FAQ  •  Login

HW 10 Timing Results

<<

kema

Newbie
Newbie

Posts: 41

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Thu Nov 19, 2015 7:19 pm

HW 10 Timing Results

  Code:
Max Number of Threads: 16
Sequential Result:     32.121040666359463
Sequential Time:       135.823 ms
Parallel Result:       32.121040666359441
Parallel Time:         11.744 ms
Reference Result:      32.121040688226245
<<

stephenalexanderhughespardy

Newbie
Newbie

Posts: 18

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Fri Nov 20, 2015 2:33 pm

Re: HW 10 Timing Results

Using OpenMP
Number of threads = 16
Result = 32.1210406664
Average elapsed time over 100 trials : 13.23ms
Using single core
Result = 32.1210406664
Average elapsed time over 100 trials : 143.3ms
<<

zhenyuanshen

Newbie
Newbie

Posts: 17

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Fri Nov 20, 2015 9:11 pm

Re: HW 10 Timing Results

sequential answer: 32.121
time cost: 145.606(msec)

parallel answer: 32.121
time cost: 13.6919(msec)
number of threads: 16
<<

erikolson

Newbie
Newbie

Posts: 21

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 2:47 am

Re: HW 10 Timing Results

Both are avg of 1000 runs
Sequential: 14.678899 ms
Parallel (16 threads): 1.791208004 ms
-Erik
<<

abhinavaabhinava

Newbie
Newbie

Posts: 16

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 12:51 pm

Re: HW 10 Timing Results

  Code:
Sequential:
The integral result is: 32.121040666359782
The time taken is 123.81999999999999 ms

OpemMP:
The integral result is: 32.121040666359242
The time taken is: 12.883675200864673 ms
The number of threads is: 16

Processor info:
Architecture:          x86_64
Byte Order:            Little Endian
CPU(s):                16
Thread(s) per core:    2
Core(s) per socket:    4
Socket(s):             2
NUMA node(s):          2
Model name:            Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz

Compiler info:
gcc version 4.8.3 20140911 (Red Hat 4.8.3-9) (GCC)   [With -O3 flag]
<<

erikolson

Newbie
Newbie

Posts: 21

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 1:20 pm

Re: HW 10 Timing Results

For some reason, can't edit my prev post. Ran tests on euler
CPU: Intel(R) Xeon(R) CPU E5520 @ 2.27 GHz
Compiler: GCC 4.8.3
Compiler flags: -O3 -std=c++11 -DNDEBUG

from avg of 1000 runs:
Seq. : 12.248575 ms
Parallel (16 threads): 1.583764 ms
-Erik
<<

guimingzhang

Newbie
Newbie

Posts: 19

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 1:37 pm

Re: HW 10 Timing Results

TIMING RESUTLS:
SEQUENTIAL took 161.000 ms. on 1 core
I=32.121040666359455 I_REF=32.121040688226245
PARALLEL took 16.000 ms. on 16 core
I=32.121040666359207 I_REF=32.121040688226245
speedup=10.06x

COMPILER:
gcc version 4.8.3 20140911 (Red Hat 4.8.3-9) (GCC) [with -O4 -std=gnu++11]

PROCESSOR:
vendor_id : GenuineIntel
cpu family : 6
model : 26
model name : Intel(R) Xeon(R) CPU E5520 @ 2.27GHz
stepping : 5
microcode : 0x19
cpu MHz : 1600.000
cache size : 8192 KB
physical id : 0
siblings : 8
core id : 3
cpu cores : 4
apicid : 7
initial apicid : 7
fpu : yes
fpu_exception : yes
cpuid level : 11
wp : yes
<<

jiashenboon

Newbie
Newbie

Posts: 34

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 3:59 pm

Re: HW 10 Timing Results

Silly question, but did you all use the CUDA timer to time the code? Or did you just use C's clock()?
<<

kema

Newbie
Newbie

Posts: 41

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 4:55 pm

Re: HW 10 Timing Results

jiashenboon wrote:Silly question, but did you all use the CUDA timer to time the code? Or did you just use C's clock()?

OpenMP providers its own timing function.
<<

gengyuyang

Newbie
Newbie

Posts: 21

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 10:15 pm

Re: HW 10 Timing Results

serial result is 32.121041
serial execution time is 126.266286 ms
OpenMP result is 32.121041
OpenMP execution time is 19.994740 ms
Number of processors = 16
Max threads = 16

Compiler: gcc

CPU info:
Processor number: 16
vendor_id : GenuineIntel
cpu family : 6
model: 26
model name: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz
stepping: 5
microcode : 0x19
cpu MHz : 1600.000
cache size : 8192 KB
siblings : 8
cpu cores : 4
fpu : yes
fpu_exception: yes
cpuid level: 11
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 popcnt lahf_lm ida dtherm tpr_shadow vnmi flexpriority ept vpid
bogomips : 4533.16
clflush size: 64
cache_alignment: 64
address sizes: 40 bits physical, 48 bits virtual
<<

danniwang

Newbie
Newbie

Posts: 7

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sat Nov 21, 2015 10:30 pm

Re: HW 10 Timing Results

compiler: gcc

processor model: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz

timing result:
Sequential Result: I = 32.121041
Sequential Timing: 172.493887ms
OpenMP Result: I = 32.121041
OpenMP Timing: 19.687154ms
<<

baoyunge

Newbie
Newbie

Posts: 37

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sun Nov 22, 2015 5:49 pm

Re: HW 10 Timing Results

Timing Result:
  Code:
the integration value of using OpenMP is: 32.121041
the elapsed time is: 15.37527 ms
the integration value of without using OpenMP is: 32.121041
the elapsed time is: 121.88262 ms


CPU Info:
  Code:
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                16
On-line CPU(s) list:   0-15
Thread(s) per core:    2
Core(s) per socket:    4
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 26
Model name:            Intel(R) Xeon(R) CPU           E5520  @ 2.27GHz
Stepping:              5
CPU MHz:               1600.000
BogoMIPS:              4532.66
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              8192K
NUMA node0 CPU(s):     0-3,8-11
NUMA node1 CPU(s):     4-7,12-15
<<

adammarkkaplansperling

Newbie
Newbie

Posts: 16

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Sun Nov 22, 2015 9:16 pm

Re: HW 10 Timing Results

Everything was compiled using g++ -O3 -std=c++11 -fopenmp

Euler head node (Xeon E5520 2.27 GHz, 8 cores, 16 threads)
Sequential...
Result : 32.12104066635947675
Time : 123ms

Parallel...
Result : 32.12104066635921384
Time : 13ms

Speedup : 9.46153846153846168


Graphics lab compute workstation (2x Xeon E5-2650 v3 2.30 GHz, 20 cores, 40 threads)
(using n = 10^6)
Sequential...
Result :32.12104066624463172
Time: 110ms

Parallel...
Result: 32.12104066635571797
Time: 10ms

Speedup: 11

(using n = 10^9)
Sequential...
Result :32.12104066624463172
Time: 106583ms

Parallel...
Result: 32.12104066635571797
Time: 4053ms

Speedup: 26.29731063409819924
<<

minghaodai

Newbie
Newbie

Posts: 13

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Mon Nov 23, 2015 12:00 am

Re: HW 10 Timing Results

sequential result: 32.111698 ms
sequential time: 155.420939 ms

Number of processors available: 16
Maximum number of threads available: 16

parallel result: 32.121098 ms
parallel time: 20.269103 ms

compiler: gcc version 4.8.3 20140911 (Red Hat 4.8.3-9) (GCC)
processor model: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz
<<

yaosong

Newbie
Newbie

Posts: 18

Joined: Fri Sep 04, 2015 12:51 pm

Unread post Tue Nov 24, 2015 1:23 pm

Re: HW 10 Timing Results

compiler: gcc
number of threads: 8

The openMP result is 32.121089
The openMP time is 30.55 ms
The sequential result is 32.121089
The sequential time is 163.392 ms

Thanks
Yao
Next

Return to ME759 Fall 2015: 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.