Performance
Flash |
![](images/Image6.gif) |
|
DIGITAL Servers
for Windows NT Family
This document
presents industry-standard benchmark results for
the DIGITAL Servers for Windows NT for the
following benchmarks:
Application: Exchange LoadSim and Lotus
NotesBench
Compute & Throughput: AIM Server for
NT (Domain Server Mix, File Server Mix) and
AIM Suite VII for UNIX; Ziff-Davis (NetBench,
ServerBench, and WebBench); and the SPEC
Suite.
Database: Transaction Processing Council
(TPC-C)
As these results attest, DIGITALs 32-bit
Intel-based servers provide industry-leading
performance, as do the Alpha-based servers, which
fully exploit the benefits of Digitals
64-bit architecture. All benchmark results were
obtained under the Windows NT V4.0 or V4.0
Enterprise Edition (EE) operating system unless
otherwise noted (AIM Suite VII results are SCO
UnixWare V2.1.1). "nr" indicates that
the test has not been performed, and
"N/A" is not applicable to the
category.
Performance results are grouped into three
tables:
Table 1 shows results for DIGITAL Server
family models 500, 120x, 32xx and 330x
Table 2 shows results for DIGITAL Server
family models 510x, 530x, 710x and 73xx
Table 3 shows results for the AlphaServer 8x00
family under Windows NT.
These tables provide results for all current
DIGITAL Server models, with the most recent in
the gray columns; AIM Awards are shown in red.
This May 1998 version of DIGITAL Server
Performance Flash includes results to date for
DIGITAL Server models 3205 and 3210. A companion
document (called NT Benchmark Descriptions)
providing background information about the
benchmarks included in this Performance Flash is
now available on this website.
Table 1 DIGITAL Servers: Model 500, 120x, 32xx
and 330x Benchmark Results
|
DIGITAL Servers for
Windows NT: Models 500-3305
|
Benchmarks and Metrics |
500
233MHz
|
1200
233MHz
|
1205
266MHz
|
3200
266MHz
|
3205
300MHz
|
3210
333MHz
|
3300
56/400
|
3305
5/500
|
Exchange V5.5
LoadSim Medium Users |
nr
|
1800
|
|
5500-2P
3800-1P
|
|
|
4000
|
4000
|
Lotus Domino V4.5x
NotesBench |
nr
|
nr
|
nr
|
|
nr
|
nr
|
|
|
NotesMail Users |
|
|
|
1950-2P
|
|
|
1800
|
2000
|
NotesMark (thruput) |
|
|
|
2580
|
|
|
2479
|
2624
|
MailDB Users |
|
|
|
1400-1P
|
|
|
1450
|
1600
|
NotesMark (thruput) |
|
|
|
3236
|
|
|
3317
|
3726
|
* AIM
April 1998 Best Price/Performer in Price
Range ** AIM April 1998 Best Throughput
in Price Range
|
AIM Server NT
(Domain Server Mix) |
1.0A
NT |
2.1 NT |
2.1 NT
|
1.0A
NT
|
2.1 NT
|
2.1 NT
|
|
1.0NT
|
2 CPUs Peak
Performance (jobs/min) |
|
1777.3
|
1885.4
|
723.0
|
2042.8
|
2122.8
|
|
N/A
|
2 CPUs Sustained
Perf. (loads) |
|
1738.7*
|
1846.0
|
680.5
|
2001.8
|
2076.8
|
|
|
T.V.I. Index |
|
86
|
87
|
|
88
|
83
|
|
|
1 CPU Peak
Performance (jobs/min) |
374.1
|
|
1222.9
|
|
1350.0
|
1443.2
|
|
646.9
|
1 CPU Sustained
Perf. (loads) |
355.4
|
|
1191.1
|
|
1338.6
|
1429.7
|
|
626.8
|
T.V.I. Index |
89
|
|
81
|
|
86
|
79
|
|
86
|
AIM Server NT (File
Server Mix) |
1.0A NT
|
2.1 NT |
2.1 NT
|
1.0A
NT
|
2.1
NT |
2.1
NT |
|
1.0NT
|
2 CPUs Peak
Performance (jobs/min) |
N/A
|
|
1502.6
|
590.3
|
1633.6
|
1713.1
|
N/A
|
N/A
|
Benchmarks and
Metrics |
500
233MHz
|
1200
233MHz
|
1205
266MHz
|
3200
266MHz
|
3205
300MHz
|
3210
333MHz
|
3300 56/400
|
3305 5/500
|
2 CPUs Sustained
Perf. (loads) |
|
|
1448.8
|
636.1
|
1598.7
|
1685.7
|
|
|
T.V.I. Index |
|
|
88
|
|
80
|
88
|
|
|
1 CPU Peak
Performance (jobs/min) |
342.3
|
|
946.9
|
|
1076.7
|
1161.4
|
|
612.5
|
1 CPU Sustained
Perf. (loads) |
316.9
|
|
903.0
|
|
1057.0
|
1139.9
|
|
581.3
|
T.V.I. Index |
92
|
|
88
|
|
90
|
88
|
|
89
|
AIM Suite VII
File Server Mix (UNIX) |
|
|
|
|
|
|
|
nr |
2 CPU Peak
Performance (jobs/min) |
N/A
|
|
|
|
461.8
|
474.5
|
|
N/A |
2 CPU Sustained
Perf. (loads) |
|
|
|
|
427.8
|
442.7
|
|
|
T.V.I. Index |
|
|
|
|
76
|
75
|
|
|
AIM Suite VII
Shared System Mix (UNIX) System
|
|
|
|
|
|
|
|
|
2 CPU Peak
Performance (jobs/min) |
N/A
|
1359.3
|
|
1565.6 |
1706.6
|
1845.9
|
|
|
2 CPU Sustained
Perf. (loads) |
|
1425.8
|
|
1479.3
|
1577.0
|
1678.1
|
|
|
T.V.I. Index |
|
86
|
|
87
|
87
|
88
|
|
|
Ziff-Davis NetBench
5.01 60 clients-1P |
55.839
|
74.256
|
77.593
|
74.357
|
83.066
|
86.204
|
|
73.413
|
2P |
N/A
|
92.54
|
97.021
|
98.452
|
101.221
|
101.107
|
|
N/A
|
Ziff-Davis
ServerBench - 60 clients |
V4.0
|
V4.0 |
V4.0
|
V4.0
|
V4.1
|
V4.1
|
|
V4.0
|
1P |
114.511
|
192.295 |
205.834
|
|
215.755
|
240.790
|
|
213.903
|
2P |
|
298.428
|
310.003
|
296.533
|
327.269
|
345.154
|
|
|
Ziff-Davis WebBench
60 clients |
V1.1
|
V1.1
|
V1.1
|
V1.1
|
V2.0
|
V2.0
|
|
V1.1
|
Static 1P 1P |
747.425
|
992.004
|
1041.184
|
1153.571
|
851.891
|
889.667
|
|
860.679
|
Static 2P |
|
1387.621
|
1417.175
|
1424.904
|
1246.0
|
1269.942 |
|
|
TPC-C |
|
|
|
|
|
|
|
|
Tpm-C |
nr
|
nr
|
nr
|
nr
|
|
|
nr
|
nr
|
$/tpm-C |
nr
|
nr
|
nr
|
nr
|
|
|
nr
|
nr
|
SPEC CINT95 |
|
|
|
|
|
|
|
|
SPECint95 |
nr
|
nr
|
nr
|
nr
|
|
|
12.4
|
14.7
|
SPECint_base95 |
nr
|
nr
|
nr
|
nr
|
|
|
12.3
|
14.5
|
SPEC CFP95 |
|
|
|
|
|
|
|
|
SPECfp95 |
nr
|
nr
|
nr
|
nr
|
|
|
14.4
|
15.9
|
SPECfp_base95 |
nr
|
nr
|
nr
|
nr
|
|
|
13.3
|
14.8
|
SPEC CINT95
Homogeneous Capacity |
|
|
|
|
|
|
|
|
SPECint_rate95 |
nr
|
nr
|
nr
|
nr
|
|
|
112
|
132
|
SPECint_rate_base95 |
nr
|
nr
|
nr
|
nr
|
|
|
111
|
130
|
SPEC CFP95
Homogeneous Capacity |
|
|
|
|
|
|
|
|
SPECfp_rate95 |
nr
|
nr
|
nr
|
nr
|
|
|
130
|
143
|
SPECfp_rate_base95 |
nr
|
nr
|
nr
|
nr
|
|
|
120
|
133
|
Table 2 DIGITAL Servers: Model 5100, 5200,
530x, 710x and 73xx Benchmark Results
|
DIGITAL
Servers for Windows NT: Models 5100-7310
|
Benchmarks and Metrics |
5100
200MHz
|
5200
300MHz
|
5300 5/400
|
5305
56/533
|
7100 512KB 200MHz
|
7105 1MB
200MHz
|
7300 5/400
|
7305
5/533
|
7310
5/600
|
Exchange V5.5
LOADSIM Medium Users |
4000-2P |
5800-2P 4000-1P
|
8500-2P |
8500-2P 5600-1P
|
9000-4P
6750-2P
|
10,800-4P
7000-2P |
11,500-4P |
11,500-4P
|
|
|
|
|
|
|
|
|
|
|
|
Lotus Domino V4.5
NotesBench |
|
|
|
|
|
|
|
|
|
NotesMail Users |
1300-1P |
|
|
4000-2P |
2100-2P |
5160-4P
|
3100-2P |
6000-4P
|
*6000-4P
|
NotesMark (thruput) |
1726
|
|
|
5290
|
2646
|
6761
|
4050
|
7821
|
7820
|
$/User |
|
|
|
|
|
|
|
$19.80
|
|
MailDB Users |
1575-2P
975-1P
|
|
|
3100-2P
|
|
3870-4P
|
2325-2P |
4700-4P |
5000-4P |
NotesMark (thruput) |
|
|
|
7266
|
|
|
|
10847
|
10847
|
GroupWareB |
|
|
|
|
|
|
|
2100-4P |
|
*Bound by 2GB
memory limit in NT Server 4.0 |
|
|
|
|
|
|
|
6085
|
|
* AIM April 1998 Best Price/Performer in Price
Range ** AIM April 1998 Best Throughput in Price
Range
AIM Server NT
(Domain Server Mix) |
1.0A NT |
1.0A NT |
|
1.0A
NT
|
2.1
NT
|
2.1 NT
|
|
|
|
2 CPUs Peak
Performance (jobs/min) |
|
761.2
|
|
1151.9
|
|
|
|
|
|
2 CPUs Sustained
Perf. (loads) |
|
725.6
|
|
1092.9*
and **
|
|
|
|
|
|
T.V.I. |
|
89
|
|
87
|
|
|
|
|
|
4 CPUs Peak
Performance (jobs/min) |
N/A
|
N/A
|
N/A
|
N/A
|
2917.8
|
3973.0
|
nr
|
nr
|
nr
|
4 CPUs Sustained
Perf. (loads) |
N/A
|
N/A
|
N/A
|
N/A
|
2843.3
|
3830.4
|
nr
|
nr
|
nr
|
T.V.I. |
N/A
|
N/A
|
N/A
|
N/A
|
84
|
85
|
|
|
|
AIM
Server NT (File Server Mix) |
|
|
|
1.0A NT
|
2.1 NT
|
2.1 NT
|
|
|
|
2 CPUs Peak
Performance (jobs/min) |
|
710.2
|
|
1106.3
|
|
|
|
|
|
2 CPUs Sustained
Perf. (loads) |
|
683.1
|
|
1050.7
|
|
|
|
|
|
T.V.I. |
|
92
|
|
88
|
|
|
|
|
|
4 CPUs Peak
Performance (jobs/min) |
N/A
|
N/A
|
N/A
|
N/A
|
|
2949.9
|
nr
|
nr
|
nr
|
4 CPUs Sustained
Perf. (loads) |
N/A
|
N/A
|
N/A
|
N/A
|
|
2870.8
|
nr
|
nr
|
nr
|
T.V.I. |
N/A
|
N/A
|
N/A
|
N/A
|
|
80
|
|
|
|
AIM Suite
VIIShared Server (UnixWare) System
|
|
|
|
|
|
|
|
|
|
2 CPUs Peak
Performance (jobs/min) |
|
1720.5
|
|
Nr
|
|
nr
|
nr
|
nr
|
nr
|
2 CPUs Sustained
Perf. (loads) |
|
1599.8
|
|
Nr
|
|
nr
|
nr
|
nr
|
nr
|
T.V.I. |
|
87
|
|
|
* and **
|
|
|
|
|
4 CPUs Peak
Performance (jobs/min) |
|
|
|
|
2522.5
|
|
|
|
|
4 CPUs Sustained
Perf. (loads) |
|
|
|
|
2408.6
|
|
|
|
|
J.T.I |
|
|
|
|
86
|
|
|
|
|
|
|
266
MHz
|
|
|
|
|
|
|
|
Ziff-Davis NetBench
5.01- 4P |
N/A
|
N/A
|
|
|
99.060
|
106.894
|
nr
|
nr
|
nr
|
2P |
|
97.226
|
|
122.287
|
|
|
|
|
|
Ziff-Davis
ServerBench 4.0 4P |
N/A
|
N/A
|
|
|
622.465
|
670.59
|
nr
|
nr
|
nr
|
2P |
|
320.407
|
|
533.076
|
419.262
|
|
|
|
|
Ziff-Davis WebBench
1.1 Static 4P |
N/A
|
N/A
|
|
|
1456.229
|
1488.787
|
nr
|
nr
|
nr
|
2P |
|
1418.792
|
|
1521.550
|
|
|
|
|
|
1P |
|
|
|
1275.658 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
TPC-C 4 CPUs tpm-C |
N/A
|
N/A
|
N/A
|
N/A
|
9578
|
11,386
|
nr
r
|
NDA
|
|
$/tpm-C |
|
|
|
|
$45
|
$32
|
|
|
|
2 CPUs tpm-C |
nr
|
Nr
|
nr
|
NDA
|
|
|
|
|
|
$/tpm-C |
|
|
|
|
|
|
|
|
|
Benchmarks and
Metrics |
5100
200MHz
|
5200
300MHz
|
5300
5/400
|
5305 56/533
|
7100-512KB
200MHz
|
7105-1MB
200MHz
|
7300
5/400
|
7305 5/533
|
7310 5/600
|
SPEC CINT95 |
|
|
|
|
|
|
|
|
|
SPECint95 |
nr
|
Nr
|
nr
|
16.2
|
Nr
|
nr
|
|
16.9
|
19.3
|
|
|
|
|
|
|
|
|
|
|
SPECint_base95 |
nr
|
Nr
|
nr
|
15.9
|
Nr
|
nr
|
11.4
|
16.8
|
19.2
|
|
|
|
|
|
|
|
|
|
|
SPEC CFP95 |
|
|
|
|
|
|
|
|
|
SPECfp95 |
nr
|
Nr
|
nr
|
21.7
|
Nr
|
nr
|
|
21.7
|
28.6
|
SPECfp_base95 |
nr
|
Nr
|
nr
|
20.2
|
Nr
|
nr
|
15.58
|
20.3
|
26.6
|
|
|
|
|
|
|
|
|
|
|
SPEC CINT95
Homogeneous Capacity |
|
|
|
|
|
|
|
|
|
SPECint_rate95 |
nr
|
Nr
|
nr
|
146
|
Nr
|
nr
|
|
152
|
173
|
SPECint_rate_base95 |
nr
|
Nr
|
nr
|
143
|
Nr
|
nr
|
|
152
|
174
|
|
|
|
|
|
|
|
|
|
|
SPEC CFP95
Homogeneous Capacity |
|
|
|
|
|
|
|
|
|
SPECfp_rate95 |
nr
|
Nr
|
nr
|
195
|
Nr
|
nr
|
|
196
|
257
|
SPECfp_rate_base95 |
nr
|
Nr
|
nr
|
183
|
Nr
|
nr
|
|
183
|
239
|
Table 3 AlphaServer 8x00 NT: Models 8400 and
8200 Benchmark Results
Benchmarks and
Metrics |
8400
5/625
|
8400
5/440
|
8200
5/625
|
8200 5/440
|
AIM Server NT
(Domain Server Mix) |
|
|
|
|
4 CPUs Peak
Performance (jobs/min) |
nr
|
nr
|
nr
|
4943.5
|
4 CPUs Sustained
Perf. (loads) |
nr
|
nr
|
nr
|
4653.1*
|
* AIM April 1998 Best
Throughput > $45,000
|
|
|
|
|
|
|
|
|
|
TPC-C 14 CPUs tpm-C |
nr
|
nr
|
nr
|
NDA
|
$/tpm-C |
|
|
|
|
DIGITAL evaluated the performance of the
DIGITAL Server family using industry-standard
benchmarks. These benchmarks allow comparisons
across vendors systems. Performance
characterization is just one "data
point" to be used in conjunction with other
purchase criteria such as features, service, and
price.
For more information on DIGITAL Servers for
Windows NT, visit our web site at
http://www.windows.digital.com/ or contact your
local DIGITAL sales representative. Please send
questions and comments about the information
presented in this Performance Flash to Internet
address: csgperf@zko.dec.com or to
ava.schutzman@digital.com.
DIGITAL believes the information in this
publication is accurate as of its publication
date; such information is subject to change
without notice. DIGITAL is not responsible for
any inadvertent errors. DIGITAL conducts its
business in a manner that conserves the
environment and protects the safety and health of
its employees, customers, and the community.
DIGITAL, the DIGITAL logo, the
AlphaPowered logo, DIGITAL Servers and
AlphaServer are trademarks of Digital
Equipment Corporation.
The Intel Inside logo is a registered
trademark of Intel Corporation.
AIM is a trademark of AIM Technology, Inc.
NetBench, ServerBench, and WebBench are
trademarks of Ziff-Davis, Inc.
SPEC, SPECint95, SPECfp95, SPECrate_int95,
and SPECrate_fp95 are trademarks of the
Standard Performance Evaluation Corporation.
TPC-C Benchmark and tpm-C are trademarks
of the Transaction Processing Performance
Council.
Windows NT and Exchange are trademarks of
Microsoft, Inc.
Lotus and Domino are trademarks of Lotus
Development Corporation.
UNIX is a registered trademark in the
United States and other countries,
exclusively licensed through X/Open Company
Ltd.
SCO UnixWare is a trademark of the Santa
Cruz Operation, Inc.
Copyright 1998 Digital Equipment
Corporation. All rights reserved.
|