Hi Davesh,

 1.  Yes.
 2.  If we find a row-hit that can be performed seamlessly we stop the 
iteration. In all other cases, we iterate over the entire queue. The selection 
is guided by minBankPrep.
 3.  Bank parallelism is achieved by looking at the requests to all banks. Try 
running build/NULL/gem5.opt –r configs/dram/sweep.py, and then 
util/dram_sweep_plot.py m5out, this will show you how good the controller is at 
using bank parallelism.

Andreas

From: gem5-users 
<gem5-users-boun...@gem5.org<mailto:gem5-users-boun...@gem5.org>> on behalf of 
Davesh Shingari <shingaridav...@gmail.com<mailto:shingaridav...@gmail.com>>
Reply-To: gem5 users mailing list 
<gem5-users@gem5.org<mailto:gem5-users@gem5.org>>
Date: Thursday, 23 July 2015 23:21
To: gem5 users mailing list <gem5-users@gem5.org<mailto:gem5-users@gem5.org>>
Subject: [gem5-users] [DRAM] FRFCFS: Reordering Request Queue & Bank Parallelism

Hi

I am having few doubts in FRFCFS implementation. Please help in clarifying the 
same. As per my understanding "processNextReqEvent" calls "chooseNext" which 
calls "reorderQueue" and then returns back and then calls "doDRAMAccess". The 
reoderQueue and hence chooseNext return a bool value found_packet and once it 
is true, then  doDRAMAcess acts on the front packet of the queue.

My question is:
Q.1: So reorderQueue brings the packet to the front of the queue on basis of 
FRFCFS logic?
Q.2: If not then what does it do? If yes, then how is it doing. As per my 
understanding we should traverse the WHOLE queue and look at the request which 
have openRow in the banks, and service them. But in the implementation I see 
that we look at whether there is openRow or not. If not then we call 
minBankPrep. I could not completely understand what minBankPrep do. Does it 
reorder the queue?
Q.3: How is bank parallelism achieved in Gem5. I am having hard time figuring 
out how requests associated with different banks are processed in parallel?

Any guidance will be highly appreciated.

--
Have a great day!

Thanks and Warm Regards
Davesh Shingari
Master's in Computer Engineering [EE]
Arizona State University

davesh.shing...@asu.edu<mailto:davesh.shing...@asu.edu>
[https://mailfoogae.appspot.com/t?sender=ac2hpbmdhcmlkYXZlc2hAZ21haWwuY29t&type=zerocontent&guid=69cae66c-386f-43ee-a690-bf0753bec2cf]ᐧ

-- 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.

ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, Registered 
in England & Wales, Company No: 2557590
ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, 
Registered in England & Wales, Company No: 2548782
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to