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
-
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