Syracuse University Syracuse University
SURFACE SURFACE
Northeast Parallel Architecture Center College of Engineering and Computer Science
1995
Software Tool Evaluation Methodology Software Tool Evaluation Methodology
Salim Hariri
Syracuse University
Sung Yong Park
Syracuse University
Rajashekar Reddy
Syracuse University
Mahesh Subramanyan
Syracuse University
Follow this and additional works at: https://surface.syr.edu/npac
Part of the Computer Sciences Commons
Recommended Citation Recommended Citation
Hariri, Salim; Park, Sung Yong; Reddy, Rajashekar; and Subramanyan, Mahesh, "Software Tool Evaluation
Methodology" (1995).
Northeast Parallel Architecture Center
. 46.
https://surface.syr.edu/npac/46
This Working Paper is brought to you for free and open access by the College of Engineering and Computer
Science at SURFACE. It has been accepted for inclusion in Northeast Parallel Architecture Center by an authorized
administrator of SURFACE. For more information, please contact surface@syr.edu.
PCs
DEC
WSs
Sun
WSs
Front
Ends
FDDI
switch
FDDI
concentrator
DECmpps
NYNET
OC3/OC12
FORE
switch
SGI
Network
Server
Allnode
switch
DECNIS
Router
SP1
CM-5
nCUBE
FDDI
Ethernet
HiPPI
ATM
Allnode
DS3/ATM
X terminal
server
Xterminals
IBM R/6000
cluster
Alpha
Cluster
File Servers
(50 GB+)
* This diagram doesn't reflect the details of the actual network topology.
0
50
100
150
200
250
300
350
0 10 20 30 40 50 60 70
Execution Time (msec)
Message Size (Kbytes)
Broadcast Timing on ATM using 4 SUNs
PVM
p4
0
100
200
300
400
500
600
0 10 20 30 40 50 60 70
Execution Time (msec)
Message Size (Kbytes)
Broadcast Timing on Ethernet using 4 SUN
PVM
p4
Express
0
100
200
300
400
500
600
700
0 10 20 30 40 50 60 70
Execution Time (msec)
Message Size (Kbytes)
Ring(Loop) Timing on ATM using 4 SUNs
PVM
p4
0
100
200
300
400
500
600
700
800
0 10 20 30 40 50 60 70
Execution Time (msec)
Message Size (Kbytes)
Ring(Loop) Timing on Ethernet using 4 SUNs
PVM
p4
express
0
2000
4000
6000
8000
10000
12000
0 10000 20000 30000 40000 50000 60000 70000 80000 90000 100000
Execution Time (msec)
Vector Size (# of integers)
Vector Sum Timing 4 SUNs
p4
express
p4-NYNET
0.004
0.005
0.006
0.007
0.008
0.009
0.01
0.011
0.012
0.013
0.014
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
2D-FFT on FDDI
Express
p4
PVM
1
1.5
2
2.5
3
3.5
4
4.5
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
JPEG Simulation on FDDI
Express
p4
PVM
0.2
0.4
0.6
0.8
1
1.2
1.4
1.6
1.8
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Monte Carlo Integration on FDDI
Express
p4
PVM
0.4
0.45
0.5
0.55
0.6
0.65
0.7
0.75
0.8
0.85
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Sorting by Sampling on FDDI
Express
p4
PVM
0
0.01
0.02
0.03
0.04
0.05
0.06
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
2D-FFT on IBM-SP1 (Switch)
Express
p4
PVM
1
2
3
4
5
6
7
8
9
10
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
JPEG Simulation on IBM-SP1 (Switch)
Express
p4
PVM
0
0.5
1
1.5
2
2.5
3
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Monte Carlo Integration on IBM-SP1 (Switch)
Express
p4
PVM
0.8
1
1.2
1.4
1.6
1.8
2
2.2
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Sorting by Sampling on IBM-SP1 (Switch)
Express
p4
PVM
0.01
0.012
0.014
0.016
0.018
0.02
0.022
0.024
0.026
1 1.5 2 2.5 3 3.5 4
Execution Time (seconds)
Number of Processors
2D-FFT on ATM (NYNET)
p4
PVM
6
8
10
12
14
16
18
20
22
1 1.5 2 2.5 3 3.5 4
Execution Time (seconds)
Number of Processors
JPEG Simulation on ATM (NYNET)
p4
PVM
2
3
4
5
6
7
8
1 1.5 2 2.5 3 3.5 4
Execution Time (seconds)
Number of Processors
Monte Carlo Integration on ATM (NYNET)
p4
PVM
1
2
3
4
5
6
7
8
9
10
1 1.5 2 2.5 3 3.5 4
Execution Time (seconds)
Number of Processors
Sorting by Sampling on ATM (NYNET)
p4
PVM
0
0.2
0.4
0.6
0.8
1
1.2
1.4
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
2D-FFT on Ethernet
Express
p4
PVM
5
10
15
20
25
30
35
40
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
JPEG Simulation on Ethernet
Express
p4
PVM
2
3
4
5
6
7
8
9
10
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Monte Carlo Integration on Ethernet
Express
p4
PVM
2
4
6
8
10
12
14
16
18
20
22
1 2 3 4 5 6 7 8
Execution Time (seconds)
Number of Processors
Sorting by Sampling on Ethernet
Express
p4
PVM
