SPEC2006 CPU Superiority Table, by Ian Mapleson Last Change: 16/Jul/2008 (reference adjustments, new CPU data not added since Jan/08) Core2Extreme Overclocking Reference: http://www.nordichardware.com/Reviews/?skrivelse=487&page=5 NOTE: The 4.7GHz Core2Extreme numbers in these tables are _extrapolated_ from the published Dell 390 results, ie. linear extrapolation and then reduced by 5%. They are a guide only!! Source Refs: http://www.spec.org/cpu2006/results/cfp2006.html http://www.spec.org/cpu2006/results/cint2006.html FLOATING POINT SPEC2006 RESULTS (ch = chip, cr/crs = core/cores, Para = Autoparallelize option used?): HP rx2660 HP ProLiant IBM P570 Dell 390 Overclocked Fujitsu Integrity DL360-G5 XEON Power6 Core2Extreme Core2Extreme CELSIUS V840 (SPECfp2006) 1.66GHz IA64 5460, 3.16GHz 4.7GHz X6800, 2.93GHz X6800, 4.7GHz Opteron 3GHz 1 ch, 2 crs 2 ch, 8 crs 1 ch, 1 cr 1 ch, 2 crs 1 ch, 2 crs 2 ch, 4 crs Para: No Para: Yes Para: No Para: No Para: No Para: Yes 410.bwaves 44.7 32.9 67.3 20.9 31.6 60.8 416.gamess 11.5 23.7 14.8 17.3 26.4 17.1 433.milc 21.3 10.8 20.0 11.4 17.4 13.2 434.zeusmp 19.3 16.8 26.4 16.0 24.4 12.4 435.gromacs 17.3 20.4 12.6 17.0 25.9 15.4 436.cactusADM 36.5 105.0 24.8 20.2 30.8 39.1 437.leslie3d 27.9 19.5 31.2 13.3 20.3 9.45 444.namd 26.8 16.8 14.1 15.1 23.0 13.9 447.dealII 21.6 30.6 23.8 18.0 27.4 25.0 450.soplex 11.6 15.7 21.4 14.9 22.7 11.8 453.povray 11.5 30.7 15.4 26.1 39.8 19.4 454.calculix 16.7 24.8 18.7 13.9 21.2 8.62 459.GemsFDTD 19.7 19.2 21.3 12.0 18.3 23.3 465.tonto 13.1 25.3 17.5 12.6 19.2 17.5 470.lbm 37.6 24.3 53.7 14.0 21.3 15.3 481.wrf 16.6 22.3 12.3 17.0 25.9 19.5 482.sphinx3 24.4 28.4 36.3 22.9 34.9 15.3 SPECfp2006 Peak HP ProLiant DL360-G5 XEON X5460 3.16GHz: 23.9 IBM p570, Power6 4.7GHz: 22.5 HP Integrity rx2660, Itanium2 1.66GHz: 20.4 Fujitsu CELSIUS V840 Opteron 2222 3GHz: 17.4 Dell 390, Core2Extreme X6800, 2.93GHz: 16.2 Itanium2: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071015-02285.html XEON: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071029-02381.html Power6: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071030-02420.html Core2Ext: http://www.spec.org/cpu2006/results/res2007q1/cpu2006-20061226-00189.html Opteron: http://www.spec.org/cpu2006/results/res2007q3/cpu2006-20070802-01587.html INTEGER SPEC2006 RESULTS (ch = chip, cr/crs = core/cores, Para = Autoparallelize option used?): HP Integrity Intel 3.16GHz IBM P570 Dell 390 Overclocked ASUS Intel HP Proliant rx2660 1.66GHz HP ProLiant Power6 Core2Extreme Core2Extreme Core2Quad DL185 G5 (SPECint2006) Itanium2 IA64 XEON-X5460 4.7GHz X6800, 2.93GHz X6800, 4.7GHz QX9650 3GHz Opteron 3GHz 1 ch, 2 crs 2 ch, 8 crs 1 ch, 1 cr 1 ch, 2 crs 1 ch, 2 crs 1 ch, 4 crs 2 ch, 4 crs Para: No Para: Yes Para: No Para: No Para: No Para: Yes Para: No 400.perlbench 11.7 25.4 13.7 23.5 35.8 24.8 16.6 401.bzip2 11.4 18.4 16.1 15.7 23.9 17.2 11.6 403.gcc 12.9 20.1 19.8 13.3 20.1 23.3 12.6 429.mcf 19.4 24.3 36.8 23.8 36.3 29.9 18.1 445.gobmk 15.0 22.8 17.9 21.5 32.8 22.4 18.0 456.hmmer 28.6 28.8 17.1 12.3 18.8 17.2 21.2 458.sjeng 12.4 20.7 14.9 19.6 29.9 20.5 14.9 462.libquantum 61.4 227.0 96.6 17.9 27.3 105.0 29.5 464.h264ref 22.6 35.2 30.6 31.6 48.2 33.4 23.1 471.omnetpp 9.1 17.0 18.5 15.8 24.1 21.3 10.9 473.astar 15.6 17.2 13.8 14.2 21.6 17.4 10.6 483.xalancbmk 16.6 26.9 18.3 20.7 31.6 24.6 15.3 SPECint2006 Peak HP ProLiant DL360 G5, XEON-X5460 3.16GHz: 27.6 ASUS P5E3 Deluxe, Core2Quad QX9650 3GHz: 25.5 IBM p570, Power6 4.7GHz: 21.6 Dell 390, Core2Extreme X6800, 2.93GHz: 18.5 HP Integrity rx2660, 1.66GHz Itanium2: 17.0 HP Proliant DL185 G5 Opteron 3GHz: 16.1 Itanium2: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071015-02284.html XEON: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071029-02385.html Power6: http://www.spec.org/cpu2006/results/res2007q2/cpu2006-20070518-01096.html Core2Ext: http://www.spec.org/cpu2006/results/res2007q1/cpu2006-20061226-00186.html Core2Quad: http://www.spec.org/cpu2006/results/res2007q4/cpu2006-20071112-02554.html Opteron: http://www.spec.org/cpu2006/results/res2008q1/cpu2006-20071220-02914.html ******************************************************************************************************************* To aid SGI users, here is a SPEC2000 comparison between R14K/600MHz, the older Itanium2 1.6GHz IA64 (before the newer L2 sizes), aswell as some other CPUs from the past, listed in order of aggregate fp performance (extrapolated R16K/1GHz included as a comparative guess): System CPU MHz Cache Sizes SPECint2000 SPECfp2000 SGI Altix 4700/D Itanium2 9040 1600 16/16 + 1MB/256K + 24MB ? 3098 [b] SGI Altix 4700/D Itanium2 9040 1600 16/16 + 1MB/256K + 18MB ? 3001 [b] SGI Altix XE 210 P4 XEON 5160 3000 32/32 + 4MB 2937 [b] 2752 [b] IBM p570 Power5+ 1900 64/32 + 2MB + 36MB 1453 2733 SGI Altix 3700 Bx2 Itanium2 1600 16/16 + 256K + 9MB 1441 [b] 2647 [b] HP rx4640 Itanium2 1600 16/16 + 256K + 6MB 1590 2612 SGI Altix 3700 Bx2 Itanium2 1600 16/16 + 256K + 6MB 1410 [b] 2600 [b] SGI Altix 3700 Bx2 Itanium2 1500 16/16 + 256K + 4MB 1242 [b] 2361 [b] SGI Altix 3000 Itanium2 1500 16/16 + 256K + 6MB 1077 2148 SGI Altix 350 Itanium2 1400 16/16 + 256K + 3MB 1078 1942 SGI Altix 3000 Itanium2 1300 16/16 + 256K + 3MB 875 1854 AMD/ASUS Opteron 150 2400 64/64 + 1MB 1663 1849 Intel D925 P4-X 3466 12/8 + 512 + 2MB 1772 1724 HP Alpha GS1280 21364 1300 64/64 + 2MB 994 1684 SGI Altix 350 Itanium2 1400 16/16 + 256K + 1.5MB 986 1684 Intel D925 P4 3600 12/8 + 1MB 1575 1630 SGI Altix 350 Itanium2 1000 16/16 + 256K + 1.5MB 743 1374 Fujitsu SPARC64-V 1350 128 + 128K/2MB 905 1340 Apple PPC970 (G5) 2000 64/32 + 512K 800 840 Origin 3000 [*] R16000 1000 32/32 + 16MB 792 838 HP rx4610 Itanium 800 16/16 + 96K + 4MB 379 701 HP c3750 PA-8700 875 768K/1.5MB 678 674 HP Pentium-M 1000 32/32 + 1MB 687 552 SGI Origin 3200 R14000A 600 32/32 + 8MB 500 529 SGI Origin 300 R14000A 600 32/32 + 4MB 483 495 SGI Origin 3200 R14000 500 32/32 + 8MB 427 463 SGI Origin 3200 R12000 400 32/32 + 8MB 353 407 SGI 2200 R14000 500 32/32 + 8MB 412 386 SGI Origin 300 R14000 500 32/32 + 2MB 379 378 SGI 2200 R12000 400 32/32 + 8MB 347 343 SGI 2100 R12000 350 32/32 + 8MB 289 293 SGI Origin 200 R12000 360 32/32 + 4MB 298 290 SGI 2200 R12000 300 32/32 + 8MB 264 283 [*] Extrapolation based on R14K/600, done as: (1000/600) * 0.95 * result. Real speed might be faster due to larger L2 and higher L2 speed, or might be less due to simple clock increase not benefiting every code in the same way. Guesstimate only!! REFS: http://www.cl.cam.ac.uk/teaching/2006/CompArch/mainnotes/comparch-2.pdf http://www.spec.org/cpu2000/results/cint2000.html http://www.spec.org/cpu2000/results/cfp2000.html