Arm Mali-G72 was the second generation high performance GPU based on the Mali Bifrost architecture. Benefitting from advanced technologies such as claused shaders and full system coherency, Mali-G72 increased tile buffer memory supporting up to 16 x multi-sample anti-aliasing (MSAA) at minimal performance cost. Arithmetic optimizations tailored to complex machine learning (ML) and high fidelity mobile gaming use cases provide 25% higher energy efficiency, 20% better performance density and 40% greater overall performance than devices based on previous generation Bifrost GPUs. 

Mali-G72 Block Diagram.

Arm Mali-G72 GPU

Features Value Description
Anti-Aliasing 4x MSAA
16x MSAA
Hardware-implemented Full-Scene Multiple Sample Anti-Aliasing. 
API Support OpenGL®ES 1.1, 2.0, 3.0, 3.1, 3.2
OpenCL™ 1.1, 1.2, 2.0
Full support for next-generation and legacy2D/3D graphics applications.
Bus Interface AMBA®4 ACE, ACE-LITE and AXI Compatible with a wide range of bus interconnect and peripheral IP.
L2 Cache Configurable 128kB-2048kB From 1-4 slices, each configurable from 128kB – 512kB.
Memory System Virtual Memory Built-in Memory Management Unit (MMU) to support virtual memory.
Multi-Core Scaling 1 to 32 cores Optimized for high energy efficiency to address the high-end mobile and consumer device requirements.   
Adaptive Scalable Texture Compression Low dynamic range (LDR) and high dynamic range (HDR).
Supports both 2D and 3D images
ASTC offers a number of advantages over previous texture compression schemes by improving image quality, while reducing memory bandwidth and thus energy use.
Arm Frame Buffer Compression 4x4 pixel block size AFBC is a lossless image compression format that provides random access to pixel data to a 4x4 pixel block granularity. It is employed to reduce memory bandwidth both internally within the GPU and externally throughout the SoC.
Transaction Elimination 16x16 pixel block size Transaction Elimination spots the identical pixel blocks between two consecutive render targets and performs a partial update to the frame buffer with the changed pixel blocks only, which reduces memory bandwidth and thus energy.
Smart Composition 16x16 pixel block size Smart Composition extends the concept of Transaction Elimination to every stage of UI composition. Identical pixel blocks of input surfaces are not read, not processed for composition and not written to final frame buffer.

Performance - Mali-G72 (MP32)

Features Value Description
Frequency 850 MHz in 16nm (16 FinFET)
Throughput 850 Mtri/s, 27.2 Gpix/s in 16nm (16 FinFET)