Project Report for CS573-Optimization Compilers Resuse Distance Analysis of the Mediabench Suite
نویسنده
چکیده
This is the project report for the Course CS573 Optimization Compilers. The goal of the project is to study the reuse distance of several of the applications included in the MediaBench Suite. 1 Methodology The reuse distance of a memory location or variable of a program is the number of individual memory references between two consecutive references to the same memory location or variable. The importance of the reuse distance analysis comes from the fact that it gives insight to the cache performance of a program for any given cache size without the necessity to conduct detailed cache simulations. A more extensive description of the reuse distance analysis and its bene ts is given in [1]. In order to study the reuse distance of the benchmarks, the ATOM simulator in combination with the code provided by C. Ding for monitoring load and store was used. For each program tested a reuse distance histogram is provided The histogram presents the frequency with which a speci c reuse distance re-appears in a program. In addition to the above, the C language instrumentor provided by C. Ding was used with one of the benchmarks in order to get source-level information related to the program's access patterns. However, the instrumentor failed to compile successfully the progrmas of the MediaBench suite. Thus, insight on
منابع مشابه
MediaBench: A Tool for Evaluating and Synthesizing Multimedia and Communications Systems
Over the last decade, significant advances have been made in compilation technology for capitalizing on instruction-level parallelism (ILP). The vast majority of ILP compilation research has been conducted in the context of generalpurpose computing, and more specifically the SPEC benchmark suite. At the same time, a number of microprocessor architectures have emerged which have VLIW and SIMD st...
متن کاملInstruction Buffering Exploration for Low Energy Embedded Processors
For multimedia applications, loop buffering is an efficient mechanism to reduce the power in the instruction memory of embedded processors. Especially software controlled loop buffers are energy efficient. However current compilers do not fully take advantage of the possibilities of such loop buffers. This paper presents an algorithm the explore for an application or a set of applications what ...
متن کاملMediaBench II video: Expediting the next generation of video systems research
The first step towards the design of video processors and video systems is to achieve an accurate understanding of the major video applications, including not only the fundamentals of the many video compression standards, but also the workload characteristics of those applications. Introduced in 1997, the MediaBench benchmark suite provided the first set of full application-level benchmarks for...
متن کاملUsing the SGI Pro64 Open Source Compiler Infra-Structure for Teaching and Research
Modern optimizing compilers are complex programs that require from tens to hundreds of people-years to be developed. Thus professors must use third-party compiler infra-structures to introduce students to compiler optimizations. Until recently only infra-structures developed at universities, research institutes, or by GNU were widely available for teaching. However, in May 2000, SGI made public...
متن کاملAnalysis of critical paths in a project network with random fuzzy activity times
Project planning is part of project management, which is relates to the use of schedules such as Gantt charts to plan and subsequently report progress within the project environment. Initially, the project scope is defined and the appropriate methods for completing the project are determined. In this paper a new approach for the critical path analyzing a project network with random fuzzy activi...
متن کامل