Arjan Bink
Arjan Bink
Maybe nothing actually needs to be done. Just cause exceptions as usual and leave it to the coprocessor whether to actually cause a fault or not.
>> Allowing instructions to writeback the result before being committed can solve this. This would then put all the complexity on the CPU, which would be a no go for...
Hi @andermattmarco Adding a ready on this interface would be really difficult to support on a core like the CV32E40P or CV32E40X as there is also no ready signal related...
If one core would handle the XIF memory requests that are related to the issue interface of another core, then we would be completely changing the protocol. I still think...
> what do people think? I agree, I think its too late to add anything if we want ratification this year, and I dont see the savings from these instructions...