Matching Items (4)
Filtering by
- All Subjects: FPGA
- Creators: Barnaby, Hugh
- Member of: ASU Electronic Theses and Dissertations
- Status: Published
Description
Efficiency of components is an ever increasing area of importance to portable applications, where a finite battery means finite operating time. Higher efficiency devices need to be designed that don't compromise on the performance that the consumer has come to expect. Class D amplifiers deliver on the goal of increased efficiency, but at the cost of distortion. Class AB amplifiers have low efficiency, but high linearity. By modulating the supply voltage of a Class AB amplifier to make a Class H amplifier, the efficiency can increase while still maintaining the Class AB level of linearity. A 92dB Power Supply Rejection Ratio (PSRR) Class AB amplifier and a Class H amplifier were designed in a 0.24um process for portable audio applications. Using a multiphase buck converter increased the efficiency of the Class H amplifier while still maintaining a fast response time to respond to audio frequencies. The Class H amplifier had an efficiency above the Class AB amplifier by 5-7% from 5-30mW of output power without affecting the total harmonic distortion (THD) at the design specifications. The Class H amplifier design met all design specifications and showed performance comparable to the designed Class AB amplifier across 1kHz-20kHz and 0.01mW-30mW. The Class H design was able to output 30mW into 16Ohms without any increase in THD. This design shows that Class H amplifiers merit more research into their potential for increasing efficiency of audio amplifiers and that even simple designs can give significant increases in efficiency without compromising linearity.
ContributorsPeterson, Cory (Author) / Bakkaloglu, Bertan (Thesis advisor) / Barnaby, Hugh (Committee member) / Kiaei, Sayfe (Committee member) / Arizona State University (Publisher)
Created2013
Description
Class D Amplifiers are widely used in portable systems such as mobile phones to achieve high efficiency. The demands of portable electronics for low power consumption to extend battery life and reduce heat dissipation mandate efficient, high-performance audio amplifiers. The high efficiency of Class D amplifiers (CDAs) makes them particularly attractive for portable applications. The Digital class D amplifier is an interesting solution to increase the efficiency of embedded systems. However, this solution is not good enough in terms of PWM stage linearity and power supply rejection. An efficient control is needed to correct the error sources in order to get a high fidelity sound quality in the whole audio range of frequencies. A fundamental analysis on various error sources due to non idealities in the power stage have been discussed here with key focus on Power supply perturbations driving the Power stage of a Class D Audio Amplifier. Two types of closed loop Digital Class D architecture for PSRR improvement have been proposed and modeled. Double sided uniform sampling modulation has been used. One of the architecture uses feedback around the power stage and the second architecture uses feedback into digital domain. Simulation & experimental results confirm that the closed loop PSRR & PS-IMD improve by around 30-40 dB and 25 dB respectively.
ContributorsChakraborty, Bijeta (Author) / Bakkaloglu, Bertan (Thesis advisor) / Garrity, Douglas (Committee member) / Ozev, Sule (Committee member) / Arizona State University (Publisher)
Created2012
Description
The rapid improvement in computation capability has made deep convolutional neural networks (CNNs) a great success in recent years on many computer vision tasks with significantly improved accuracy. During the inference phase, many applications demand low latency processing of one image with strict power consumption requirement, which reduces the efficiency of GPU and other general-purpose platform, bringing opportunities for specific acceleration hardware, e.g. FPGA, by customizing the digital circuit specific for the deep learning algorithm inference. However, deploying CNNs on portable and embedded systems is still challenging due to large data volume, intensive computation, varying algorithm structures, and frequent memory accesses. This dissertation proposes a complete design methodology and framework to accelerate the inference process of various CNN algorithms on FPGA hardware with high performance, efficiency and flexibility.
As convolution contributes most operations in CNNs, the convolution acceleration scheme significantly affects the efficiency and performance of a hardware CNN accelerator. Convolution involves multiply and accumulate (MAC) operations with four levels of loops. Without fully studying the convolution loop optimization before the hardware design phase, the resulting accelerator can hardly exploit the data reuse and manage data movement efficiently. This work overcomes these barriers by quantitatively analyzing and optimizing the design objectives (e.g. memory access) of the CNN accelerator based on multiple design variables. An efficient dataflow and hardware architecture of CNN acceleration are proposed to minimize the data communication while maximizing the resource utilization to achieve high performance.
Although great performance and efficiency can be achieved by customizing the FPGA hardware for each CNN model, significant efforts and expertise are required leading to long development time, which makes it difficult to catch up with the rapid development of CNN algorithms. In this work, we present an RTL-level CNN compiler that automatically generates customized FPGA hardware for the inference tasks of various CNNs, in order to enable high-level fast prototyping of CNNs from software to FPGA and still keep the benefits of low-level hardware optimization. First, a general-purpose library of RTL modules is developed to model different operations at each layer. The integration and dataflow of physical modules are predefined in the top-level system template and reconfigured during compilation for a given CNN algorithm. The runtime control of layer-by-layer sequential computation is managed by the proposed execution schedule so that even highly irregular and complex network topology, e.g. GoogLeNet and ResNet, can be compiled. The proposed methodology is demonstrated with various CNN algorithms, e.g. NiN, VGG, GoogLeNet and ResNet, on two different standalone FPGAs achieving state-of-the art performance.
Based on the optimized acceleration strategy, there are still a lot of design options, e.g. the degree and dimension of computation parallelism, the size of on-chip buffers, and the external memory bandwidth, which impact the utilization of computation resources and data communication efficiency, and finally affect the performance and energy consumption of the accelerator. The large design space of the accelerator makes it impractical to explore the optimal design choice during the real implementation phase. Therefore, a performance model is proposed in this work to quantitatively estimate the accelerator performance and resource utilization. By this means, the performance bottleneck and design bound can be identified and the optimal design option can be explored early in the design phase.
As convolution contributes most operations in CNNs, the convolution acceleration scheme significantly affects the efficiency and performance of a hardware CNN accelerator. Convolution involves multiply and accumulate (MAC) operations with four levels of loops. Without fully studying the convolution loop optimization before the hardware design phase, the resulting accelerator can hardly exploit the data reuse and manage data movement efficiently. This work overcomes these barriers by quantitatively analyzing and optimizing the design objectives (e.g. memory access) of the CNN accelerator based on multiple design variables. An efficient dataflow and hardware architecture of CNN acceleration are proposed to minimize the data communication while maximizing the resource utilization to achieve high performance.
Although great performance and efficiency can be achieved by customizing the FPGA hardware for each CNN model, significant efforts and expertise are required leading to long development time, which makes it difficult to catch up with the rapid development of CNN algorithms. In this work, we present an RTL-level CNN compiler that automatically generates customized FPGA hardware for the inference tasks of various CNNs, in order to enable high-level fast prototyping of CNNs from software to FPGA and still keep the benefits of low-level hardware optimization. First, a general-purpose library of RTL modules is developed to model different operations at each layer. The integration and dataflow of physical modules are predefined in the top-level system template and reconfigured during compilation for a given CNN algorithm. The runtime control of layer-by-layer sequential computation is managed by the proposed execution schedule so that even highly irregular and complex network topology, e.g. GoogLeNet and ResNet, can be compiled. The proposed methodology is demonstrated with various CNN algorithms, e.g. NiN, VGG, GoogLeNet and ResNet, on two different standalone FPGAs achieving state-of-the art performance.
Based on the optimized acceleration strategy, there are still a lot of design options, e.g. the degree and dimension of computation parallelism, the size of on-chip buffers, and the external memory bandwidth, which impact the utilization of computation resources and data communication efficiency, and finally affect the performance and energy consumption of the accelerator. The large design space of the accelerator makes it impractical to explore the optimal design choice during the real implementation phase. Therefore, a performance model is proposed in this work to quantitatively estimate the accelerator performance and resource utilization. By this means, the performance bottleneck and design bound can be identified and the optimal design option can be explored early in the design phase.
ContributorsMa, Yufei (Author) / Vrudhula, Sarma (Thesis advisor) / Seo, Jae-Sun (Thesis advisor) / Cao, Yu (Committee member) / Barnaby, Hugh (Committee member) / Arizona State University (Publisher)
Created2018
Description
Proton beam therapy has been proven to be effective for cancer treatment. Protons allow for complete energy deposition to occur inside patients, rendering this a superior treatment compared to other types of radiotherapy based on photons or electrons. This same characteristic makes quality assurance critical driving the need for detectors capable of direct beam positioning and fluence measurement. This work showcases a flexible and scalable data acquisition system for a multi-channel and segmented readout parallel plate ionization chamber instrument for proton beam fluence and positioning detection. Utilizing readily available, modern, off-the-shelf hardware components, including an FPGA with an embedded CPU in the same package, a data acquisition system for the detector was designed. The undemanding detector signal bandwidth allows the absence of ASICs and their associated costs and lead times in the system. The data acquisition system is showcased experimentally for a 96-readout channel detector demonstrating sub millisecond beam characteristics and beam reconstruction. The system demonstrated scalability up to 1064-readout channels, the limiting factor being FPGA I/O availability as well as amplification and sampling power consumption.
ContributorsAcuna Briceno, Rafael Andres (Author) / Barnaby, Hugh (Thesis advisor) / Brunhaver, John (Committee member) / Blyth, David (Committee member) / Arizona State University (Publisher)
Created2021