CFP2000 Result: SGI SGI Origin 300 4X 600MHz R14000A

Benchmark	Base Copies	Base Runtime	Base Ratio	Copies	Runtime	Ratio
168.wupwise	4	408	18.2	4	360	20.6
171.swim	4	991	14.5	4	975	14.7
172.mgrid	4	716	11.7	4	711	11.7
173.applu	4	688	14.2	4	623	15.6
177.mesa	4	338	19.2	4	308	21.1
178.galgel	4	228	58.9	4	202	66.8
179.art	4	218	55.4	4	216	56.0
183.equake	4	515	11.7	4	511	11.8
187.facerec	4	444	19.9	4	439	20.1
188.ammp	4	401	25.5	4	398	25.6
189.lucas	4	722	12.8	4	712	13.0
191.fma3d	4	865	11.3	4	797	12.2
200.sixtrack	4	376	13.6	4	374	13.7
301.apsi	4	774	15.6	4	630	19.1
SPECfp_rate_base2000	18.4
SPECfp_rate2000	19.5

Benchmark

Base
Copies

Base
Runtime

Base
Ratio

Copies

Runtime

Ratio

168.wupwise

408

18.2

360

20.6

171.swim

991

14.5

975

14.7

172.mgrid

716

11.7

711

11.7

173.applu

688

14.2

623

15.6

177.mesa

338

19.2

308

21.1

178.galgel

228

58.9

202

66.8

179.art

218

55.4

216

56.0

183.equake

515

11.7

511

11.8

187.facerec

444

19.9

439

20.1

188.ammp

401

25.5

398

25.6

189.lucas

722

12.8

712

13.0

191.fma3d

865

11.3

797

12.2

200.sixtrack

376

13.6

374

13.7

301.apsi

774

15.6

630

19.1

SPECfp_rate_base2000

18.4

SPECfp_rate2000

19.5

Hardware

Hardware Vendor:

SGI

Model Name:

SGI Origin 300 4X 600MHz R14000A

CPU:

R14000A

CPU MHz:

600

FPU:

Integrated

CPU(s) enabled:

4 cores, 4 chips, 1 core/chip

CPU(s) orderable:

2-32

Parallel:

Primary Cache:

32KBI + 32KBD on chip

Secondary Cache:

4MB(I+D) off chip

L3 Cache:

N/A

Other Cache:

N/A

Memory:

4 GB

Disk Subsystem:

1 x 18 GB FC

Other Hardware:

None

Software

Operating System:

IRIX 6.5.16m

Compiler:

MIPSpro 7.3.1.3m C, Fortran90
SCSL 1.4 Math Library

File System:

xfs

System State:

Single-user

Notes / Tuning Information
Baseline optimization flags (for C benchmarks): PASS1 : -Ofast=ip35 -fb_create /tmp/SPEC2000/FBDIR_base/$(EXEBASE) PASS2 : -Ofast=ip35 -fb_opt /tmp/SPEC2000/FBDIR_base/$(EXEBASE) Baseline optimization flags (for Fortran benchmarks): -Ofast=ip35 -LNO:fusion=2 Portability Flags: 178.galgel: -fixedform Peak optimization flags: note: all occurances of (FEEDBACK) below means compiled with a two-step process: PASS1 = -fb_create /tmp/SPEC2000/FBDIR_peak/$(EXEBASE) PASS2 = -fb_opt /tmp/SPEC2000/FBDIR_peak/$(EXEBASE) 168.wupwise: -Ofast=ip35 -IPA:space=1000:linear=on:plimit=10000:callee_limit=5000 . -INLINE:aggressive=on -OPT:Olimit=0 -LNO:fusion=2:prefetch_ahead=5 171.swim: -Ofast=ip35 -CG:ld_latency=10 172.mgrid: -Ofast=ip35 -LNO:fusion=2 173.applu: -Ofast=ip35 -LNO:ou_max=5:ou_prod_max=10:prefetch=0:fusion=2 -CG:ld_latency=3 177.mesa: -Ofast=ip35 -OPT:goto=off -LNO:opt=0 -CG:ld_latency=6 (FEEDBACK) 178.galgel: -Ofast=ip35 -LNO:ou_max=7 -CG:ld_latency=3 -lscs (FEEDBACK) . RM_SOURCES = lapak.f90 179.art: -Ofast=ip35 -LNO:prefetch=0 -IPA:min_hot=15 -CG:ld_latency=3 (FEEDBACK) 183.equake: -Ofast=ip35 -LNO:prefetch=0 -TENV:X=4 -CG:ld_latency=7 -IPA:space=500 (FEEDBACK) 187.facerec: -Ofast=ip35 -LNO:fusion=2 188.ammp: -Ofast=ip35 -OPT:goto=off -IPA:space=500:plimit=900 -CG:ld_latency=7 (FEEDBACK) 189.lucas: -Ofast=ip35 -LNO:fusion=2:blocking=off -CG:ld_latency=4 -IPA:min_hot=8 (FEEDBACK) 191.fma3d: -Ofast=ip35 -bigp_off -LNO:prefetch=0 -CG:ld_latency=2 . -OPT:goto=off:unroll_size=160:unroll_times_max=4 (FEEDBACK) 200.sixtrack:= -Ofast=ip35 -IPA:maxdepth=2 -LNO:prefetch=0 (FEEDBACK) 301.apsi: -Ofast=ip35 -TENV:X=4 -LNO:prefetch=0:blocking=off -IPA:linear=on:use_intrinsic The following O/S parameters were set: setenv PAGESIZE_DATA 4096 ; setenv PAGESIZE_TEXT 4096 ; setenv PAGESIZE_STACK 4096 systune -i ; percent_totalmem_4m_pages = 40 ; percent_totalmem_1m_pages = 7 systune -i ; percent_totalmem_256k_pages = 7 ; percent_totalmem_64k_pages = 7 systune -i ; r12k_bdiag = 0x4000000 limit stacksize 500000 The following is done before building each benchmark that requires (FEEDBACK): rm -rf /tmp/SPEC2000/FBDIR_peak/$baseexe ; mkdir -p /tmp/SPEC2000/FBDIR_peak/$baseexe Jobs are submitted using dplace. Contents of the placement file submit.pf: memories 1 in topology physical near $NODE threads 1 run thread 0 on memory 0 using cpu $CPU

Notes / Tuning Information

 Baseline optimization flags (for C benchmarks): 
   PASS1 : -Ofast=ip35 -fb_create /tmp/SPEC2000/FBDIR_base/$(EXEBASE)
   PASS2 : -Ofast=ip35 -fb_opt /tmp/SPEC2000/FBDIR_base/$(EXEBASE)
 Baseline optimization flags (for Fortran benchmarks): -Ofast=ip35 -LNO:fusion=2 
 Portability Flags:
   178.galgel: -fixedform
 Peak optimization flags:
 note:  all occurances of (FEEDBACK) below means compiled with a two-step process:
   PASS1 = -fb_create /tmp/SPEC2000/FBDIR_peak/$(EXEBASE)
   PASS2 = -fb_opt /tmp/SPEC2000/FBDIR_peak/$(EXEBASE)
 168.wupwise: -Ofast=ip35 -IPA:space=1000:linear=on:plimit=10000:callee_limit=5000
.             -INLINE:aggressive=on -OPT:Olimit=0 -LNO:fusion=2:prefetch_ahead=5
 171.swim: -Ofast=ip35 -CG:ld_latency=10
 172.mgrid: -Ofast=ip35 -LNO:fusion=2
 173.applu: -Ofast=ip35 -LNO:ou_max=5:ou_prod_max=10:prefetch=0:fusion=2 -CG:ld_latency=3
 177.mesa: -Ofast=ip35 -OPT:goto=off -LNO:opt=0 -CG:ld_latency=6 (FEEDBACK)
 178.galgel: -Ofast=ip35 -LNO:ou_max=7 -CG:ld_latency=3 -lscs (FEEDBACK)
.           RM_SOURCES = lapak.f90
 179.art: -Ofast=ip35 -LNO:prefetch=0 -IPA:min_hot=15 -CG:ld_latency=3 (FEEDBACK)
 183.equake: -Ofast=ip35 -LNO:prefetch=0 -TENV:X=4  -CG:ld_latency=7 -IPA:space=500 (FEEDBACK)
 187.facerec: -Ofast=ip35 -LNO:fusion=2
 188.ammp: -Ofast=ip35 -OPT:goto=off -IPA:space=500:plimit=900 -CG:ld_latency=7 (FEEDBACK)
189.lucas: -Ofast=ip35 -LNO:fusion=2:blocking=off -CG:ld_latency=4 -IPA:min_hot=8 (FEEDBACK)
 191.fma3d: -Ofast=ip35 -bigp_off -LNO:prefetch=0 -CG:ld_latency=2 
.          -OPT:goto=off:unroll_size=160:unroll_times_max=4 (FEEDBACK)
 200.sixtrack:= -Ofast=ip35 -IPA:maxdepth=2 -LNO:prefetch=0 (FEEDBACK)
 301.apsi: -Ofast=ip35 -TENV:X=4 -LNO:prefetch=0:blocking=off -IPA:linear=on:use_intrinsic
 The following O/S parameters were set:
   setenv PAGESIZE_DATA 4096 ; setenv PAGESIZE_TEXT 4096 ; setenv PAGESIZE_STACK 4096 
   systune -i ; percent_totalmem_4m_pages = 40 ; percent_totalmem_1m_pages = 7 
   systune -i ; percent_totalmem_256k_pages = 7 ; percent_totalmem_64k_pages = 7 
   systune -i ; r12k_bdiag = 0x4000000 
   limit stacksize 500000
 The following is done before building each benchmark that requires (FEEDBACK):  
 rm -rf /tmp/SPEC2000/FBDIR_peak/$baseexe ; mkdir -p /tmp/SPEC2000/FBDIR_peak/$baseexe 
 Jobs are submitted using dplace. Contents of the placement file submit.pf:   
 memories 1 in topology physical near $NODE
 threads 1
 run thread 0 on memory 0 using cpu $CPU

First published at SPEC.org on 09-Jul-2002

Generated on Fri Mar 25 16:02:36 2005 by SPEC CPU2000 HTML formatter v1.01