Pirmin Vogel

Hi @Olivier-Dopeli , thanks for opening this issue. It's a long time ago, but if I remember correctly, the private FPU can't be used insdie bigPULP. The bigPULP cluster is...

> Thx @vogelpi for you review. I will comment on you review on Monday in more detail, but two short remarks: > > 1. @mustafa-khairallah Do you want to comment...

CHANGE AUTHORIZED: hw/ip/prim/pre_dv/prim_ascon/prim_ascon_round_tb/rtl/prim_ascon_round_tb.sv CHANGE AUTHORIZED: hw/ip/prim/rtl/prim_ascon_round.sv CHANGE AUTHORIZED: hw/ip/prim/rtl/prim_ascon_sbox.sv This PR touches RTL code not relevant for the Earlgrey-PROD tapeout. This is okay.

This still seems to be an issue. The `edn_disable_auto_req_mode` test has currently a pass rate of roughly 85%. This is not sufficient for V2(S). We need to investigate this for...

Update: #22752 fixed quite some test failures. The pass rate of edn_disable_auto_req_mode is now back up at 98%. The remaining failures have a predictable pattern though (see below). We should...

Since failure may be systematic and may be related to the top-level issue we want to debug, I am raising priority here.

Before we can merge this, we need to ensure it's also not used on the closed source side, e.g., in any of the closed source wrappers or the closed-source AST...

FYI, the questionable primitive got added in #13152 and was discussed / reviewed by people with visibility into the closed source side. I'll bring this up in a meeting with...

Thanks for the reminder @rswarbrick , I've now reached out to the PD team to ask.

Hi @rswarbrick , the PD team confirmed that the primitive is not used in the closed source and we can remove it.