Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

GPU vs FPGA - Performance and future utilisation - looking for discussion and opinion

Status
Not open for further replies.

watertreader

Full Member level 3
Joined
Dec 2, 2005
Messages
174
Helped
4
Reputation
8
Reaction score
0
Trophy points
1,296
Activity points
2,560
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
 

yousif

Member level 1
Joined
Dec 2, 2005
Messages
38
Helped
3
Reputation
6
Reaction score
3
Trophy points
1,288
Activity points
1,580
FPGA Versus GPU(GPGPU) as two ways of "Hardware Acceleration"

GPUs have a fixed computational/programming model
FPGAs do not, and their logic can be customized exactly for an application's needs.

FPGAs require (usually) some hardware design experience
GPUs does not

GPU is really a "software acceleration" that can accelerate certain class of compute-intensive applications. The only interface to the GPU (nVidia or AMD) is PCI Express.
FPGA, on the other hand, can be used for a broader range of accelerations. It has customizable IOs, so it can interface with any chip (with compatible signal levels, speed, number of IOs)

You can compare:
Xilinx highest-end FPGAs, XC6VLX760(~$20k) OR XC6VSX475T(~$10k)
Nvidia TESLA C2070 (~$3k) Or Tesla M2090(~$3k)


---------- Post added at 08:21 ---------- Previous post was at 07:37 ----------

You can look at this interesting discussion
GPUs VS FPGAs/DSP - NVIDIA Forums
 
Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Top