Hi Yuxin,
Below our our benchmark results. Figures are in cycles and do not include the cost of a the system call.
Intra-AS Call 756
Intra-AS ReplyWait 742
Inter-AS Call 980
Inter-AS ReplyWait 987
Inter-AS Call (Low to High) 1050
Inter-AS ReplyWait (High to Low) 1540
Inter-AS Call (High to Low) 1463
Inter-AS ReplyWait (Low to High) 1043
Inter-AS Send 1043
Inter-AS Call(10) 1008
Inter-AS ReplyWait(10) 1015
- Alex
________________________________________
From: Devel [devel-bounces@sel4.systems] on behalf of Yuxin Ren [ryx@gwmail.gwu.edu]
Sent: Saturday, 18 October 2014 08:32
To: devel@sel4.systems
Subject: [seL4] IPC performance for slowpath
________________________________
Hi All,
I find there have slow and fast path for IPC.
I want to know the performance difference between those two.
More accurate, on x86, how many cycles for slow path round-trip ipc between two address space?(on single core)
And how many for fast path?
Thank you very much.
Yuxin
The information in this e-mail may be confidential and subject to legal professional privilege and/or copyright. National ICT Australia Limited accepts no liability for any damage caused by this email or its attachments.