Replies: 4 comments 1 reply
-
|
Did you apply retiming to the FPU? |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
I checked the generated verilog, for FMAC, it directly use the "*" operator, Doesn't the rocket generator implement the FMAC? Thanks |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
Does Anyone have some idea about this ? THANKS |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
@IC-Dream do you have any update on this? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I synthesized the rocket core based on 28nm processing and also substituted the behavior SRAMs with the vendor-specific SRAMs, got the following timing report:

Critical Path:

That's is to say, the rocket core could run at most 500Mhz. Compared to the official data(page 15), there is a big gap. According to the official data, Based on 40nm processing, the rocket core could run over 1Ghz.
https://www.hotchips.org/wp-content/uploads/hc_archives/hc27/HC27.25-Tuesday-Epub/HC27.25.70-Processors-Epub/HC27.25.731-RISC-V-Lee-UCB-V4.with-backup.pdf
Why does the timing get worse ? or Have you did some specific optimization, but didn't release on github?
Any help will be appreciated.
Beta Was this translation helpful? Give feedback.
All reactions