Thanks to Mr. David Swanson for a very good article, I am very impressed
I want to comment this fragment (sure if only nobody will be angry):
"Many times, there is the software/hardware trade-off situation.
Typically, the software guy wins. If something can be done in software
versus doing it in hardware, trust me, it gets done in software.
After all, as long as there is space and bandwidth,
additional software is "free.""
In my opinion it can not be "software versus hardware trade-off situation" and SW's can win ,
because software was "build" on a hardware to do jobs that will be cost
effective(space, components...) than HW modules. And a "trade-off situation" can
appear only if SW's cost higher than HW's cost, and HW wins.
I am hardware and software engineer, for those that will say that I am for HW side.
Thanks for attention.
I detect a note of sarcasm in the "software is free" comment. I have been on the receiving end of that comment often enough that I have had to develop some standard responses, such as "If software is free, why is it so hard to change it during product validation?"
"Software is free as long as your requirements stay unchanged."
In the early days of automotive embedded design, most customers preferred (or at least pretended) to remain blissfully ignorant of the constraints of embedded design, since many came from the sheet metal world. Those days are changing with the new generation of engineers.
Two axioms remain from those early days.
1. Software ain't really free.
2. There is no such thing as a "simple software fix".
Blog Doing Math in FPGAs Tom Burke 15 comments For a recent project, I explored doing "real" (that is, non-integer) math on a Spartan 3 FPGA. FPGAs, by their nature, do integer math. That is, there's no floating-point ...