FAQ  •  Login

HW 7 Result Posting

Moderator: Dan Negrut

<<

ME964KwangC

Newbie
Newbie

Posts: 11

Joined: Tue Jan 25, 2011 12:03 pm

Unread post Fri Apr 01, 2011 3:16 pm

HW 7 Result Posting

Name: Kwang Won Choi

Case #Node #Core #Process Average Time
1 1 1 1 0.1312
2 1 4 4 0.0386
3 1 8 8 0.0208
4 2 4 8 0.017
5 4 2 8 Not available to use 4 nodes due to many users

Executed on Newton
<<

Andrew Seidl

Administrator
Administrator

Posts: 193

Joined: Thu Oct 28, 2010 11:54 am

Unread post Sun Apr 03, 2011 1:21 pm

Re: HW 7 Result Posting

FYI we've been having some issues with MPI and the Infiniband HCAs. For shorter calculations (such as for this assignment), this should only affect the 4 node run. I've taken one of the misbehaving nodes offline, so as of right now my old failed jobs are completing. It appears to be a hardware issue, though I'll have to investigate further.

Note that if your jobs fail, you do not have to create a new one: just right click and select 'Requeue Job'. Another tip: create a single job for all 5 tasks in the assignment instead of 5 separate jobs.

And if anyone is interested, an actual issue/bug tracker is in the pipeline (I've had it running internally since January), but I won't have time to open it up to everyone until after Euler is up & running.
<<

ME964AbhiramiS

Newbie
Newbie

Posts: 25

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Mon Apr 04, 2011 12:10 pm

Re: HW 7 Result Posting

Is it all right to skip the 4 node job while submitting results for the HW?
<<

ME964IanO

Newbie
Newbie

Posts: 9

Joined: Wed Jan 12, 2011 1:53 pm

Location: UW-Madison

Unread post Mon Apr 04, 2011 6:41 pm

Re: HW 7 Result Posting

Nodes Cores/Node Execution Time (ms)
1 1 140
1 4 47
1 8 32
2 4 3027
4 2 3042
2 8 3027
<<

ME964KuyaT

Newbie
Newbie

Posts: 20

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Mon Apr 04, 2011 11:36 pm

Re: HW 7 Result Posting

# Node / #Core / Time[ms]
1/1/135
1/4/36
1/8/26
2/4/19
4/2/21

All of them came up with same answer
I is approximately 32.1212, Error is 0.000148254
<<

ME964FuqiangG

Newbie
Newbie

Posts: 16

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Tue Apr 05, 2011 11:41 am

Re: HW 7 Result Posting

#Node #Core I Time(ms)
1 1 32.1209665234315200 144.038
1 4 32.1209665234312780 45.7611
1 8 32.1209665234306100 30.2752
2 4 32.1209665234306100 36.1125
4 2 32.1209665234306100 35.3292

On Newton
<<

ME964BrianD

Jr. Member
Jr. Member

Posts: 77

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Tue Apr 05, 2011 5:37 pm

Re: HW 7 Result Posting

Node Cores I Time(ms)
1 1 32.1210889328307 113.690336
1 4 32.1210889328307 26.662499
1 8 32.1210889328298 16.96729
2 4 32.1210889328298 20.247639
4 2 32.1210889328298 21.727386
<<

ME964AbhiramiS

Newbie
Newbie

Posts: 25

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Tue Apr 05, 2011 9:00 pm

Re: HW 7 Result Posting

Nodes Cores I Time (s)
1 1 32.1210406663595 0.125379
1 4 32.1210406663586 0.032814
1 8 32.1210406663595 0.023620
2 4 32.1210406663595 0.019234
4 2 32.1210406663595 0.021005
<<

Andrew Seidl

Administrator
Administrator

Posts: 193

Joined: Thu Oct 28, 2010 11:54 am

Unread post Wed Apr 06, 2011 1:44 pm

Re: HW 7 Result Posting

  Code:
 Nodes  Cores/Node        Result        Time (s)
  1        1       32.121040666359782  0.101473
  1        4       32.121040666359548  0.049532
  1        8       32.121040666358873  0.025314
  2        4       32.121040666358873  0.019234
  4        2       32.121040666358873  0.021832
<<

ME964BenjaminW

Jr. Member
Jr. Member

Posts: 85

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Wed Apr 06, 2011 8:13 pm

Re: HW 7 Result Posting

Integral Time
1 Node 1 Core 32.121 140
1 Node 4 Cores 32.121 125
1 Node 8 Cores 32.121 125
2 Nodes 4 Cores 32.121 109
4 Nodes 2 Cores 32.121 125
<<

ME964TimothyC

Newbie
Newbie

Posts: 7

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Thu Apr 07, 2011 2:14 pm

Re: HW 7 Result Posting

Nodes Cores I Time(ms)
1 1 32.1210406663597 144.025
1 4 32.1210406663595 63.751
1 8 32.1210406663588 23.556
2 4 32.1210406663588 19.986
4 2 32.1210406663588 23.799
<<

ME964BrianD

Jr. Member
Jr. Member

Posts: 77

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Thu Apr 07, 2011 2:19 pm

Re: HW 7 Result Posting

After bug fix. Did not change relative results.

Trial Nodes Cores I Time (ms)
1 1 1 32.1210406663598 130.786222
2 1 4 32.1210406663598 61.780183
3 1 8 32.1210406663589 16.05749
4 2 4 32.1210406663598 40.234976
5 4 2 32.1210406663587 67.668592
<<

ME964ChinaA

Newbie
Newbie

Posts: 15

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Thu Apr 07, 2011 4:30 pm

Re: HW 7 Result Posting

Nodes Cores Computation time(ms) Result
1 1 133.893 32.1210406663595
1 4 36.7042 32.1210406663586
1 8 19.0019 32.1210406663595
2 4 19.7346 32.1210406663595
4 2 19.8431 32.1210406663595
<<

ME964StuartS

Newbie
Newbie

Posts: 11

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Thu Apr 07, 2011 4:51 pm

Re: HW 7 Result Posting

Nodes/Cores per Node/Computed Integral/Time (s)
1 1 32.121041 0.132201
1 4 32.121041 0.035742
1 8 32.121041 0.022761
2 4 32.121041 0.024136
4 2 32.121041 0.021089
<<

ME964RehanA

Newbie
Newbie

Posts: 12

Joined: Wed Jan 12, 2011 1:53 pm

Unread post Thu Apr 07, 2011 5:33 pm

Re: HW 7 Result Posting

Config Time(s)
1-1 0.141
1-4 0.14
1-8 0.171
2-4 0.031
4-2 0.031

Integral is approximately 32.121, Error is 2.18674e-008
Next

Return to ME964 Spring 2011: High Performance Computing

Who is online

Users browsing this forum: No registered users and 1 guest

cron
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group.
Designed by ST Software.