This guide describes the top-level layout and the benefits of and shader core functionality of a typical Mali Valhall GPU programmable core. Valhall is the fourth generation of Mali GPUs. The Valhall family includes the Mali-G5x and Mali-G7x series of products. These products were released from 2018 onwards.

When optimizing applications using a GPU, it is useful to have at least a high-level mental model for how the underlying hardware works. It is also useful to understand the expected performance of the hardware, and the data rates for the different types of operations that it might perform. Understanding the block architecture is particularly important when optimizing using the Mali performance counters. This is because understanding what the counters are telling you implies a need to understand the blocks that the counters are tied to.

By the end of this guide, you will understand how the Mali Valhall series of GPUs perform shader core operations using shared access to the L2 cache. You will also learn the benefits of the warp manager and the processing engines within the execution core, and the benefits of the Index-Driven Vertex Shading (IDVS) geometry pipeline.

Before you begin

Before you work through this guide, we assume that you have read our introductory-level guide on tile-based rendering. This guide  builds on concepts that are introduced in that guide.