Sökning: "Implementation on Chip"

Visar resultat 1 - 5 av 168 uppsatser innehållade orden Implementation on Chip.

1. 1. Code Synthesis for Heterogeneous Platforms

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Zhouxiang Fu; [2023]
   Nyckelord :Code Synthesis; Heterogeneous Platform; Zero-Overhead Topology Infrastructure; Kodsyntes; Heterogen plattform; Zero-Overhead Topologi Infrastruktur;

   Sammanfattning : Heterogeneous platforms, systems with both general-purpose processors and task-specific hardware, are largely used in industry to increase efficiency, but the heterogeneity also increases the difficulty of design and verification. We often need to wait for the completion of all the modules to know whether the functionality of the design is correct or not, which can cause costly and tedious design iteration cycles. LÄS MER

3. 2. A Conjugate Residual Solver with Kernel Fusion for massive MIMO Detection

   Master-uppsats, Högskolan i Halmstad/Centrum för forskning om tillämpade intelligenta system (CAISR)

   Författare :Ioannis Broumas; [2023]
   Nyckelord :MIMO; massive MIMO; GPU; CUDA; Software Defined Radio; SDR; MMSE; ZF; zero-forcing; parallel detection; iterative methods; conjugate residual; parallel computing; kernel fusion;

   Sammanfattning : This thesis presents a comparison of a GPU implementation of the Conjugate Residual method as a sequence of generic library kernels against implementations ofthe method with custom kernels to expose the performance gains of a keyoptimization strategy, kernel fusion, for memory-bound operations which is to makeefficient reuse of the processed data. For massive MIMO the iterative solver is to be employed at the linear detection stageto overcome the computational bottleneck of the matrix inversion required in theequalization process, which is 𝒪(𝑛3) for direct solvers. LÄS MER

4. 3. Low-power Implementation of Neural Network Extension for RISC-V CPU

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Dario Lo Presti Costantino; [2023]
   Nyckelord :Artificial intelligence; Deep learning; Neural networks; Edge computing; Convolutional neural networks; Low-power electronics; RISC-V; AI accelerators; Parallel processing; Artificiell intelligens; Deep learning; Neurala nätverk; Edge computing; konvolutionella neurala nätverk; Lågeffektelektronik; RISC-V; AI-acceleratorer; Parallell bearbetning;

   Sammanfattning : Deep Learning and Neural Networks have been studied and developed for many years as of today, but there is still a great need of research on this field, because the industry needs are rapidly changing. The new challenge in this field is called edge inference and it is the deployment of Deep Learning on small, simple and cheap devices, such as low-power microcontrollers. LÄS MER

5. 4. Chip Management in Milling and Drilling of Ductile Cast Iron

   Master-uppsats, Lunds universitet/Industriell Produktion

   Författare :Alexander Jönsson; Giacomo Aliboni; [2023]
   Nyckelord :Chip Carryover; Chip Management; Ductile Cast Iron; Chip Removal; Chip Asportation; Milling; Drilling; Technology and Engineering;

   Sammanfattning : This paper presents a comprehensive cross-functional analysis of machining operations for ductile cast iron components in the automotive industry, focusing on the problem of chip carryover and its impact on downstream processes. The research aims to understand the role of machining and identify the source of the issue, by analyzing different machining sequences and the chips that affect the final product or subsequent production stages. LÄS MER

7. 5. Low-power Acceleration of Convolutional Neural Networks using Near Memory Computing on a RISC-V SoC

   Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

   Författare :Kristoffer Westring; Linus Svensson; [2023]
   Nyckelord :FPGA; ASIC; Near Memory Computing; RISC-V; Convolutional Neural Network; Technology and Engineering;

   Sammanfattning : The recent peak in interest for artificial intelligence, partly fueled by language models such as ChatGPT, is pushing the demand for machine learning and data processing in everyday applications, such as self-driving cars, where low latency is crucial and typically achieved through edge computing. The vast amount of data processing required intensifies the existing performance bottleneck of the data movement. LÄS MER