A newer version of this document is available. Customers should click here to go to the newest version.
Visible to Intel only — GUID: GUID-FB052396-F712-4661-919F-E758E09D5AAE
Visible to Intel only — GUID: GUID-FB052396-F712-4661-919F-E758E09D5AAE
General-Purpose Computing on GPU
Traditionally, GPUs are used for creating computer graphics such as images, videos, etc. Due to their large number of execution units for massively parallelism, modern GPUs are also used for computing tasks that are conventionally performed on CPU. This is commonly referred to as General-Purpose Computing on GPU or GPGPU.
Many high performance computing and machine learning applications benefit greatly from GPGPU.
- Execution Model Overview
- Thread Mapping and GPU Occupancy
- Kernels
- Using Libraries for GPU Offload
- Host/Device Memory, Buffer and USM
- Host/Device Coordination
- Using Multiple Heterogeneous Devices
- Compilation
- OpenMP Offloading Tuning Guide
- Multi-GPU, Multi-Stack and Multi-C-Slice Architecture and Programming
- Level Zero
- Performance Profiling and Analysis
- Configuring GPU Device