VaginAY

1. FO4 for 28 nm is about 10 picoseconds. This means that the frequency you reached was about 2 GHz? 2. FO4 for 90 nm is about 30 picoseconds. This...

The results after the retiming are much better. However, there are paths that the length exceeds 100 FO4. I added the list of the first 100 to the attachment. [crit_paths.txt](https://github.com/ucb-bar/riscv-boom/files/1512789/crit_paths.txt)

This is (jtag)MegaBoomConfig. Here this path without cells and delays (NDA prohibition), but with fanouts: [first_path.txt](https://github.com/ucb-bar/riscv-boom/files/1514360/first_path.txt) And here is another 100 critical paths after changing library set (90nm too). Timings...

The results of the proceedings showed that the problem was in the set of libraries. Sorry for the disinformation about first case. But second case still actual.

Good day, some new information after delay. 1. Max freq on 90 LP tech is 180 MHz. 1FO4 is 48.5 ps. So ~124FO4 for design. Rocket give us about ~...

I believe that the indivisibility (monolithicity) of the final image obtained when working with graalvm is one of its key disadvantages. Especially for large and complex applications. I hope that...

Confirm for 123 version. After make all patches from meta-browser applicable (or remove such backport). Pathces from meta-imx doesn't help.