| Login | | Don't have an account yet? You can create one. As a registered user you have some advantages like theme manager, comments configuration and post comments with your name. | |
| Who's Online | There are currently, 50 guest(s) and 0 member(s) that are online.
You are Anonymous user. You can register for free by clicking here | |
 | |
|
Verification Guild: Forums |
|
| View previous topic :: View next topic |
| Author |
Message |
Newsletter Original Contribution

Joined: Dec 08, 2003 Posts: 1107
|
Posted: Fri Jun 14, 2002 11:00 pm Post subject: How to represent & document pipelined FSM? |
|
|
(Originally from Issue 3.10, Item 9.0)
From: Adam Krolnik
I am looking for techniques to present a pipelined FSM design in a
document. An unpipelined FSM is the common (degenerate) case where the
FSM controls the aspects of the local machine. A pipelined FSM can
handle multiple operations that must operate in the same manner
(sequence) but separated in time.
The actual design was built as pipelined logic. But this style is very
difficult to review/analyze/etc. Has anyone been able to create a
representation and a reasonable (FSM like) coding style to support
this kind of a design? |
|
| Back to top |
|
 |
Newsletter Original Contribution

Joined: Dec 08, 2003 Posts: 1107
|
Posted: Mon Jul 08, 2002 11:00 pm Post subject: How to represent & document pipelined FSM? |
|
|
(Originally from Issue 3.11, Item 4.0)
From: Illan Glasner
How about using excel spread-sheet. here an example of pipeline using
CAM and two conscutive ZBT.
0 0
1 0 search 0
2 1
3 1 search 1 AGGP
4 2
5 2 search 2
6 3 rbus has result 0
7 3 search 3 rbus has result 0
8 4 rbus has result 1
9 4 rbus has result 1 DLUT,0
10 5 rbus has result 2
11 5 rbus has result 2 NLUT,0
12 6 rbus has result 3 NLUT,1
13 6 rbus has result 3
14 7 rbus_reg3 has result0 GLUT
15 7 rbus_reg3 has result0 PLCR
...
Basicly each line is the fast clock than another colomn might show a
slower clock or the sequence and then each device at that particular
sequence what it get or send out etc. |
|
| Back to top |
|
 |
Newsletter Original Contribution

Joined: Dec 08, 2003 Posts: 1107
|
Posted: Sun Aug 04, 2002 11:00 pm Post subject: How to represent & document pipelined FSM? |
|
|
(Originally from Issue 3.12, Item 3.0)
From: Thomas C. Jones
The classic text "Computer Architecture A Quantitative Approach" by
Hennessy and Patterson shows a pretty standard way of representing
pipelines and pipeline behavior that I have also seen used in
industry. Repeated here, without permission, is an example of their
pipelined DLX architecture with 5 stages (Fig 6.1, pg 259 of my
edition):
1) IF - instruction fetch
2) ID - instruction decode
3) EX - execution (effective address calc)
4) MEM - memory access
5) WB - write back
In this example time flows left to right. A new instruction enters
the pipe each cycle (best viewed in courier or other fixed font)
Clock
Inst 1 2 3 4 5 6 7 8 9
i IF ID EX MEM WB
i+1 IF ID EX MEM WB
i+2 IF ID EX MEM WB
i+3 IF ID EX MEM WB
i+4 IF ID EX MEM WB
^
|
At this point the pipe is full.
There are further examples showing hazards, etc. where specific
instruction types (ADD, MOV, etc) interact and hazards must be
detected and corrected by bypass or pipeline stall.
An alternative is to transpose it such that time flows from top to
bottom. It may work better depending on your paper size and
orientation.
Anyway, get the book (ISBN 1-55860-069-8) - it's worth whatever
they're charging for it these days. |
|
| Back to top |
|
 |
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|
| |
|
|