1 Floating-point Unit Implementation in Altera FLEX10K FPGA using VHDL Agfianto Eko Putra 1 , Isnan Nur Rifa’i 2 1,2 Electronics and Instrumentation, Physics Department Faculty of Mathematics & Natural Sciences Gadjah Mada University, Yogyakarta – Indonesia 55281 Abstract Floating-point systems were developed to provide high resolution over a large dynamic range. Floating-point systems can often provide a solution when fixed-point systems, with their limited dynamic range, fail. Floating-point systems, however, bring a speed and complexity penalty. Most microprocessor floating-point systems comply with the published single- or double-precision IEEE floating-point standard; while in FPGA-based systems often employ custom formats. In this research, a 16-bit floating-point unit, which has addition, subtraction, multiplication and division operator, and based on floating-point system, has been implemented in Altera FLEX10K FPGA using VHDL (VHSIC Hardware Description Language). The design used structural and behavior model implementation to know which the best design is. The best results are structural model using ROM which require 438 logic elements with 7.99 MFLOPS (million floating-point operations per second), and the behavior model using ROM which require 526 logic elements with 7.51 MFLOPS. The floating-point unit has been designed for normal floating-point operation, thus it can not detect overflow or underflow conditions. Keywords: FPGA, VHDL, Floating Point 1. INTRODUCTION Floating Point Unit is a numerical computing unit which is important in the computer system. Almost algorithms that use real numbers, depends on this operation, because the floating point unit is a system of numerical interpretation series of digits or bits that are presented as real number [1]. In other words, floating point unit is serving a fraction of the computer. Many algorithms rely on floating point arithmetic for the dynamic range of representations and require millions of calculations per second. The programmers are freely to code numbers in various applications [2]. This shows the number of computing with floating point played an important role in various applications in the fields of science, engineering and industry, especially in the meteorology, mechanical design and simulation. The ability to perform floating point operations is an essential measurement to the performance of computer applications [2]. Floating point arithmetic operations can be implemented into the FPGA by using the schematic method, but the algorithm used in the floating point unit is too complex, so it requires a very high accuracy in making the optimum schematic model and requires analysis when errors occur in a complex schematic. So this method is considered less efficient. However, using the language VHDL description, the problems are very capable.