Rodinia suite with solid time counters and kernels in PTX

Cufft that compiles with CUDA static libcufft.a that is important to enable cuda runtime and driver call interception

A simple benchmark for comparing NVIDIA's MPS with NATIVE execution

Compare pin and peagable memory

Evaluate the performance of launching a kernel from another kernel using CUDA dynamic parallelism

Evaluate the performance of creating cuda contexts via the driver API

Evaluate the performance of killing a CUDA process to provide the GPU in a high priority process.

Evaluate CUDA pascal compute preemption using high-low priority streams

evaluation of cuda register functions

Evaluate different bit masking approaches for CUDA

A simple example for Vector Addition using CUDA

GPU kernel that gray scales an image