watertreader
Full Member level 3
Hi,
Just a opinion survey thrown to the floor.
FPGA has the advantage of parallelism and datastreaming under a lower clock speed(less power usage) while GPU have higher clockspeed and utilise float point calculation(better accuracy) though suffer from low throughput with memory access requirement and high power usage.
With the introduction of high level function language like OpenCL, CUDA, DirectCompute. Is there any shift in the balance towards more GPU usage? Since GPU performance often leads FPGA and CPU, would GPU usage increase? Would the GPU be utilised to share the workload of CPU in the future?
Regards
Just a opinion survey thrown to the floor.
FPGA has the advantage of parallelism and datastreaming under a lower clock speed(less power usage) while GPU have higher clockspeed and utilise float point calculation(better accuracy) though suffer from low throughput with memory access requirement and high power usage.
With the introduction of high level function language like OpenCL, CUDA, DirectCompute. Is there any shift in the balance towards more GPU usage? Since GPU performance often leads FPGA and CPU, would GPU usage increase? Would the GPU be utilised to share the workload of CPU in the future?
Regards