SUGI 28: An Inside Look at Version 9 and 9.1 Threaded Base SAS(r) Procedures
نویسنده
چکیده
This paper looks at the changes in key SAS Base procedures which now incorporate threading to achieve significant performance improvements on SMP architectures. The paper is relevant to the following SAS procedures: SORT, SUMMARY, MEANS, TABULATE, REPORT and SQL. We look at software scalability in general and specifically how threading has been utilized in these procedures to enhance scalability. Sample test plots illustrate how threading can reduce the real-time to completion. We also cover the new system and procedure options that pertain to threading such as THREADS and CPUCOUNT. In addition, we cover guidelines regarding utility I/O configuration that will help optimize scalability and discuss the new startup parameter UTILLOC.
منابع مشابه
SUGI 28: Developing Client/Server Applications to Maximize SAS 9 Parallel Capabilities
Parallel SAS processes, multiple threads within a single SAS process, parallel SAS servers, distributed computing, grid computing, cluster computing – how might all of these choices affect the way that you develop your client/server SAS applications? This paper will address some of these areas and what you should understand when you develop or run client/server SAS applications in these environ...
متن کاملSUGI 27: Up and Out: Where We're Going with Scalability in SAS(r) Version 9
This paper gives an overview of the ways that SAS is addressing performance through scalability in SAS Version 9. Scalability features have been implemented in many areas of SAS Version 9 to allow your applications to scale up and scale out. These include: • Multi-Process (MP) CONNECT, • the Scalable Performance Data Engine (SPDE engine), • certain SAS/ACCESS engines, • several scalable SAS pro...
متن کاملSUGI 27: SAS(r) Meets Big Iron: High Performance Computing in SAS(r) Analytical Procedures
Version 9 targets the heavy-duty analytic procedures in SAS® for high performance computing enhancements. These enhancements encompass both algorithmic improvements and modifications to exploit multiprocessor hardware. This paper provides a survey of this development and the performance gains obtained in several procedures in SAS/STAT and Enterprise Miner. Some general scalability issues are ...
متن کاملSUGI 28: Smoothing with SAS(r) PROC MIXED
Mixed models are an extension of regression models that allows for incorporation of random effects. The application of mixed-effects models to practical data analysis has greatly expanded with consequent development of theory and computer software. It also turns out that mixed models are closely related to smoothing. Nonparametric regression models, especially the general smoothing spline model...
متن کاملSUGI 27: A SAS(r) Application for Measuring Efficiency and Productivity of Decision Making Units
In the last two decades many authors have developed techniques to measure the efficiency of Decision Making Units in a way consistent with the underlying economic theory of optimization behavior. The model frequently used is Data Envelopment Analysis (DEA) which initially developed by Charnes, Cooper and Rhodes (1978). Using such as efficiency method over two consecutive periods, one can natura...
متن کامل