GPU Flow
GPUs are special-purpose compute devices that can be used to offload a compute intensive portion of your application. GPUs usually consists of many smaller cores and are therefore known for massive throughput. There are some tasks better suited to a CPU and others that may be better suited to a GPU.
Note
In addition to Intel® processors listed in the System Requirements, AMD* and NVIDIA* GPUs may also be targeted (Linux only):
To use an AMD* GPU with the Intel® oneAPI DPC++ Compiler, install the oneAPI for AMD GPUs plugin from Codeplay.
To use an NVIDIA* GPU with the Intel® oneAPI DPC++ Compiler, install the oneAPI for NVIDIA GPUs plugin from Codeplay.
Tip
Unsure whether your workload fits best on CPU, GPU, or FPGA? Compare the benefits of CPUs, GPUs, and FPGAs for different oneAPI compute workloads.