Automatic hardware generation for the Molen reconfigurable architecture: a G721 case study
نویسندگان
چکیده
The advantages of the reconfigurable technology in terms of performance have been widely recognized. However, programming reconfigurable systems and designing hardware accelerators for them is not a trivial task. The Molen paradigm provides an easy to use approach to couple a General Purpose Processor (GPP) with custom designed reconfigurable accelerators both at program level and at hardware design level. In this case study, we illustrate the entire design flow to demonstrate how one can use the DelftWorkbench Automated Reconfigurable VHDL Generator (DWARV) tool, the Molen compiler and the Molen reconfigurable co-processor to accelerate a C application code in hardware. As a case study application, the G721 audio encoder is used. The implementation platform is a Xilinx VirtexII Pro XC2VP30-7 FPGA, which integrates two PowerPC 405 processors. The experimental results obtained after employing the described design flow suggest an overall application speedup of 2.7 times over a pure software implementation. Keywords— Reconfigurable processors, FPGA, Molen paradigm, Automatic HDL generation
منابع مشابه
Loop Parallelization for Reconfigurable Architectures
Reconfigurable Computing (RC) is one of the research directions that focuses on accelerating applications. In the presented approach we assume the Molen machine organization and the Molen programming paradigm as our framework. Molen combines a general purpose processor (GPP) and a Field Programmable Gate Array (FPGA), having the advantages of both speed of hardware and flexibility of software e...
متن کاملCompiling for the Molen Programming Paradigm
In this paper we present compiler extensions for the Molen programming paradigm, which is a sequential consistency paradigm for programming custom computing machines (CCM). The compiler supports instruction set extensions and register file extensions. Based on pragma annotations in the application code, it identifies the code fragments implemented on the reconfigurable hardware and automaticall...
متن کاملMatrix Multiplication Implementation in the MOLEN Polymorphic Processor
Floating-point matrix multiplication is arguably the most important kernel routine in many scientific applications. Therefore, its efficient implementation is crucial for the overall performance of any computer system targeting scientific computations. In this paper, we propose a holistic solution to accelerate matrix multiplication on reconfigurable hardware using the MOLEN polymorphic process...
متن کاملFlexible Routing Architecture Generation for Domain-Specific Reconfigurable Subsystems
Reconfigurable hardware is ideal for use in Systems-on-a-Chip, as it provides hardware speeds as well as the benefits of post-fabrication modification. However, not all applications are equally suited to any one reconfigurable architecture. Therefore, the Totem Project focuses on the automatic generation of customized reconfigurable hardware. This paper details our first attempts at the design ...
متن کاملComputer Graphics and the MOLEN paradigm: a survey
Focusing in the advantages and drawbacks on the FPGA implementations vs. ASIC and pure software, this paper surveys the development of computer graphics. We start with the description of the theoretical problems related to computer graphics. Consequently, we present the most relevant industrial and academic solutions categorizing them from the point of view of their contribution in the speed up...
متن کامل