The PowerVR Series8XT family is based on the new Furian GPU Architecture and pushes mobile and embedded performance to new heights with configurations featuring two to eight clusters offering dramatically scalable performance from 300 GFLOPS to 1.2 TFLOPS, a range of ultra-efficient, highly-featured GPUs based on the new Furian Architecture. Features include: an advanced scalable compute cluster architecture; high-efficiency compression technology including parameter compression and the widely respected PVRTC™ texture compression; an enhanced scheduling architecture; dedicated housekeeping processors; and a next-generation tile-based deferred rendering architecture. These features combine to produce a highly latency tolerant GPU architecture that consumes the lowest memory bandwidth in the industry while delivering the best performance per mm2 and per mW.

API Support

  • OpenGL® ES 1.1, 2.0, 3.0, 3.1, 3.2
  • Vulkan® 1.0, 1.1
  • OpenCL™ 1.1, 1.2, 2.0
  • Android NN HAL
  • RenderScript™

Bus Interface

  • AMBA®4 ACE or ACE-LITE

Security

  • Beyond TrustZone®

Hardware virtualization

  • Up to eight operating systems

Memory System

  • Virtual Memory

Compression

Texture

  • ETC
  • ETC2
  • ASTC
  • PVRTC

PVRIC Frame Buffer

  • V3 Supported

PVRGC Geometry

  • Supported

Core Configuration

  • 1 SPU (Scalable Processing Unit)

Performance

Floating point operations per clock

  • 192 FP32 FLOPs/Clock
  • 384 FP16 FLOPs/Clock

Pixel rate per clock

  • 8 pixels per clock