Fixed-point arithmetic for ASIP code generation
نویسندگان
چکیده
In this paper we present an environment supporting fixed-point arithmetic in C programs. It allows the specification of the position of the binary point in the source code and code generation for architectures with hardware support for the fixed-point arithmetic. Our tools are implemented on the top of the SUIF C compiler[1] and do not require any special adaptations. We demonstrate the validity of our approach on a series of experiments on a test program. The results show that fixed-point arithmetic executed on an integer datapath has a limited impact on the accuracy when compared to a floating-point version of the same program. In the same time the performance difference is remarkable: the fixed-point code is 3.7 to 10 times faster than its equivalent floating-point emulation on an integer datapath.
منابع مشابه
Automatic Fixed-point Code Generation for Modelica using Dymola
This paper describes a Modelica package for fixedpoint arithmetics and automatic fixed point code generation for embedded systems and FPGA applications. Using Dymola [1] to investigate the dynamic behavior of the original model a fixed point representation is automatically generated. The model can then be simulated, using fixed point arithmetics to verify the fixed-point representation. Finally...
متن کاملFloating Point to Fixed Point Conversion of C Code
In processors that do not support floating-point instructions, using fixed-point arithmetic instead of floating-point emulation trades off computation accuracy for execution speed. This trade-off is often profitable. In many cases, like embedded systems, low-cost and speed bounds make it the only acceptable option. We present an environment supporting fixed-point code generation from C programs...
متن کاملConverting Models from Floating Point to Fixed Point for Production Code Generation
An essential step in embedded software development, floatingto fixed-point conversion can be tedious, labor-intensive, and error-prone. System engineers frequently design algorithms in floating-point math, usually double-precision. This format represents the ideal algorithm behavior but takes little account of the algorithm’s final realization in production software and hardware. Software engin...
متن کاملDesign and Implementation of Numerical Linear Algebra Algorithms on Fixed Point DSPs
Numerical linear algebra algorithms use the inherent elegance of matrix formulations and are usually implemented using C/C++ floating point representation. The system implementation is faced with practical constraints because these algorithms usually need to run in real time on fixed point digital signal processors (DSPs) to reduce total hardware costs. Converting the simulation model to fixed ...
متن کاملFloating-to-Fixed-Point Conversion for Digital Signal Processors
Digital signal processing applications are specified with floating-point data types but they are usually implemented in embedded systems with fixed-point arithmetic to minimise cost and power consumption. Thus, methodologies which establish automatically the fixed-point specification are required to reduce the application time-to-market. In this paper, a new methodology for the floating-to-fixe...
متن کامل