Difference between revisions of "Matts: Benchmarks"

From Define Wiki
Jump to navigation Jump to search
Line 29: Line 29:
 
* [[Benchmarking: E5-2600 Series]]
 
* [[Benchmarking: E5-2600 Series]]
 
== Benchmarking: E5-2600 Series ==
 
== Benchmarking: E5-2600 Series ==
−
{| {{table}}
+
 
−
| align="center" style="background:#f0f0f0;"|'''Settings'''
 
−
| align="center" style="background:#f0f0f0;"|'''Test name/number'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2640, 1333MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2640 V2, 1600MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2650 v2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2660 V2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2670, 1600MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2670 V2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2687W, 1600MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2687W V2, 1600MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2687W V2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2690 V2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''2x E5-2697 V2, 1866MHz'''
 
−
| align="center" style="background:#f0f0f0;"|'''E5-2697 v3'''
 
−
| align="center" style="background:#f0f0f0;"|'''2683'''
 
−
|-
 
−
| default||OpenGL (fps)||26.73||27.03||26.97||26.98||26.89||27.09||27.02||26.99||27.01||26.96||27.12||97.28||93.14
 
−
|-
 
−
| default||CPU (pts)||15.7||17.26||22.14||22.53||22.69||25.85||24.42||26.36||26.92||29.32||26.58||26.54||23.99
 
−
|-
 
−
| default||CPU [single core], (pts)||1.21||1.05||1.41||0.93||1.34||1.38||1.51||1.68||1.67||1.39||1.12||1.6||1.29
 
−
|-
 
−
| Set CPU threads||Mins and secs||07:14||08:19||06:20||07:33||06:24||06:29||05:48||05:21||05:28||05:48||06:29||05:09||06:11
 
−
|-
 
−
| HDTV resolution||Render Teapot scene (Mins and secs)||06:50||06:12||04:45||05:47||04:54||04:20||04:23||03:59||04:05||03:43||03:51||02:56||03:31
 
−
|-
 
−
| default||Render Teapot scene, 60 frames (Mins and secs)||17:35||16:04||12:37||11:45||12:54||10:44||11:41||10:31||10:30||09:41||09:18||06:20||07:20
 
−
|-
 
−
| default, windowed||benchmark||1051||1086||1091||1088||1057||1076||1096||1104||1103||1096||1069||3233||00:00
 
−
|-
 
−
| 1920x1080, no FSAA||catia-03||19.9||19.43||20.05||19.66||19.05||19.45||19.7||19.99||20.2||20.17||19.42||53.39||51.83
 
−
|-
 
−
| 1920x1080, no FSAA||ensight-04||13.65||13.53||13.68||13.47||13.27||13.25||13.72||13.55||13.75||13.89||13.44||43.1||09:07
 
−
|-
 
−
| 1920x1080, no FSAA||lightwave-01||24.07||24.88||25.94||25.04||23.49||23.66||24.17||24.28||25.89||24.94||25.33||51.5||15:21
 
−
|-
 
−
| 1920x1080, no FSAA||maya-03||19.64||17.35||22.99||18.02||21.18||19.82||26.77||21.83||20.12||19.74||17.2||55.77||04:33
 
−
|-
 
−
| 1920x1080, no FSAA||proe-05||7.65||6.58||6.28||7.06||7.22||6.84||8.11||8.06||8.27||8.1||7.57||18.12||02:38
 
−
|-
 
−
| 1920x1080, no FSAA||sw-02||20.2||20.89||21.29||21.11||19.99||20.83||19.6||21.18||21.79||21.32||21.4||48.39||19:26
 
−
|-
 
−
| 1920x1080, no FSAA||tcvis-02||20.46||20.42||21.12||20.51||20.87||20.73||20.85||21.37||20.86||21.04||20.42||34.93||13:55
 
−
|-
 
−
| 1920x1080, no FSAA||snx-01||17.9||17.56||17.76||17.58||17.63||17.42||17.81||17.7||17.8||17.64||17.25||42.47||11:31
 
−
|-
 
−
| Processor Arithmetic||Aggregate (GOPS)||257||281||375||395||368||457||416||451||451||511||563||622||524
 
−
|-
 
−
| Processor Arithmetic||Dhrystone (GIPS)||329||345||467||482||473.37||572||535||563||565||629||701||805||676
 
−
|-
 
−
| Processor Arithmetic||Whetstone (GFLOPS)||200||229||301||324||286||364||324||361||360||415||453||547||458
 
−
|-
 
−
| Processor Multi-Media||Aggregate Multi_Media Preformance (Mpix/s)||566||619||810||881||805||985||912||976||980||1100||1200||1730||1400
 
−
|-
 
−
| Multi-Core Efficency||Inter core Bandwidth (GB/s)||54.33||46.9||62||45.49||61.39||89.73||70||68||76||52.63||47.85||140.26||117
 
−
|-
 
−
| Multi-Core Efficency||Inter-core Latency (ns)||176.7||198.8||181.9||192.5||56||133.8||172.9||163.5||149.8||178.1||207.9||113||125
 
−
|-
 
−
| GP Processing||Aggregate Shader Preformance (Mpix/s)||101.19||101.09||100||100.12||100.08||99.3||102||101||99||100.22||98||558||558
 
−
|-
 
−
| GP Processing||Native Float Shaders (Mpix/s)||148.46||148||145||145.62||145.52||142.9||151||148||143||145.51||139||976||976
 
−
|-
 
−
| GP Processing||Native Double Shaders (Mpix/s)||69||69||69||68.84||68.83||69||69||69||69||69||69||320||320
 
−
|-
 
−
| Video Rendering||Aggregate Shader Preformance (Mpix/s)||66||66||66||66||65.44||65.83||66||69||66||66||66||173||190
 
−
|-
 
−
| Set CPU threads||1024m (Secs)||425||510||380||437.1||384||393||347||319||322||355||369||42||48
 
−
|-
 
−
| default||CFD (Hz)||11.317||12.786||15.822||15.093||15.355||16.797||16.284||18.339||18.258||18.054||18.028||19.732||18.574
 
−
|-
 
−
| 1GB, AES||Encryption (GB/sec)||3.5||7.9||10||10||4.8||10||4.7||11.3||11.5||11.8||10.5||NA||11.7
 
−
|-
 
−
| 1GB, AES||Decryption (GB/sec)||3.6||6.6||10.3||9.5||4.7||7.5||4.8||11.3||12.6||11.9||10.5||NA||11.8
 
−
|-
 
−
| 1GB, Serpent-Twofish-AES||Encryption (MB/sec)||379||444||545||598||479||621||532||576||589||598||709||NA||641
 
−
|-
 
−
| 1GB, Serpent-Twofish-AES||Decryption (MB/sec)||388||460||566||637||524||697||568||590||597||598||748||NA||650
 
−
|-
 
−
| Hyper-Threading disabled  (linx amd OLD)||1 times, custom, auto (GFLOPS) LINUX||244||264||321||370||320||411||357||402||406||440||483||NA||NA
 
−
|-
 
−
| Hyper-Threading disabled, set number of threads||Copy (MB/sec)||46717||58919||76347||98184||69869||101603||83313||101298||101911||123136||136123||NA||NA
 
−
|-
 
−
| Hyper-Threading disabled, set number of threads||Scale (MB/sec)||44326||53881||70940||93859||65600||101911||74441||98184||98762||117221||136262||NA||NA
 
−
|-
 
−
| Hyper-Threading disabled, set number of threads||Add (MB/sec)||47050||76434||97353||129721||83747||139519||92309||133329||135209||159910||180400||NA||NA
 
−
|-
 
−
| Hyper-Threading disabled, set number of threads||Triad (MB/sec)||49381||72420||92991||123362||815089||133329||85562||128315||129055||155826||177850||NA||NA
 
−
|-
 
−
| Linux desktop||Watts||88||109||107||104||90||95||91||98||98||96||111||NA||NA
 
−
|-
 
−
| Linux  under load desktop||Watts||296||263||314||305||362||357||471||483||482||426||407||NA||NA
 
−
|-
 
−
| RRP (TRAY price) of CPU||$||1770||1770||2332||2332||3104||3104||3770||3770||3770||4114||5228||NA||NA
 
−
|-
 
−
| RRP (TRAY price) of CPU||$||885||885||1166||1389||1552||1552||1885||1885||1885||2057||2614||NA||NA
 
−
|-
 
−
| GFLOPS / $||$||0.14||0.15||0.14||0.16||0.10||0.13||0.09||0.11||0.11||0.11||0.09||NA||NA
 
−
|-
 
−
| TDP / GFLOPS||Watts||0.82||1.00||1.02||1.21||0.88||1.15||0.76||0.83||0.84||1.03||1.19||NA||NA
 
−
|-
 
−
|
 
−
|}
 
 
* [[Benchmarking: E5-2600 NEW Series]]
 
* [[Benchmarking: E5-2600 NEW Series]]
 +
 
== Benchmarking: E5-2600 new Series ==
 
== Benchmarking: E5-2600 new Series ==
  

Revision as of 12:50, 2 September 2014

Introduction

The benchmarks cover CPU related system performance and benchmarks which cover packages used in the workstation market along with pure performance metrics.

How to run each benchmark

Benchmarks used

Benchmark setup files location: "\\storage1\software\software\Benchmark\NEW X10"

Stream benchmark:


Benchmarking: E5-2600 Series

Benchmarking: E5-2600 new Series

' Settings Test name/number 2x E5-2697 V3, 2133MHz 2x E5-2683 V3, 2133MHz 2x E5-2697 V2, 1866MHz 2x E5-2699 V3, 2133MHz
CINEBENCH 15 64-bit default OpenGL (fps) 105.4 110.96 80.5 119.59
CINEBENCH 15 64-bit default CPU (pts) 3749 3233 2944 4421
CINEBENCH 15 64-bit default CPU [single core], (pts) 141 119 106 138
Terragen 3 Set CPU threads Mins and secs 04:52 05:46 06:16:00 04:52
3DS Max 2015 HDTV resolution Render Teapot scene (Mins and secs) 02:27 02:57 03:16:00 03:47
Lightwave 11 default Render Teapot scene, 60 frames (Mins and secs) 10:11 11:43 13:20:00 15:25
Redsdk turbine benchmark default, windowed benchmark 2917 3041 2907 2880
SPECviewperf 11 1920x1080, no FSAA catia-03 53.39 51.83 48.13 53.23
SPECviewperf 11 1920x1080, no FSAA ensight-04 43.1 09:07 42.02 43.35
SPECviewperf 11 1920x1080, no FSAA lightwave-01 51.5 15:21 44.52 47.63
SPECviewperf 11 1920x1080, no FSAA maya-03 55.77 04:33 51.63 55.19
SPECviewperf 11 1920x1080, no FSAA proe-05 18.12 02:38 11.49 16.46
SPECviewperf 11 1920x1080, no FSAA sw-02 48.39 19:26 41.85 47.79
SPECviewperf 11 1920x1080, no FSAA tcvis-02 34.93 13:55 37.87 44.74
SPECviewperf 11 1920x1080, no FSAA snx-01 42.47 11:31 40.55 41.34
Sandra2012 Processor Arithmetic Aggregate (GOPS) 533 458 456 657
Sandra2012 Processor Arithmetic Dhrystone (GIPS) 642 557 550 782
Sandra2012 Processor Arithmetic Whetstone (GFLOPS) 539 442 454 662
Sandra2012 Processor Multi-Media Aggregate Multi_Media Preformance (Mpix/s) 579 520 472 875
Sandra2012 Multi-Core Efficency Inter core Bandwidth (GB/s) 140.56 119 111 85.86
Sandra2012 Multi-Core Efficency Inter-core Latency (ns) 105.8 125 153 139
Sandra2012 Memory bandwidth Aggregate Memory Performance (GB/s) 13.42
Sandra2012 GP Processing Aggregate Shader Preformance (Mpix/s) 305 305 305 305
Sandra2012 GP Processing Native Float Shaders (Mpix/s) 1160 1160 1.16 1.16
Sandra2012 GP Processing Native Double Shaders (Mpix/s) 80 80 80 80
Sandra2012 Video Rendering DX11 Aggregate Shader Preformance (Mpix/s) 180 197 195 228
WPrime 2.0 Set CPU threads 1024m (Secs) 353 434 196 371
Euler3D default CFD (Hz) 19.732 18.771 11.37 20.22
Truecrypt 7.1 – AES – E 1GB, AES Encryption (GB/sec) 14.2 11.7 11.9 13.3
Truecrypt 7.1 – AES – D 1GB, AES Decryption (GB/sec) 13.2 11.8 11.5 13.4
Truecrypt 7.1 – STAES – E 1GB, Serpent-Twofish-AES Encryption (MB/sec) 770 642 740 712
Truecrypt 7.1 – STAES – D 1GB, Serpent-Twofish-AES Decryption (MB/sec) 783 655 748 728
Linpack (linux) ICC Hyper-Threading disabled (linx amd OLD) 1 times, custom, auto (GFLOPS) LINUX 902 255 465 1005
Stream (linux) ICC Hyper-Threading disabled, set number of threads Copy (MB/sec) 76988 97905 56527 101131
Stream (linux) ICC Hyper-Threading disabled, set number of threads Scale (MB/sec) 76394 97411 56222 101243
Stream (linux) ICC Hyper-Threading disabled, set number of threads Add (MB/sec) 87310 102145 64619 104057
Stream (linux) ICC Hyper-Threading disabled, set number of threads Triad (MB/sec) 87477 102785 64982 104658
Idle power Linux desktop Watts 95 85 100 115
Load power Linux under load desktop Watts 455 461 425 458
2 CPU cost RRP (TRAY price) of CPU $ 5050 1725 5228 8230
Part cost RRP (TRAY price) of CPU $ 2525 1725 2614 4115
Linpack vs Dollar GFLOPS / $ $ 0.18 0.15 0.09 0.12
Linpack vs TDP TDP / GFLOPS Watts 1.98 0.55 1.09 2.19

Benchmarking: Intel Atom Series

Benchmark type Settings Test name/number 5018A-TN4, 16GB, 64GB SSD 2x E5-2640, 1333MHz Core i5-4430 3.0GHz, 8GB DDR3 UN
CINEBENCH 11.5 64-bit default OpenGL (fps) N/A 26.73 27.23
CINEBENCH 11.5 64-bit default CPU (pts) 3.84 15.7 5.1
CINEBENCH 11.5 64-bit default CPU [single core], (pts) 0.49 1.21 1.42
Terragen 2 Set CPU threads Mins and secs 21:22 07:14 11:22
3DS Max 2012 HDTV resolution Render Teapot scene (Mins and secs) N/A 06:50 19:52
Lightwave 11 default Render Teapot scene, 60 frames (Mins and secs) N/A 17:35 46.47
Redsdk turbine benchmark default, windowed benchmark N/A 1051 1318
SPECviewperf 11 1920x1080, no FSAA catia-03 N/A 19.9 24.39
SPECviewperf 11 1920x1080, no FSAA ensight-04 N/A 13.65 14.51
SPECviewperf 11 1920x1080, no FSAA lightwave-01 N/A 24.07 48.65
SPECviewperf 11 1920x1080, no FSAA maya-03 N/A 19.64 41.06
SPECviewperf 11 1920x1080, no FSAA proe-05 N/A 7.65 14.46
SPECviewperf 11 1920x1080, no FSAA sw-02 N/A 20.2 32.62
SPECviewperf 11 1920x1080, no FSAA tcvis-02 N/A 20.46 23.02
SPECviewperf 11 1920x1080, no FSAA snx-01 N/A 17.9 18.97
Sandra2012 Processor Arithmetic Aggregate (GOPS) 55.52 257 75
Sandra2012 Processor Arithmetic Dhrystone (GIPS) 67.56 329 124
Sandra2012 Processor Arithmetic Whetstone (GFLOPS) 45.63 200 45
Sandra2012 Processor Multi-Media Aggregate Multi_Media Preformance (Mpix/s) 115.86 566 238
Sandra2012 Multi-Core Efficency Inter core Bandwidth (GB/s) 2.21 54.33 7.39
Sandra2012 Multi-Core Efficency Inter-core Latency (ns) 122 176.7 48
Sandra2012 GP Processing Aggregate Shader Preformance (Mpix/s) N/A 101.19 138
Sandra2012 GP Processing Native Float Shaders (Mpix/s) N/A 148.46 261
Sandra2012 GP Processing Native Double Shaders (Mpix/s) N/A 69 73
Sandra2012 Video Rendering Aggregate Shader Preformance (Mpix/s) N/A 66 71
WPrime 2.0 Set CPU threads 1024m (Secs) 704 425 389
Euler3D default CFD (Hz) N/A 11.317 4.505
Truecrypt 7.1 – AES – E 1GB, AES Encryption (GB/sec) 2 3.5 2.6
Truecrypt 7.1 – AES – D 1GB, AES Decryption (GB/sec) 2 3.6 2.6
Truecrypt 7.1 – STAES – E 1GB, Serpent-Twofish-AES Encryption (MB/sec) 162 379 144
Truecrypt 7.1 – STAES – D 1GB, Serpent-Twofish-AES Decryption (MB/sec) 160 388 154
Linpack (amd linpack) Hyper-Threading disabled (linx amd OLD) 1 times, custom, auto (GFLOPS) LINUX 18 244 87
Stream Hyper-Threading disabled, set number of threads Copy (MB/sec) 5509 46717 18149
Stream Hyper-Threading disabled, set number of threads Scale (MB/sec) 5197 44326 18166
Stream Hyper-Threading disabled, set number of threads Add (MB/sec) 6126 47050 18802
Stream Hyper-Threading disabled, set number of threads Triad (MB/sec) 6218 49381 18791
Idle power Linux desktop Watts 16 88 34
Load power During Linpack test Watts 30 296 101
Linpack vs Dollar GFLOPS / $ $ 1770
Linpack vs TDP TDP / GFLOPS Watts 0.461538462 885
Retrieved from "http://wiki.define-technology.com/mediawiki-1.35.0/index.php?title=Matts:_Benchmarks&oldid=4805"