SPEC CFP2000 Summary Hewlett-Packard Company AlphaServer GS1280 7/1150 Mon Dec 9 22:22:45 2002 SPEC License #2 Test date: Dec-2002 Hardware availability: Jul-2003 Tester: HP Software availability: Jan-2003 Base Base Base Peak Peak Peak Benchmarks # Copies Run Time Rate # Copies Run Time Rate ------------ -------- -------- -------- -------- -------- -------- 168.wupwise 32 187 317 32 77.7 765 168.wupwise 32 187 317* 32 77.8 763* 168.wupwise 32 188 317 32 78.1 760 171.swim 32 89.1 1292 32 89.1 1292 171.swim 32 88.3 1303 32 88.3 1303 171.swim 32 89.0 1293* 32 89.0 1293* 172.mgrid 32 264 254 32 171 390* 172.mgrid 32 263 254 32 171 390 172.mgrid 32 263 254* 32 171 390 173.applu 32 142 548 32 139 559 173.applu 32 142 547 32 140 559 173.applu 32 142 547* 32 140 559* 177.mesa 32 155 336 32 130 400 177.mesa 32 155 336* 32 129 401 177.mesa 32 155 335 32 130 401* 178.galgel 32 141 762 32 140 766 178.galgel 32 141 761* 32 140 767* 178.galgel 32 142 759 32 140 770 179.art 32 135 718 32 83.1 1161* 179.art 32 134 719 32 83.6 1155 179.art 32 134 718* 32 82.9 1164 183.equake 32 262 184* 32 84.8 569* 183.equake 32 262 184 32 85.1 567 183.equake 32 262 184 32 84.4 572 187.facerec 32 178 397 32 161 439 187.facerec 32 178 397* 32 160 442 187.facerec 32 177 398 32 160 440* 188.ammp 32 309 265 32 268 305 188.ammp 32 309 265 32 268 304 188.ammp 32 309 265* 32 268 304* 189.lucas 32 133 559 32 117 635 189.lucas 32 133 560* 32 114 649 189.lucas 32 132 561 32 117 637* 191.fma3d 32 212 367* 32 159 490* 191.fma3d 32 213 367 32 159 490 191.fma3d 32 212 368 32 159 491 200.sixtrack 32 236 173* 32 218 187* 200.sixtrack 32 236 173 32 218 187 200.sixtrack 32 236 173 32 219 187 301.apsi 32 217 446 32 202 478 301.apsi 32 217 445* 32 202 479 301.apsi 32 217 444 32 202 478* ======================================================================== 168.wupwise 32 187 317* 32 77.8 763* 171.swim 32 89.0 1293* 32 89.0 1293* 172.mgrid 32 263 254* 32 171 390* 173.applu 32 142 547* 32 140 559* 177.mesa 32 155 336* 32 130 401* 178.galgel 32 141 761* 32 140 767* 179.art 32 134 718* 32 83.1 1161* 183.equake 32 262 184* 32 84.8 569* 187.facerec 32 178 397* 32 160 440* 188.ammp 32 309 265* 32 268 304* 189.lucas 32 133 560* 32 117 637* 191.fma3d 32 212 367* 32 159 490* 200.sixtrack 32 236 173* 32 218 187* 301.apsi 32 217 445* 32 202 478* SPECfp_rate_base2000 405 SPECfp_rate2000 536 HARDWARE -------- Hardware Vendor: Hewlett-Packard Company Model Name: AlphaServer GS1280 7/1150 CPU: Alpha 21364 CPU MHz: 1150 FPU: Integrated CPU(s) enabled: 32 cores, 32 chips, 1 core/chip CPU(s) orderable: 2 to 32 Parallel: No Primary Cache: 64KB(I)+64KB(D) on chip Secondary Cache: 1.75MB on chip per CPU L3 Cache: None Other Cache: None Memory: 256GB Disk Subsystem: HSV Other Hardware: None SOFTWARE -------- Operating System: Tru64 UNIX V5.1B (Rev. 2650) +IPK Compiler: Compaq C V6.5-011-48C5K Spike V5.2 (506A) Compaq Fortran V5.5-2602-48C8L Compaq Fortran 77 V5.5-2602-48C8L KAP Fortran V4.3 k3105171 000607 KAP Fortran 77 V4.1 k310440 980926 KAP C V4.1 k010726 000607 File System: AdvFS System State: Multi-user NOTES ----- Baseline C: cc -arch ev7 -fast -O4 ONESTEP Fortran: f90 -arch ev7 -fast -O5 ONESTEP Peak: All use: -arch ev7 -non_shared ONESTEP except these (which use only the tunings shown below): 173.applu 188.ammp 191.fma3d Individual benchmark tuning: 168.wupwise: kf77 -call_shared -inline all -tune ev67 -unroll 12 -automatic -align commons -arch ev67 -fkapargs=' -aggressive=c -fuse -fuselevel=1 -so=2 -r=1 -o=1 -interleave -ur=6 -ur2=060 ' +PFB 171.swim: same as base 172.mgrid: kf90 -call_shared -arch generic -O5 -inline manual -nopipeline -transform_loops -unroll 9 -automatic -fkapargs='-aggressive=a -fuse -interleave -ur=2 -ur3=5 -cachesize=128,16000 ' +PFB 173.applu: kf90 -O5 -transform_loops -fkapargs=' -o=0 -nointerleave -ur=14 -ur2=260 -ur3=18' +PFB 177.mesa: kcc -fast -O4 +CFB +IFB 178.galgel: f90 -O5 -fast -unroll 5 -automatic 179.art: kcc -assume whole_program -ldensemalloc -call_shared -assume restricted_pointers -unroll 16 -inline none -ckapargs=' -fuse -fuselevel=1 -ur=3' +PFB 183.equake: cc -call_shared -arch generic -fast -O4 -ldensemalloc -assume restricted_pointers -inline speed -unroll 13 -xtaso_short +PFB 187.facerec: f90 -O4 -nopipeline -inline all -non_shared -speculate all -unroll 7 -automatic -assume accuracy_sensitive -math_library fast +IFB 188.ammp: cc -arch host -O4 -ifo -assume nomath_errno -assume trusted_short_alignment -fp_reorder -readonly_strings -ldensemalloc -xtaso_short -assume restricted_pointers -unroll 9 -inline speed +CFB +IFB +PFB 189.lucas: kf90 -O5 -fkapargs='-ur=1' +PFB 191.fma3d: kf90 -arch ev6 -non_shared -O4 -transform_loops -fkapargs='-cachesize=128,16000 ' +PFB 200.sixtrack: f90 -fast -O5 -assume accuracy_sensitive -notransform_loops +PFB 301.apsi: kf90 -O5 -inline none -call_shared -speculate all -align commons -fkapargs=' -aggressive=ab -tune=ev5 -fuse -ur=1 -ur2=60 -ur3=20 -cachesize=128,16000' Most benchmarks are built using one or more types of profile-driven feedback. The types used are designated by abbreviations in the notes: +CFB: Code generation is optimized by the compiler, using feedback from a training run. These commands are done before the first compile (in phase "fdo_pre0"): mkdir /tmp/pp rm -f /tmp/pp/${baseexe}* and these flags are added to the first and second compiles: PASS1_CFLAGS = -prof_gen_noopt -prof_dir /tmp/pp PASS2_CFLAGS = -prof_use -prof_dir /tmp/pp (Peak builds use /tmp/pp above; base builds use /tmp/pb.) +IFB: Icache usage is improved by the post-link-time optimizer Spike, using feedback from a training run. These commands are used (in phase "fdo_postN"): mv ${baseexe} oldexe spike oldexe -feedback oldexe -o ${baseexe} +PFB: Prefetches are improved by the post-link-time optimizer Spike, using feedback from a training run. These commands are used (in phase "fdo_post_makeN"): rm -f *Counts* mv ${baseexe} oldexe pixie -stats dstride oldexe 1>pixie.out 2>pixie.err mv oldexe.pixie ${baseexe} A training run is carried out (in phase "fdo_runN"), and then this command (in phase "fdo_postN"): spike oldexe -fb oldexe -stride_prefetch -o ${baseexe} When Spike is used for both Icache and Prefetch improvements, only one spike command is actually issued, with the Icache options followed by the Prefetch options. vm: vm_bigpg_enabled = 1 vm_bigpg_thresh=16 vm_swap_eager = 0 proc: max_per_proc_address_space = 0x40000000000 max_per_proc_data_size = 0x40000000000 max_per_proc_stack_size = 0x40000000000 max_proc_per_user = 2048 max_threads_per_user = 0 maxusers = 16384 per_proc_address_space = 0x40000000000 per_proc_data_size = 0x40000000000 per_proc_stack_size = 0x40000000000 Portability: galgel: -fixed Information on UNIX V5.1B Patches can be found at http://ftp1.service.digital.com/public/unix/v5.1b/ Processes were bound to CPUs using 'runon'. HSV controller with 8 striped 36GB disks. ----------------------------------------------------------------------------- For questions about this result, please contact the tester. For other inquiries, please contact webmaster@spec.org. Copyright 1999-2004 Standard Performance Evaluation Corporation Generated on Wed Apr 13 13:14:03 2005 by SPEC CPU2000 ASCII formatter v2.1