Mark A. Franklin

Publications (27)0 Total impact

• Conference Proceeding: Statistics on logic simulation.

  Kenneth F. Wong, Mark A. Franklin, Roger D. Chamberlain, B. L. Shing
  01/1986
• Source

  Available from: Ronald S. Indeck

  Article: Exploiting Reconfigurability for Text Search

  Roger D Chamberlain, Mark A Franklin, Ronald S Indeck
• Source

  Available from: wustl.edu

  Article: Against all probabilities: A modeling paradigm for streaming applications that goes against common notions

  Rahav Dor, Roger D Chamberlain, Mark A Franklin
  [show abstract] [hide abstract]
  ABSTRACT: Hardware and software design requires the right portion of skills and mental faculties. The design of a good system is an exercise in rational thinking, engineering, and art. The design process is further complicated when we aspire to build systems that exploit parallelism or are targeted to be deployed on architecturally diverse computing devices, FPGAs or GPUs to name just a few. The need to develop systems that can take advantage of computing devices beyond general purpose CPUs is real. There are several application domains and research efforts that will simply not be able to adequately perform or yield answers in a reasonable amount of time otherwise. Developing a mathematical model of a system is a key stepping stone to a high performance system, but often is absent from the design process due to the complexity of the model development. In this paper we offer an easy, yet solid approach to the development of such mathematical models. This adds a little bit more weight to engineering side of the design process in the form of a quantifiable method that enables designers to reason about their systems, identify bottlenecks, and gain vital information for performance Type of Report: Other Abstract Hardware and software design requires the right por-tion of skills and mental faculties. The design of a good system is an exercise in rational thinking, engineering, and art. The design process is further complicated when we aspire to build systems that exploit parallelism or are targeted to be deployed on architecturally diverse com-puting devices, FPGAs or GPUs to name just a few. The need to develop systems that can take advantage of computing devices beyond general purpose CPUs is real. There are several application domains and re-search efforts that will simply not be able to adequately perform or yield answers in a reasonable amount of time otherwise. Developing a mathematical model of a system is a key stepping stone to a high performance system, but often is absent from the design process due to the complexity of the model development. In this paper we offer an easy, yet solid approach to the development of such mathematical models. This adds a little bit more weight to engineering side of the design process in the form of a quantifiable method that enables designers to reason about their systems, iden-tify bottlenecks, and gain vital information for perfor-mance improvements.
• Source

  Available from: wustl.edu

  Article: Sorting as a streaming application executing on chip multiprocessors

  Roger D Chamberlain, Greg A Galloway, Mark A Franklin
  [show abstract] [hide abstract]
  ABSTRACT: Expressing concurrency in applications has always been a difficult and error-prone endeavor, yet effective utilization of multi-core processors requires that the concurrency in applications be understood. One approach to the expression of concurrency is streaming, which has shown real promise as a safe and effective method for many application classes. Here, we express a classic problem, sorting, in the streaming paradigm and explore the implications of various algorithm and architectural design parameters on the performance of the application. Abstract Expressing concurrency in applications has always been a difficult and error-prone endeavor, yet effective utilization of multi-core processors requires that the concurrency in applications be understood. One ap-proach to the expression of concurrency is streaming, which has shown real promise as a safe and effective method for many application classes. Here, we express a classic problem, sorting, in the streaming paradigm and explore the implications of various algorithm and architectural design parameters on the performance of the application.
• Source

  Available from: Ronald S. Indeck

  Article: The Mercury System: Embedding Computation into Disk Drives

  Roger D Chamberlain, Ron K Cytron, Mark A Franklin, Ronald S Indeck
• Source

  Available from: citeseerx.ist.psu.edu

  Article: The Mercury system: exploiting truly fast hardware for data search

  Roger D. Chamberlain, Ron K. Cytron, Mark A. Franklin, Ronald S. Indeck
  [show abstract] [hide abstract]
  ABSTRACT: In many data mining applications, the size of the database is not only extremely large, it is also growing rapidly. Even for relatively simple searches, the time required to move the data off magnetic media, cross the system bus into main memory, copy into processor cache, and then execute code to perform a search is prohibitive. We are building a system in which a significant portion of the data mining task (i.e., the portion that examines the bulk of the raw data) is implemented in fast hardware, close to the magnetic media on which it is stored. Furthermore, this hardware can be replicated allowing mining tasks to be performed in parallel, thus providing further speedup for the overall mining application. In this paper, we describe a general framework under which this can be accomplished and provide initial performance results for a set of applications.
• Source

  Available from: sbs.wustl.edu

  Article: Acceleration of atmospheric Cherenkov telescope signal processing to real-time speed with the Auto-Pipe design system

  Eric J. Tyson, James Buckley, Mark A. Franklin, Roger D. Chamberlain
  [show abstract] [hide abstract]
  ABSTRACT: The imaging atmospheric Cherenkov technique for high-energy gamma-ray astronomy is emerging as an important new technique for studying the high energy universe. Current experiments have data rates of and duty cycles of about 10%. In the future, more sensitive experiments may produce up to 1000 TB/year. The data analysis task for these experiments requires keeping up with this data rate in close to real-time. Such data analysis is a classic example of a streaming application with very high performance requirements. This class of application often benefits greatly from the use of non-traditional approaches for computation including using special purpose hardware (FPGAs and ASICs), or sophisticated parallel processing techniques. However, designing, debugging, and deploying to these architectures is difficult and thus they are not widely used by the astrophysics community.This paper presents the Auto-Pipe design toolset that has been developed to address many of the difficulties in taking advantage of complex streaming computer architectures for such applications. Auto-Pipe incorporates a high-level coordination language, functional and performance simulation tools, and the ability to deploy applications to sophisticated architectures. Using the Auto-Pipe toolset, we have implemented the front-end portion of an imaging Cherenkov data analysis application, suitable for real-time or offline analysis. The application operates on data from the VERITAS experiment, and shows how Auto-Pipe can greatly ease performance optimization and application deployment of a wide variety of platforms. We demonstrate a performance improvement over a traditional software approach of using an FPGA solution and using a multiprocessor based solution.
  Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment.