SPEC CFP2000 Summary Hewlett-Packard Company AlphaServer DS15/1000 Sat Jun 12 18:46:58 2004 SPEC License #2 Test date: Jun-2004 Hardware availability: Jul-2004 Tester: HP Software availability: Jul-2004 Base Base Base Peak Peak Peak Benchmarks Ref Time Run Time Ratio Ref Time Run Time Ratio ------------ -------- -------- -------- -------- -------- -------- 168.wupwise 1600 251 637 1600 118 1360 168.wupwise 1600 251 637* 1600 118 1362* 168.wupwise 1600 251 637 1600 117 1362 171.swim 3100 274 1133* 3100 274 1133* 171.swim 3100 273 1137 3100 273 1137 171.swim 3100 277 1119 3100 277 1119 172.mgrid 1800 381 473 1800 280 643 172.mgrid 1800 381 472* 1800 277 650* 172.mgrid 1800 384 469 1800 276 653 173.applu 2100 258 814 2100 228 919* 173.applu 2100 259 811* 2100 229 919 173.applu 2100 260 808 2100 227 925 177.mesa 1400 183 766 1400 151 927* 177.mesa 1400 183 765* 1400 151 928 177.mesa 1400 183 764 1400 152 923 178.galgel 2900 211 1375* 2900 187 1548 178.galgel 2900 179 1621 2900 176 1647 178.galgel 2900 213 1359 2900 178 1628* 179.art 2600 305 851* 2600 265 981 179.art 2600 347 749 2600 228 1138* 179.art 2600 290 896 2600 226 1153 183.equake 1300 398 327 1300 156 832* 183.equake 1300 399 326* 1300 157 830 183.equake 1300 401 324 1300 155 838 187.facerec 1900 264 720* 1900 237 803 187.facerec 1900 263 722 1900 236 805 187.facerec 1900 264 720 1900 236 804* 188.ammp 2200 447 492* 2200 380 578 188.ammp 2200 456 483 2200 378 582 188.ammp 2200 445 494 2200 380 579* 189.lucas 2000 236 847 2000 206 970 189.lucas 2000 236 848* 2000 208 960 189.lucas 2000 235 852 2000 206 970* 191.fma3d 2100 342 613 2100 300 700 191.fma3d 2100 343 613* 2100 283 743 191.fma3d 2100 348 603 2100 296 708* 200.sixtrack 1100 289 381* 1100 257 428 200.sixtrack 1100 289 381 1100 257 428* 200.sixtrack 1100 289 381 1100 257 428 301.apsi 2600 312 834* 2600 297 875* 301.apsi 2600 313 831 2600 296 877 301.apsi 2600 312 835 2600 308 844 ======================================================================== 168.wupwise 1600 251 637* 1600 118 1362* 171.swim 3100 274 1133* 3100 274 1133* 172.mgrid 1800 381 472* 1800 277 650* 173.applu 2100 259 811* 2100 228 919* 177.mesa 1400 183 765* 1400 151 927* 178.galgel 2900 211 1375* 2900 178 1628* 179.art 2600 305 851* 2600 228 1138* 183.equake 1300 399 326* 1300 156 832* 187.facerec 1900 264 720* 1900 236 804* 188.ammp 2200 447 492* 2200 380 579* 189.lucas 2000 236 848* 2000 206 970* 191.fma3d 2100 343 613* 2100 296 708* 200.sixtrack 1100 289 381* 1100 257 428* 301.apsi 2600 312 834* 2600 297 875* SPECfp_base2000 682 SPECfp2000 876 HARDWARE -------- Hardware Vendor: Hewlett-Packard Company Model Name: AlphaServer DS15/1000 CPU: Alpha 21264C CPU MHz: 1000 FPU: Integrated CPU(s) enabled: 1 core, 1 chip, 1 core/chip CPU(s) orderable: 1 Parallel: No Primary Cache: 64KB(I)+64KB(D) on chip Secondary Cache: 2MB L3 Cache: None Other Cache: None Memory: 2GB; 512MB RIMMs Disk Subsystem: 36GB Ultra 160 10KRPM Other Hardware: None SOFTWARE -------- Operating System: Tru64 UNIX V5.1B (Rev. 2650) +IPK Compiler: Compaq C V6.5-011-48C5K Program Analysis Tools V2.0 Spike V5.2 (510 USG) HP Fortran V5.5A-3548-48D88 HP Fortran 77 V5.5A-3548-48D88 KAP Fortran V4.3 000607 KAP Fortran 77 V4.1 980926 KAP C V4.1 000607 File System: UFS System State: Multi-user NOTES ----- Baseline C: cc -arch ev6 -fast -O4 ONESTEP Fortran: f90 -arch ev6 -fast -O5 ONESTEP Peak: All use -g3 -arch ev6 -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 -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_feedback -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 = 6 vm_swap_eager = 0 ubc_maxpercent = 50 proc: max_per_proc_address_space = 34359738368 max_per_proc_data_size = 34359738368 max_per_proc_stack_size = 34359738368 max_proc_per_user = 2048 max_threads_per_user = 4096 maxusers = 2048 per_proc_address_space = 34359738368 per_proc_data_size = 34359738368 per_proc_stack_size = 34359738368 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". ----------------------------------------------------------------------------- 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 Tue Aug 10 15:57:04 2004 by SPEC CPU2000 ASCII formatter v2.1