharing are minimized. The second step then restructures the layout of the data in the shared address space with an algorithm that is based on a new data transformation framework. We ran our compiler on a set of application programs and measured their performance on the Stanford DASH multiprocessor. Our results show that the compiler can effectively optimize parallelism in conjunction with memory subsystem performance.