Well, the lsq, in every cycle, executes a function that checks whether or
not the cache is blocked. I would rather prefer that some variable is set
in recvRetry(), which indicates that the cache is now available for
servicing requests. Putting the code for sending packet in recvRetry()
seems to be introducing more complexity than necessary.
--
Nilay
On Mon, 14 Nov 2011, Andreas Hansson wrote:
Hi Nilay,
The idea behind the recvRetry is that the module that is trying to send
a packet (the LSQ/CPU in this case) should only retry once the receiving
module (the cache in this case) is available. The alternative is to
"poll" by repeatedly trying to send, but this creates unnecessary
function calls thus reducing simulation performance. (You would also
have to address the issue of deciding how often to poll etc.)
Andreas
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of
Nilay Vaish
Sent: 14 November 2011 18:26
To: [email protected]
Subject: [gem5-dev] Need for recvRetry()
Hi
I am try to do something with LSQ in the O3 CPU. There is function called
recvRetry(). As per the documentation in the source files and the source
code itself, it seems that the cache informs the processor side that an
earlier failed request can be retired now. Why do we need this function?
Would it not be simple to let the processor retry the request on its own?
--
Nilay
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev
-- IMPORTANT NOTICE: The contents of this email and any attachments are
confidential and may also be privileged. If you are not the intended recipient,
please notify the sender immediately and do not disclose the contents to any
other person, use it for any purpose, or store or copy the information in any
medium. Thank you.
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev
_______________________________________________
gem5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/gem5-dev
