Intel Xeon Octa Core E7 4830 2 13ghz BX80615E74830 User Manual

WHITE PAPER  
Intel® Xeon® Processor E7 Family  
Performance Brief: Model Number Characteristics and Impact to Performance  
Intel® Xeon® Processor E7 Family  
Performance and Model Numbers  
Intel® Xeon® Processor E7-8800/4800/2800 Product Families Characteristics and Impact to Performance  
EXECUTIVE SUMMARY  
Just like many automobile manufacturers and other companies that have multiple  
product lines within their product family, server processors have model numbers  
to help distinguish the differences in features and delineate value. As your  
business grows, so does demand for your products and / or services with  
additional customers, users, and transactions that strain your current IT  
infrastructure and back-end databases. The Intel® Xeon® brand helps customers  
select the appropriate product line and family stack as their demand justifies it1.  
This paper focuses specifically on the Intel Xeon processor E7 family which is designed to be expandable and  
scalable for larger deployments of business- or mission-critical workloads such as on-line transaction  
processing, physical-to-virtual machine consolidation projects, business intelligence, customer relationship  
management (CRM), and enterprise resource planning (ERP) / line-of-business applications that generate  
revenue. The model numbers (see Figure 1) help differentiate the capabilities of the processors and in the  
case of the Intel Xeon processor E7 product family, the wayness or maximum number of processors (CPUs or  
sockets) in a node can be two, four, or eight (contrasted to the Intel Xeon processor E3 or E5 families, which  
support only one or two/four processors, respectively). Performance may scale as the number of processors  
installed (wayness) in a server is increased (up to 94% efficiency as published in this paper); but in a two-way  
server, regardless of the actual processor wayness capability, the throughput application performance would  
be expected to be the same.  
MODEL NUMBERS AND  
SCALABILITY  
For the Intel Xeon processor E7 family,  
processor models (also called SKUs) are  
available in three wayness  
configurations – two, four, or eight  
socket native support (no third party  
node controller required to connect the  
Figure 1 - 2012 Processor Numbering Example  
sockets together). Within a given Intel Xeon processor E7-xxxx SKU, the difference in wayness is irrelevant if  
populated in only a two-socket node and corresponding performance differences are negligible. For example,  
the top-bin Intel Xeon processor E7-8870/E7-4870/E7-2870 all have the same socket type (8) and the same  
 
White Paper Intel® Xeon® Processor E7 Family Performance  
number of users (typically matches the number of logical threads seen by the Operating System, OS)  
simultaneously running a problem on a given server. The performance scaling is calculated by dividing the  
resulting score from the maximum number of processors populated in one server by the score of the server with  
n-way processors populated in another server configuration. So from 2- to 4- to 8-socket-based servers, the  
perfect scaling would be four times, meaning that the number of users supported (or problems solved) in the 8-  
socket server is four times more than what a 2-socket server could support. The efficiency is measured by how  
close a scale-up server performs comparatively to that perfect scaling, which in this case is quite reasonable at up  
to 94% efficiency (see Figure 4 below).  
2-socket 4-socket 8-socket  
Servers Servers Servers  
Figure 4 - Scaling of supported users on multi-processor servers4  
The Intel Xeon processor E7-8870 can be populated in a 2-, 4-, or 8-socket server configuration. This is due to the  
Intel® QuickPath Interconnect (Intel® QPI) that allows the processors to share resources by allowing all of the  
components to access other components through the mainboard network. Similar to the Intel Xeon processor E7-  
8870, the E7-4870 model supports 2- or 4-socket server configurations; but on the Intel Xeon processor E7-2870,  
only 2-sockets can be populated in a server node (though multiple nodes can be joined together to form a larger  
single server image 2S – see Figure 3 above).  
There are no characteristics in each of the three processors noted above that differ, other than the wayness  
capability. All three processors operate in the same number of available cores per socket, core frequency, Intel®  
QPI speed, and cache structure (see Figure 2 above). Therefore, in a 2-socket server configuration, the  
performance delta between the three will only be typical run-to-run variation due to a number of factors including  
manufacturing variances that may affect the length of time the processors run above their marked frequency  
using Intel® TurboBoost Technology. SPEC* allows for up to 1.75% variation. This hypothesis was confirmed  
through testing using Intel internal labs and as seen in Figure 5 below as there is less than 0.5% difference in  
performance between the three processors when in the same two-socket server configuration (see Table 1 below  
for complete list of equivalent processor SKUs).  
3
 
White Paper Intel® Xeon® Processor E7 Family Performance  
Table 1 - Intel Xeon processor E7 family model numbers and wayness supported  
Wayness  
2-Sockets Native  
Intel® Xeon® Processor E7-8800/4800/2800 Product Family Equivalent Performance  
E7-2870 / E7-4870 E7-2860 / E7-4860 E7-2850 / E7-4850 E7-2830 / E7-4830  
/ E7-8870  
E7-4870 / E7-8870 E7-4860 / E7-8860 E7-4850 / E7-8850 E7-4830 / E7-8830  
E7-8870 E7-8860 E7-8850 E7-8830  
/ E7-8860  
/ E7-8850  
/ E7-8830  
4-Sockets Native  
8-Sockets Native  
CONCLUSION  
Servers are very complex machines, especially in the “big iron” class where multi-processor configurations are the  
norm. The Intel Xeon processor E7 family is designed to support a multitude of shipping configurations and the  
model numbering schema is attempting to clarify the wayness and feature choices that customers have. In the  
current generation Intel Xeon  
processor E7 family scalable  
platform situation, the  
performance throughput  
increases at up to 94%  
efficiency from 2- to 8-  
sockets. However, in a two-  
552  
553  
555  
socket server configuration,  
there is no appreciable  
difference in performance  
regardless of the processor  
SKU chosen – Intel Xeon  
processors E7-  
8870/4870/2870 and others  
shown in Table 1 above are  
equivalent.  
Figure 5 - 2-socket Server Performance using Intel Xeon processors E7-8870/4870/28705  
4
   
White Paper Intel® Xeon® Processor E7 Family Performance  
NOTES / SOURCES  
Xeon processor numbering.  
families-specification-update.pdf for more information on Intel Xeon processor E7 family identification information.  
3. Additional Configurations via OEM-specific scaling technologies (up to 256-sockets)  
4. Comparison based on best published Intel Xeon processor E7 results in a 2-, 4-, and 8-socket configuration using the  
SPECint*_rate_base2006 integer throughput benchmark that is often used as a proxy for general server application  
performance.  
a. 8-socket server: Hewlett-Packard ProLiant* DL980 G7 scoring 2070 baseline.  
b. 4-socket server: Cisco UCS* C460 M2 scoring 1100 baseline.  
c. 2-socket server: IBM System x* 3690 X5 scoring 550 baseline.  
5. Comparison based on Intel internal testing on Intel Xeon processor E7 family using SPECint*_rate_base2006  
benchmark baseline scores. System Configuration: Intel® C606 Chipset based reference platform  
two each Intel Xeon processors E7-8870, E7-4870, and E7-2870 populated in sockets 0 and 1 with 128 GB memory  
(32x 4 GB DR DDR3-1066 RDIMMs), Red Hat* Enterprise LINUX 6.2, Intel Compiler XE2012 (12.1) compiled binaries.  
Source: Intel internal TR#1326 October 2012. See Appendix for details.  
5
         
White Paper Intel® Xeon® Processor E7 Family Performance  
APPENDIX  
Intel® Xeon® Processor E7-2870  
Base Base Base Peak  
Copies Run Time Rate  
------  
Peak  
Peak  
Benchmarks  
--------------  
400.perlbench  
400.perlbench  
400.perlbench  
401.bzip2  
401.bzip2  
401.bzip2  
403.gcc  
403.gcc  
403.gcc  
429.mcf  
429.mcf  
429.mcf  
445.gobmk  
445.gobmk  
445.gobmk  
456.hmmer  
456.hmmer  
456.hmmer  
458.sjeng  
Copies Run Time Rate  
--------- ---------  
--------- --------- ------  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
923  
926  
921  
1236  
1235  
1233  
750  
755  
747  
471  
472  
470  
883  
883  
882  
553  
552  
559  
1065  
1064  
1063  
247  
248  
247  
1314  
1368  
1368  
799  
799  
799  
877  
878  
876  
478  
477  
478  
423 *  
422 S  
424 S  
312 S  
313 *  
313 S  
429 *  
426 S  
431 S  
775 *  
774 S  
776 S  
475 *  
475 S  
476 S  
675 *  
677 S  
667 S  
454 S  
455 *  
455 S  
3360 S  
3340 S  
3350 *  
674 S  
647 S  
647 *  
313 S  
313 *  
313 S  
320 *  
320 S  
320 S  
577 S  
579 S  
578 *  
458.sjeng  
458.sjeng  
462.libquantum  
462.libquantum  
462.libquantum  
464.h264ref  
464.h264ref  
464.h264ref  
471.omnetpp  
471.omnetpp  
471.omnetpp  
473.astar  
473.astar  
473.astar  
483.xalancbmk  
483.xalancbmk  
483.xalancbmk  
===================  
400.perlbench  
401.bzip2  
======= ====== ============================================  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
923  
1235  
750  
471  
883  
553  
1064  
247  
1368  
799  
877  
423 *  
313 *  
429 *  
775 *  
475 *  
675 *  
455 *  
3350 *  
647 *  
313 *  
320 *  
578 *  
552  
403.gcc  
429.mcf  
445.gobmk  
456.hmmer  
458.sjeng  
462.libquantum  
464.h264ref  
471.omnetpp  
473.astar  
483.xalancbmk  
SPECint(R)_rate_base2006  
SPECint_rate2006  
478  
Not Run  
6
White Paper Intel® Xeon® Processor E7 Family Performance  
Intel® Xeon® Processor E7-4870  
Base Base Peak Peak Peak  
Copies Run Time Rate Copies Run Time Rate  
------ --------- --------- ------ --------- ---------  
Base  
Benchmarks  
--------------  
400.perlbench  
400.perlbench  
400.perlbench  
401.bzip2  
401.bzip2  
401.bzip2  
403.gcc  
403.gcc  
403.gcc  
429.mcf  
429.mcf  
429.mcf  
445.gobmk  
445.gobmk  
445.gobmk  
456.hmmer  
456.hmmer  
456.hmmer  
458.sjeng  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
922  
924  
918  
1235  
1234  
1233  
746  
753  
763  
470  
472  
470  
883  
886  
882  
555  
551  
548  
1064  
1063  
1065  
247  
247  
247  
1325  
1358  
1367  
799  
799  
799  
879  
877  
875  
478  
477  
478  
424 *  
423 S  
426 S  
313 S  
313 *  
313 S  
432 S  
427 *  
422 S  
776 *  
774 S  
776 S  
475 *  
474 S  
476 S  
672 S  
677 *  
681 S  
455 *  
455 S  
454 S  
3350 S  
3360 *  
3360 S  
668 S  
652 *  
647 S  
313 S  
313 *  
313 S  
319 S  
320 *  
321 S  
577 S  
579 S  
578 *  
458.sjeng  
458.sjeng  
462.libquantum  
462.libquantum  
462.libquantum  
464.h264ref  
464.h264ref  
464.h264ref  
471.omnetpp  
471.omnetpp  
471.omnetpp  
473.astar  
473.astar  
473.astar  
483.xalancbmk  
483.xalancbmk  
483.xalancbmk  
==============  
400.perlbench  
401.bzip2  
======= =====================================================  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
922  
1234  
753  
470  
883  
551  
1064  
247  
1358  
799  
877  
424 *  
313 *  
427 *  
776 *  
475 *  
677 *  
455 *  
3360 *  
652 *  
313 *  
320 *  
578 *  
553  
403.gcc  
429.mcf  
445.gobmk  
456.hmmer  
458.sjeng  
462.libquantum  
464.h264ref  
471.omnetpp  
473.astar  
483.xalancbmk  
SPECint(R)_rate_base2006  
SPECint_rate2006  
478  
Not Run  
7
White Paper Intel® Xeon® Processor E7 Family Performance  
Intel® Xeon® Processor E7-8870  
Base Base Peak Peak Peak  
Copies Run Time Rate Copies Run Time Rate  
------ --------- --------- ------ --------- ---------  
Base  
Benchmarks  
--------------  
400.perlbench  
400.perlbench  
400.perlbench  
401.bzip2  
401.bzip2  
401.bzip2  
403.gcc  
403.gcc  
403.gcc  
429.mcf  
429.mcf  
429.mcf  
445.gobmk  
445.gobmk  
445.gobmk  
456.hmmer  
456.hmmer  
456.hmmer  
458.sjeng  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
925  
919  
920  
1233  
1231  
1232  
747  
747  
756  
470  
471  
471  
880  
882  
884  
554  
554  
555  
1066  
1063  
1065  
247  
247  
247  
1314  
1313  
1335  
798  
798  
798  
876  
879  
876  
477  
477  
480  
423 S  
425 S  
425 *  
313 S  
313 S  
313 *  
431 *  
431 S  
426 S  
777 S  
774 S  
775 *  
477 S  
475 *  
475 S  
674 *  
674 S  
673 S  
454 S  
455 S  
455 *  
3350 S  
3360 S  
3350 *  
674 *  
674 S  
663 S  
313 *  
313 S  
313 S  
321 S  
319 S  
321 *  
579 S  
578 *  
575 S  
458.sjeng  
458.sjeng  
462.libquantum  
462.libquantum  
462.libquantum  
464.h264ref  
464.h264ref  
464.h264ref  
471.omnetpp  
471.omnetpp  
471.omnetpp  
473.astar  
473.astar  
473.astar  
483.xalancbmk  
483.xalancbmk  
483.xalancbmk  
==============  
400.perlbench  
401.bzip2  
======= =====================================================  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
40  
920  
1232  
747  
471  
882  
554  
1065  
247  
1314  
798  
876  
425 *  
313 *  
431 *  
775 *  
475 *  
674 *  
455 *  
3350 *  
674 *  
313 *  
321 *  
578 *  
555  
403.gcc  
429.mcf  
445.gobmk  
456.hmmer  
458.sjeng  
462.libquantum  
464.h264ref  
471.omnetpp  
473.astar  
483.xalancbmk  
SPECint(R)_rate_base2006  
SPECint_rate2006  
477  
Not Run  
8
White Paper Intel® Xeon® Processor E7 Family Performance  
Author  
Frank Jensen is a Performance Engineer in Intel’s Data Center Marketing Group  
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as  
SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those  
factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated  
purchases, including the performance of that product when combined with other products.  
Intel does not control or audit the design or implementation of third party benchmarks or Web sites referenced in this document. Intel encourages all of  
its customers to visit the referenced Web sites or others where similar performance benchmarks are reported and confirm whether the referenced  
benchmarks are accurate and reflect performance of servers available for purchase.  
This paper is for informational purposes only. THIS DOCUMENT IS PROVIDED “AS IS” WITH NO WARRANTIES WHATSOEVER. INCLUDING WARRANTY OF  
MERCHANTABILITY, NONINFRINGEMENT, FITNESS FOR ANY PARTICULAR PURPOSE OR ANY WARRANTY OTHERWISE ARISING OUT OF ANY PROPOSAL,  
SPECIFICATION OR SAMPLE. Intel disclaims all liability, including liability for infringement of any proprietary rights relating to use of information in this  
specification. No license, express or implied, by estoppel or otherwise, to any intellectual property rights is granted herein.  
SPEC and the benchmark name SPECint are trademarks of the Standard Performance Evaluation Corporation. Benchmark results stated above reflect  
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel  
microprocessors. These optimizations include SSE2, SSE3, and SSE3 instruction sets and other optimizations. Intel does not guarantee the availability,  
functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel.  
Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel  
microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information  
regarding the specific instruction sets covered by this notice.  
Notice revision #20110804  
Copyright® 2012 Intel Corporation. All rights reserved. Intel, the Intel logo, Intel®, Xeon®, and the Xeon® logos are trademarks or registered trademarks of  
Intel Corporation or its subsidiaries in other countries. * Other names and brands may be claimed as the property of others. All timeframes, dates and  
products are subject to change without further notification.  
Printed in USA  
1112/FJ/xxx/PDF  
Please Recycle  
328306-001EN  
9

JVC AV 28T4SR User Manual
JVC LT 32WX50EU User Manual
Kenwood Computer Monitor DDX790 User Manual
LG Electronics 44M User Manual
LG Electronics LG Life Good Computer Monitor M2262DP User Manual
LG Electronics LG Life Good CRT Television 32FZ4D UA User Manual
Lincoln 1133 08H A User Manual
Marvel Group Integrated Controller 88F6281 User Manual
NEC MULTISYNC LCD1855NX User Manual
Philips 29PT8607 User Manual