Date: | Thu, 15 Oct 2009 16:35:06 +0900 |
---|---|
From: | 안정섭 <jeong.seob.ahn@xxxxxxxxx> |
Subject: | [Gems-users] Cache miss of supervisor mode |
Hi all.
I have been running some bench marks like splash-2, specjbb, parsec, etc.
My problem is that cache misses of supervisor mode is higher than that of user mode.
How can i resolve it?
Cache misses(L1 and L2) of supervisor mode is over 90%.
Mmy configuration is followings: -16 core
- 32kb L1 256kb L2(both are private)
- MOESI_SMP_directory
- simple network (PT to PT)
I attached one ruby dump file. u can see strange statistics at this file.
Is this proportion(user vs supervisor) right? it seems unreasonable.
As i know, some people have same problem but there is no answer.
And another question, I use MOESI_SMP_protocol in order to mimics CMP_directory with L2 private cache. But i wonder where the storage where directory structure(like sharer) is stored is. As i know in SMP, directory is stored in memory. if so, a L2 cache miss makes off-chip traffic. right?
But if in CMP, directory is stored in directory cache, L2 cache misses in CMP is on-chip traffic.
How is this difference removed?
I hope u can fully understand my question. I'm worry because of my poor english.
Thank u.
|
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Garnet Network parameters, Niket Agarwal |
---|---|
Next by Date: | [Gems-users] Thread assignment to cores, niranjan soundararajan |
Previous by Thread: | Re: [Gems-users] A few doubts regarding garnet, gems and errors faced during simulations, Niket Agarwal |
Next by Thread: | [Gems-users] Can the benchmarks run one by one?, gt f |
Indexes: | [Date] [Thread] |