LTTng CLUST: A System-Wide Unified CPU and GPU Tracing Tool for OpenCL Applications

As computation schemes evolve and many new tools become available to programmers to enhance the performance of their applications, many programmers startedto look towards highly parallel platforms such as Graphical Processing Unit (GPU). Offloading computations that can take advantage of the architecture of the GPUis a technique that has proven fruitful in recent years. This technology enhances the speed and responsiveness of applications. Also, as a side effect, it reduces thepower requirements for those applications and therefore extends portable devices battery life and helps computing clusters to run more power efficiently. Many performance analysis tools such as LTTng, strace and SystemTap already allow Central Processing Unit (CPU) tracing and help programmers to use CPU resources more efficiently. On the GPU side, different tools such as Nvidia’s Nsight, AMD’s CodeXL, and third party TAU and VampirTrace allow tracing Application Programming Interface (API) calls and OpenCL kernel execution. These tools are useful but are completelyseparate, and none of them allow a unified CPU-GPUtracing experience. We propose an extension to the existing scalableand highly efficient LTTng tracing platform to allowunified tracing of GPU along with CPU’s full tracingcapabilities