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.

[SOLVED] Arithmetic operations

Status
Not open for further replies.

am85

Member level 2
Joined
May 30, 2011
Messages
46
Helped
1
Reputation
2
Reaction score
1
Trophy points
1,288
Location
Germany
Activity points
1,661
Hi,
Does anyone know what's the difference between the arithmetic operations in the FPU and the Multiplier, adder, divider and square root cores in Xilinx Core Generator. I know that with the FPU hardware arithmetic operations could be enabled. Then, are they the same with the only difference that FPU requires microblaze ? if not then which has the higher performance ?

thanks
 

permute

Advanced Member level 3
Joined
Jul 16, 2010
Messages
923
Helped
295
Reputation
590
Reaction score
268
Trophy points
1,343
Activity points
8,543
one of the big advantages of FPGA's is the ability to have simple operations performed in a regular fashion, and with many units.

for example, an FIR filter could make use of 64 multiply-add units (for modern fpgas), and accept new input at 350MSPS (1 new input per clock cycle). Because the operation is fixed, there is no need to have any overhead or coordination from a microprocessor.

the coregen outputs have the advantage that they can be used as needed, usually in large numbers.

In the above, the FIR filter would be possible of significantly higher performace, at the cost of FPGA area. The microprocessor can do anything, as long as it is given enough time.
 

FvM

Super Moderator
Staff member
Joined
Jan 22, 2008
Messages
48,398
Helped
14,251
Reputation
28,763
Reaction score
12,938
Trophy points
1,393
Location
Bochum, Germany
Activity points
280,086
The difference is in the operation mode. FPU aritmethic is performed sequentially under processor control, one operation at a time. Arithmetic core functions are placed in the data path and operating in parallel. Parallelization involves both higher speed and higher resource utilization.
 

Status
Not open for further replies.

Similar threads

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Top