Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 8 of 8 for “"Domain-specific architecture"”.

  1. Investigation of the Effect of Functional Units/Connectivity Arrangement on Energy Consumption of Reconfigurable Architectures Using an Interactive Design Framework

    … Lab at UNT to discover the design of custom domain-specific architectures. This thesis explores several case-studies to investigate the arrangement of functional units and interconnects to achieve a low power, high performance, and flexible heterogeneous designs that can fit for a suite of …

    unt Repository record for Investigation of the Effect of Functional Units/Connectivity Arrangement on Energy Consumption of Reconfigurable Architectures Using an Interactive Design Framework (opens in a new tab)

  2. Utilizing GPU tensor cores for algorithmic acceleration

    There has been a surge in the demand for a Domain Specific Architecture due to wide ranging deep learning applications like Image classification, speech recognition, in healthcare, self-driving cars etc. Matrix Multiplication acceleration has been a popular design choice when creating these …

    uiuc Repository record for Utilizing GPU tensor cores for algorithmic acceleration (opens in a new tab)

  3. Designing Right-Provisioned System Architectures for Edge Computing

    … a wide variety of applications, application domains, and devices. In this dissertation, we focus on developing efficient system architectures for the edge devices. The first step in optimizing the system architectures is to understand the requirements of the target applications. We need to …

    arizona-thes Repository record for Designing Right-Provisioned System Architectures for Edge Computing (opens in a new tab)

  4. Methodical Evaluation of Processing-in-Memory Alternatives

    … reconfigurable dataflow (DF-PIM), and a domain specific architecture using SIMD PIM engine consisting of a series of multiply-accumulate circuits (MACs). For each PIM alternative I investigated how performance and energy efficiency changes with respect to a series of system parameters, …

    unt Repository record for Methodical Evaluation of Processing-in-Memory Alternatives (opens in a new tab)

  5. An HDL-parameterizable m x n systolicarray- based matrixmultiplier for DNN applications

    … On the other hand, resource utilization, specifically BRAM utilization in v1 is less than that in v2 giving the same SA shape since there is no need to save all tiles’ parameters before the start of the execution. Thus available resources (higher DSP/MAC resources in v1 and higher BRAM in …

    chalmers Repository record for An HDL-parameterizable m x n systolicarray- based matrixmultiplier for DNN applications (opens in a new tab)

  6. Analytical Modeling and Efficient Implementation for Specialized Hardware Acceleration of Sparse Applications

    … in the characteristics of input matrices and specific architecture configurations. Next, by leveraging the rapid DSE enabled by this analytical model, we develop Vesper, a versatile sparse accelerator equipped with High Bandwidth Memory (HBM) to efficiently handle datasets of varying …

    cornell Repository record for Analytical Modeling and Efficient Implementation for Specialized Hardware Acceleration of Sparse Applications (opens in a new tab) Embargoed until 2028-06-18

  7. Database System Acceleration on FPGAs

    … alternative methods, such as application-specific technologies, to satisfy the more challenging performance requirements. One such technology is field-programmable gate arrays (FPGAs), which provide ideal platforms for developing and running custom architectures for accelerating database …

    qucosa-diss

  8. An Empirical Comparison of Reuse in Embedded and Nonembedded Systems

    … the software" cycle to a process-driven, domain-specific, architecture-centric, library-based way of constructing software.'' Twenty years after issuing this initiative, there is evidence of this vision beginning to be realized in nonembedded systems. However, virtually every large …

    denver Repository record for An Empirical Comparison of Reuse in Embedded and Nonembedded Systems (opens in a new tab)