In this project we explore the capability and flexibility of FPGA solutions in a sense to accelerate scientific computing applications which require very high precision arithmetic, based on IEEE 754 standard 128-bit floating-point number representations. Field Programmable Gate Arrays (FPGA) is increasingly being used to design high end computationally intense microprocessors capable of handlin...

This paper presents a three-dimensional discrete wavelet transform (DWT) for image processing based on unary arithmetic. The upper layer on-chip camera provides the input to the lower 3D-DWT processor layer utilizing Through Silicon Via (TSV) interconnections technology for data and signal transfers. Stacking of chips allow for low power operation since the inter-chip drivers are no longer nece...

Hardware organized modular multiplication based on division algorithm is one of the effective methods used for RSA encryption/decryption. This paper generalizes the hardware organization of the modular multiplication based on the higher-radix SRT division algorithm, and describes the area/time trade-off of the organization. For the number representation we used the signed-digit number system an...

In this paper I will discuss the feasibility of an implementation of an algorithm containing a Deep Convolutional Neural Network for feature extraction, and softmax regression for feature classification, for the purpose of real-time lane detection on an embedded platform containing a multi-core Digital Signal Processor (DSP). I will explore the merits of using fixed point and floating point ari...

2-bit magnitude comparator design using different logic styles is proposed in this brief. Comparison is most basic arithmetic operation that determines if one number is greater than, equal to, or less than the other number. Comparator is most fundamental component that performs comparison operation. This brief presents comparison between different logic styles used to design 2-Bit magnitude com...

Multiplication is one of the most important operation in computer arithmetic. Many integer operations such as squaring, division and computing reciprocal require same order of time as multiplication whereas some other operations such as computing GCD and residue operation require at most a factor of logn time more than multiplication. We propose an integer multiplication algorithm using Nikhila...

The double-precision floating-point arithmetic, specifically multiplication, is a widely used arithmetic operation for many scientific and signal processing applications. In general, the double-precision floating-point multiplier requires a large 53 × 53 mantissa multiplication in order to get the final result. This mantissa multiplication exists as a limit on both area and performance bounds o...

One of the main problems of interval computations is to compute the range y of the given function f(x1, . . . , xn) under interval uncertainty. Interval computations started with the invention of straightforward interval computations, when we simply replace each elementary arithmetic operation in the code for f with the corresponding operation from interval arithmetic. In general, this techniqu...

Fast Fourier Transform (FFT) processors employed with pipeline architecture consist of series of Processing Elements (PE) or Butterfly Units (BU). BU or PE of FFT performs multiplication and addition on complex numbers. This paper proposes a single BU to compute radix-2, 8 point FFT in the time domain as well as frequency domain by replacing a series of PEs. This BU comprises of fused floating ...

We describe an algorithm that produces code, with spills, for a register-constrained machine that can issue up to one arithmetic operation and one memory access operation per time slot, under the restrictions that the code's dependence graph is represented as a binary tree with no unary operations, and the latency of the operations is 1. We prove that the algorithm produces a minimum cost sched...