Advanced search

Showing result 1 - 5 of 17 essays matching the above criteria.

  1. 1. AXI-PACK : Near-memory Bus Packing for Bandwidth-Efficient Irregular Workloads

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Chi Zhang; [2022]
    Keywords : General propose processor; on-chip bus protocol; irregular memory access; ASIC digital circuit design.; Generellt förslag på processor; on-chip-bussprotokoll; oregelbunden minnesåtkomst; digital ASIC-kretsdesign.;

    Abstract : General propose processor (GPP) are demanded high performance in dataintensive applications, such as deep learning, high performance computation (HPC), where algorithm kernels like GEMM (general matrix-matrix multiply) and SPMV (sparse matrix-vector multiply) kernels are intensively used. The performance of these data-intensive applications are bounded with memory bandwidth, which is limited by computing & memory access coupling and memory wall effect. READ MORE

  3. 2. OpenMZ: a C implementation of the MultiZone API

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Henrik Karlsson; [2020]
    Keywords : ;

    Abstract : We implemented, benchmarked, and analyzed OpenMZ, a separation kernel for RISC-V targeting secure coprocessors and embedded devices. OpenMZ is an open-source implementation of the MultiZone API, which partitions a system into a fixed number of zones that can communicate with each other and handle interrupts. READ MORE

  4. 3. Evaluation of Machine Learning Primitives on a Digital Signal Processor

    University essay from Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska högskolan

    Author : Vilhelm Engström; [2020]
    Keywords : digital signal processor; DSP; SIMD; data parallelism; machine learning; deep learning; convolutional neural network;

    Abstract : Modern handheld devices rely on specialized hardware for evaluating machine learning algorithms. This thesis investigates the feasibility of using the digital signal processor, a part of the modem of the device, as an alternative to this specialized hardware. READ MORE

  5. 4. MEASURING THE REAL-TIME LATENCY OF AN I.MX7D USING XENOMAI AND THE YOCTO PROJECT

    University essay from Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Author : Bram Coenen; [2019]
    Keywords : ;

    Abstract : In this thesis the real-time latency of an i.MX7D processor on a CL-SOM-IMX7 boardis evaluated. The real-time Linux for the system is created using Xenomai with both theI-Pipe patch and thePREEMPT_RTpatch. The embedded distribution is built using theYocto Project and uses a vendor i. READ MORE

  6. 5. Evaluating Parallelization Potential for a SystemC/TLM-based Virtual Platform

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Zeeshan Hayat; [2018]
    Keywords : ;

    Abstract : System on chip (SoC) solutions, with integrated hardware and embedded software, are increasing in size and complexity. To cope with the market demand for complex SoC, the abstraction level used during development is raised to allow co-development of software (SW) and hardware (HW). READ MORE