??? 03/16/05 23:16 Read: times |
#89823 - I would be Responding to: ???'s previous message |
Are you sure you need two processors?
I would be, if the load was anything significant. I am curretly working with two 50 MIPS f126, one LPC932 and a Cypress USB host in the same box. Handling it that way is 100 times easier to do than trying to run it all on one processor. When the processors are separate, they can take care of urgent business NOW!!! you never have to wait for something else to complete. With a logical divison, you can cut the intercommunication down to almost nothing and I am doing it with a 400k IIC. Ok the LPC is a "convenience processor" used to cut PCB interconnect by 16 lines. A previous design with a single processor suffer from the "monthly hiccup syndrome" because of being single processor supposed to run so-called multitasking. The developers did not take the little "what if a, b, c and d happen within the same 3 ns" into consideration and there is no way in hades one processor can do that. Erik PS Oh what a joy that the SILabs debugger can run multiple instances so you can see all 3 processors at the same time. |
Topic | Author | Date |
Contemplating multiprocessor | 01/01/70 00:00 | |
fifo | 01/01/70 00:00 | |
and also | 01/01/70 00:00 | |
multiprocessor communication | 01/01/70 00:00 | |
ACKs | 01/01/70 00:00 | |
You want it all and you want it for free | 01/01/70 00:00 | |
Why not HW I2C or SPI | 01/01/70 00:00 | |
Why not HW I2C or SPI | 01/01/70 00:00 | |
USB ??? | 01/01/70 00:00 | |
USB !!! | 01/01/70 00:00 | |
USB | 01/01/70 00:00 | |
You Correct Sir | 01/01/70 00:00 | |
USB != I2C | 01/01/70 00:00 | |
USB > I2C![]() | 01/01/70 00:00 | |
do not multimaster | 01/01/70 00:00 | |
hmm | 01/01/70 00:00 | |
concurrence | 01/01/70 00:00 | |
This is why | 01/01/70 00:00 | |
depends on data rate | 01/01/70 00:00 | |
Normally | 01/01/70 00:00 | |
Are You Sure | 01/01/70 00:00 | |
I would be | 01/01/70 00:00 | |
I would be | 01/01/70 00:00 | |
it works for me | 01/01/70 00:00 | |
Are You Sure | 01/01/70 00:00 | |
IIC speed - no limit | 01/01/70 00:00 | |
nixed by other team members | 01/01/70 00:00 | |
Multi-Proc Xface | 01/01/70 00:00 | |
exactly | 01/01/70 00:00 | |
Shift register (Mode 0)? | 01/01/70 00:00 | |
Time savers | 01/01/70 00:00 |