Currently there are several ways to feed data to the GPU regardless of which API we use and type of application we develop. In the case of OpenGL we have uniform buffers, texture buffers, texture images, etc. The same is true for OpenCL and other compute APIs, which provide even more fine-grained memory management, taking advantage of the local data store (LDS) available on today’s hardware. This article presents memory access performance characteristics of AMD’s Evergreen-class GPUs, with a focus on what this all means from an OpenGL point of view. While most of the data is about the HD5870, the general principles and relative performance characteristics are valid for other GPUs.