SPPU BE Computer syllabus

SPPU · Final Year Computer Engineering · 2019 Course (Revised)

GPU Programming and Architecture

410245B · Elective IV · Semester VII · 3 credits · In-semester 30 + end-semester 70

One of the Elective IV options.

All notes for this subject
  1. Unit 1: Introduction to Graphics Processing Unit (GPU)

    7 hours

    Evolution of GPU architectures, parallelism with GPUs, a typical GPU architecture; CUDA hardware: threads, blocks, grids, warps and scheduling; shared, global, constant and texture memory.

    Marks: 15 in the in-semester exam

    • GPU architecture and its evolution
    • Parallelism on the GPU
    • CUDA threads, blocks, grids and warps
    • CUDA memory: shared, global, constant and texture
  2. Unit 2: CUDA Programming

    7 hours

    Using CUDA, multi-GPU solutions; optimising CUDA applications: problem decomposition, memory, transfers, thread usage and resource contention.

    Marks: 15 in the in-semester exam

    • Writing CUDA programs
    • Multi-GPU programming
    • Optimising CUDA applications
  3. Unit 3: Programming Issues

    7 hours

    CUDA error handling, parallel programming issues, synchronisation, algorithmic issues, finding and avoiding errors.

    Marks: 17–18 in the end-semester exam

    • CUDA error handling
    • Synchronisation and parallel programming issues
  4. Unit 4: OpenCL Basics

    7 hours

    The OpenCL standard, kernels, host–device interaction, the execution environment, the memory model, basic examples.

    Marks: 17–18 in the end-semester exam

    • The OpenCL standard and kernels
    • OpenCL host–device interaction and execution model
    • OpenCL memory model
  5. Unit 5: Algorithms on GPU

    7 hours

    Parallel patterns: convolution, prefix sum, sparse matrix and matrix multiplication; programming a heterogeneous cluster.

    Marks: 17–18 in the end-semester exam

    • Parallel convolution on the GPU
    • Parallel prefix sum
    • Sparse matrix and matrix multiplication on the GPU
    • Programming heterogeneous clusters
  6. Unit 6: OpenCL and Application Design

    7 hours

    OpenCL for heterogeneous computing; efficient neural-network training and inference.

    Marks: 17–18 in the end-semester exam

    • OpenCL for heterogeneous computing
    • GPU acceleration for neural networks

Unit contents are summarised from the official SPPU syllabus . AiCanCode.org is not affiliated with Savitribai Phule Pune University.