Robust OpenCL Operations

The massively parallel nature of many real-world computations has led to the development of specialized massively parallel hardware such as GPUs, TPUs and FPGAs. Many closely-related programming models exist such as CUDA and OpenCL. OpenCL is a popular framework for writing massively parallel code given its broader ecosystem and supported platforms. GIMP is a popular free open-source image manipulation tool often shipped as the default tool in many Unix-based distributions. GIMP uses GEGL internally for accelerating various image processing tasks. GEGL comes with OpenCL implementations for many operations. However, the OpenCL backend in GEGL was often slower than the baselines and resulted in incorrect outputs (and crashed sometimes). The goal of this project is to enumerate all the existing OpenCL implementations in GEGL, write a thorough suite of tests for them, and fix as many implementations as possible. If time permits and once correctness is established via tests, the project adds new faster implementations for popular operations. A successful completion of the project would allow the OpenCL backend to be enabled by default and allow the end-users to take advantage of hardware acceleration on their devices automatically.