Accelerated Computing
GPU
Custom Chips
FPGA
GPU
Distributed load across thousands of cores.
Refer Working of GPU and gpu programming paradigms
Custom Silicon
Fastest, but Extremely difficult and expensive to implement
Steps involved
- develop design
- simulate
- prototype
- silicon conversion
FPGA: programmable hardware
Custom hardware
Ways to program FPGA
- Hardware design - HDL - core electronics and VLSI
- High level synthesis (HLS) - C to RTL (Resistor Transistor Logic)
- OpenCL based abstraction