[gem5-users] Re: Garnet - Configure buffer depth - Garnet synthetic traffic - Standalone protocol

2024-08-29 Thread C.-Y. Wu via gem5-users
Hello, My understanding is that, for a (Garnet) router, the VC buffer size is marked by the (initial) credit value. For example, the outport-East of Router 0 is connected to the inport-West of Router 1. The outport-East of Router 0 keeps all the credit values, corresponding to all VCs of Router 1

[gem5-users] Re: Ruby Message handling

2024-03-04 Thread C.-Y. Wu via gem5-users
Hello Vlad, I don't think you can dynamically cast a Message pointer (MsgPtr) to RubyRequestType. Do you mean a RequestMsg pointer or a RubyRequest pointer? If you used dynamic_cast in NetworkInterface.cc to cast a MsgPtr to a RequestMsg pointer, you should be able to call the getType function. (

[gem5-users] Re: adding fields to SLICC MemoryMsg structure

2023-10-30 Thread C.-Y. Wu via gem5-users
Hello James, Have you tried: int src_cpuId, default="-1", desc="the id of the cpu core that originated the request"; I think -1 might need to be between quotation marks. Chia On Sat, Oct 28, 2023 at 10:00 PM James Pangia via gem5-users < gem5-users@gem5.org> wrote: > Hello all, > > I am tr

[gem5-users] dest_queueing_delay in the function incrementStats in NetworkInterface.cc

2023-09-29 Thread C.-Y. Wu via gem5-users
Hello everyone, I ran some simulations with Garnet and noticed that the dest_queueing_delay is always 0. (Only the queueing_delay (queueing_latency) is printed in stats.txt; queueing_delay is the sum of src_queueing_delay and dest_queueing_delay.) After checking the code and debug traces, I think