Utilizing the Raspberry Pi GPU Horsepower
Doing a little research on special purpose computation, I found it is possible to reprogram the Raspberry Pi GPU to do some powerful calculations.
The Raspberry Pi 12 cores GPU (more properly called Quad Processing Units (QPUs) ) it has theoretical max performance of 24 GPFLOS
Theres an advanced book titled:
Raspberry Pi GPU Audio Video Programming by Jan Newmarch
in which he states: "The GPU is capable of 1 Gpixel/s, 1.5 Gtexel/s, or 24 GFLOPs of general-purpose compute and features a bunch of texture filtering and DMA infrastructure"
Here's a list of related articles and code libraries:
Broadcom released documentation on their proprietary GPU some time ago, the file is no longer available on their site, some of the material below may be based on that dated material.
GPU Accelerated Object Recognition on Raspberry Pi 3 & Raspberry Pi Zero (not source so far)
Hacking The GPU For Fun And Profit (Pt. 1) 2014
Python library for GPGPU on Raspberry Pi - work in progress (includes GPU technical insights)
OpenCL implementation running on the VideoCore IV GPU of the Raspberry Pi models
GPU_FFT
QPULib - A language and compiler for the Raspberry Pi GPU
VC4ASM - macro assembler for Broadcom VideoCore IV aka Raspberry Pi GPU
Docs Link
Raspberry Pi VideoCore APIs
Here's a 40 minute presentation to a bunch of engineers
Hacking the Raspberry Pi's VideoCore IV GPU - Louis Howe
- - - - -
TensorFlow 1.9 Officially Supports the Raspberry Pi Aug 2, 2018
Awesome Deep Vision - A curated list of deep learning resources 2017
The Raspberry Pi 12 cores GPU (more properly called Quad Processing Units (QPUs) ) it has theoretical max performance of 24 GPFLOS
Theres an advanced book titled:
Raspberry Pi GPU Audio Video Programming by Jan Newmarch
in which he states: "The GPU is capable of 1 Gpixel/s, 1.5 Gtexel/s, or 24 GFLOPs of general-purpose compute and features a bunch of texture filtering and DMA infrastructure"
Here's a list of related articles and code libraries:
Broadcom released documentation on their proprietary GPU some time ago, the file is no longer available on their site, some of the material below may be based on that dated material.
GPU Accelerated Object Recognition on Raspberry Pi 3 & Raspberry Pi Zero (not source so far)
Hacking The GPU For Fun And Profit (Pt. 1) 2014
Python library for GPGPU on Raspberry Pi - work in progress (includes GPU technical insights)
OpenCL implementation running on the VideoCore IV GPU of the Raspberry Pi models
GPU_FFT
QPULib - A language and compiler for the Raspberry Pi GPU
VC4ASM - macro assembler for Broadcom VideoCore IV aka Raspberry Pi GPU
Docs Link
Raspberry Pi VideoCore APIs
Here's a 40 minute presentation to a bunch of engineers
Hacking the Raspberry Pi's VideoCore IV GPU - Louis Howe
- - - - -
TensorFlow 1.9 Officially Supports the Raspberry Pi Aug 2, 2018
Awesome Deep Vision - A curated list of deep learning resources 2017
Comments
Post a Comment