Artificial Intelligence & Data Science is coming soon
We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.
Artificial Intelligence & Data Science
GPU Programming and Architecture
GPU architecture and CUDA memory, CUDA programming and optimisation, NVCC and errors, OpenCL, parallel GPU algorithms.
Notes for GPU Programming and Architecture are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.
Coming next in GPU Programming and Architecture
- GPU architecture· notes coming
- Threads, blocks, grids and warps· notes coming
- CUDA memory types· notes coming
- CUDA kernels and thread hierarchy· notes coming
- Heterogeneous programming· notes coming
- Multi-GPU programming· notes coming
- Optimising CUDA applications· notes coming
- CUDA error handling· notes coming
- Synchronisation in CUDA· notes coming
- NVCC compilation and PTX· notes coming
- OpenCL programming model· notes coming
- OpenCL kernels and host code· notes coming
- OpenCL memory model· notes coming
- Parallel convolution· notes coming
- Parallel prefix sum· notes coming
- Sparse matrix multiplication on GPUs· notes coming
- Dynamic parallelism· notes coming
- OpenCL for heterogeneous computing· notes coming
- GPU neural network training· notes coming
- Evolution of GPU architectures and GPGPU· notes coming
- CUDA program structure and data transfer· notes coming
- CUDA runtime API and kernel launch· notes coming
- Mapping threads to multidimensional data· notes coming
- CUDA matrix–matrix multiplication· notes coming
- Thread scheduling and latency tolerance· notes coming
- Reducing global memory traffic with tiling· notes coming
- Warps, memory bandwidth and resource partitioning· notes coming
- Floating-point considerations on GPUs· notes coming
- GPU applications: gaming, computer vision and optimisation· notes coming
- Warp divergence and memory coalescing· notes coming
- Reduction kernels, kernel fusion and thread coarsening· notes coming