source: Sophya/trunk/SophyaLib/Manual/perfmachine.txt@ 3264

Last change on this file since 3264 was 3259, checked in by ansari, 18 years ago

encore des mesures (cpupower,tjet sur XServeG5, OSF-cool, PB-G4) , Reza 30/05/2007
File size: 27.2 KB
Line 
1-------------------------------------------------------------------------------------
2 Comparaison performance de differentes machines en compilation / execution (calcul)
3 -----------------------
4 Mesures effectuees en Janvier 2007 , R. Ansari / C. Magneville
5-------------------------------------------------------------------------------------
6
7(a) eros3 : Bipro-bicoeur Xeon@2.4 GHz Linux (xeon-lx-2.4GHz) , gcc 3.2
8(b) ccali : Bipro-bicoeur Xeon@2.8 GHz Linux (xeon-lx-2.8GHz) , icc 8.0 ou 9.0
9 Flags de compilation avec [-O -g]
10(c) sgsda: AMD Bipro AMD opteron 248 @ 2.2 GHz (amd-lx-
11 Flags de compilation avec [-O -g]
12(cc) grid-saclay: AMD opteron 275 Bipro-bicoeur @ 2.2 GHz (amd275-lx)
13 Flags de compilation avec [-O -g]
14
15(d) asc: bipro alpha (@ ~1 GHz) server DS20 OSF (osf1) , cxx 6.5 (osf-asc)
16(nouveau asc 420 MFLOPS, moins puissante que l'ancien asc 800 MFLOPS)
17(e) xp1000-dapnia: alpha xp1000 @ ~ 600 MHz ? OSF1 , cxx ? (osf-xp1000)
18(e') cool: alpha xp1000 @ ~ 667 MHz ? OSF1 5.1 , cxx 6.3
19(f) superosf-dapnia: multi-proc alphaServer ES80 6 procs EV7 @ 1 GHz (super-osf)
20
21(g) ccsvx01: XServe G5 bipro @~1.8-2GHz (Darwin/OSX) (G5-osx-2GHz) , gcc 3.3
22(h) PowerBook-Reza : Apple G4 @ 1.25 GHz (G4-osx-1.25GHz) , gcc 3.3
23(i) MacBook-Reza: Apple/ Core double-coeur Intel @ 1.83 GHz (core-osx-1.83GHz) gcc 4
24(j) MacPro-Grosdidier : Apple / Xeon 2 double-coeur @ 3 GHz gcc 4.0.1 , compil SOPHYA -O2 -g
25
26(p) IBM-AIX regatta , xlC , IBM eServer pSeries 655 , 8 proc power4 @ 1.1 GHz
27(q) IBM-AIX meso , AIX 5.3, xlC V8 , IBM Power5 , 8 proc bi-coeur P575 @ 1.9 GHz
28
29(s) SGI-IRIX64 magique, CC
30
31NOTES :
32- Sur les machines Xeon, il y a une interaction entre process / threads par rapport a
33l'occupation des CPU's. On perd un facteur 3 en performance multi-threads/multi-taches.
34La machine MacPro avec OSX se debrouille quand meme mieux.
35- Effet du systeme ou carte mere ???
36
37Flag de compilation
38- Flag de compilation par defaut [-O -g] en general
39- Sur eros3 (xeon-linux gcc 3.3) [-O -g] OU [-O3 -g]
40- Sur Darwin [-g] ou [-O2 -g] (ou [-tune G5] sur XServe G5)
41 Sur les mac (en particulier G4/G5), grande difference entre -g et -Ox -g
42 mais peu de difference entre -O -O2 -O3
43- Sur machine aix-meso [-O -g] ou [-O3 -g]
44
45X/ Performances brutes cpupower et donnees SPEC ((http//www.spec.org)
46----------------------------------------------------------------------
47
48(1) MFLOPS -> cpupower 2 (x/y : -O -g / -O3)
49SPECint2000 (3) / SPECfp2000 (2) (http//www.spec.org)
50
51X.1/ Performances en calcul double
52csh> cpupower 0 3000000 5
53 3 10^6 operations doubles - sur memoire 3x3 10^6 doubles (~50 MO)
54 ===> ~ 24 MO / MFLOPS
55csh> cpupower 2
56 1.6 10^9 operations doubles - sur 3x20000 doubles (~0.5 MO)
57
58
59Compilation avec -O (optimisation)
60 (1) cpupower 0 : debit memoire en MO/s
61 (2) cpupower 0 , MFLOPS
62 (5) cpupower 2 , MFLOPS
63
64Compilation avec -g (debug / sans optimisation)
65 (3) cpupower 0 , MFLOPS
66 (6) cpupower 2 , MFLOPS
67
68Compilation avec -O3 ou -fast ...( optimisation poussee)
69 (4) cpupower 0 , MFLOPS
70 (7) cpupower 2 , MFLOPS
71
72
73----------------------------------------------------------------------------------------------
74 MFLOPS |(1) MO/s| (2) (3) (4) | (5) (6) (7)
75----------------------------------------------------------------------------------------------
76(a)xeon-lx-2.4GHz | 1290 | 53 53 55 | 338 340 320
77(a)xeon-lx-2.8GHzicc | 2040 | 85 80 83 | 914 409 914
78(c)amd-lx | 1560 | 65 77 68 | 666 314 686
79(cc)amd2-lx | |
80
81(e')osf-cool | 768 | 32 15 32 | 630 150 660
82(f)superosf
83
84(g)G5-osx-1 GHz | 2100 | 88 68 88 | 1000 255 1073
85(f)G4-osx-1.25GHz | 600 | 25 16 25 | 417 93 430
86(i)core-osx-1.83GHz | 2500 | 107 75 107 | 855 309 884
87(j)xeon-osx
88
89(p)ibm-aix-regatta | 3100 | 130 55 133 | 730 115 1750
90(p)ibm-aix-meso | 3600 | 150 75 150 | 1480 203 3600
91----------------------------------------------------------------------------------------------
92
93X.2/ Comparaison performances int, float double
94 cpupower compile avec -O
95
96(1) float , cpupowerF 0 3000000 5 / cpupowerF 2
97 -> MFLOPS (puissance de calcul sur float)
98(2) double, cpupowerD 0 3000000 5 / cpupowerF 2 (idem tableau X.1)
99 -> MDBLOPS (puissance de calcul sur float)
100(3) int, cpupowerI 0 3000000 5 / cpupowerI 2
101 -> MINTOPS (puissance de calcul sur int)
102(4) long (ou long long (*)) cpupowerL 0 3000000 5 / cpupowerL 2
103 -> MLONOPS (puissance de calcul sur long)
104----------------------------------------------------------------------------------------------
105 MFLOPS | (1)MFLOPS (2)MDBLOPS (3)MINTOPS (4)MLONOPS
106----------------------------------------------------------------------------------------------
107(a)xeon-lx-2.4GHz |
108(a)xeon-lx-2.8GHzicc | 166/905 90/900 166/1500 88/522 (*)
109(c)amd-lx | 125/695 65/675 125/1570 65/1045
110(cc)amd2-lx |
111
112(e')osf-cool | 60/635 32/631 62/640 31/630
113(f)superosf
114
115(g)G5-osx-1 GHz | 180/1260 90/1150 165/940 81/280 (*)
116(f)G4-osx-1.25GHz | 45/430 25/410 45/710 24/190 (*)
117(i)core-osx-1.83GHz | 185/919 105/855 187/935 62/246 (*)
118(j)xeon-osx
119
120(p)ibm-aix-regatta |
121(p)ibm-aix-meso | 250/628 160/1260 240/1120
122----------------------------------------------------------------------------------------------
123
124X.3/ Comparaison avec SPEC
125csh> cpupower 2
126----------------------------------------------------------------------
127 MFLOPS(1) SPECfp SPECint
128----------------------------------------------------------------------
129(b)xeon-lx-2.8GHz 900 1400 1400
130(c)amd-lx 690 1600 1300
131(cc)amd2-lx 675 1600 1300
132
133(e)osf-xp1000 648 500 400
134(f)superosf 842 1100 700
135
136(f)G4-osx-1.25GHz 92/380 (-g)/(-O2 -g)
137(i)core-osx-1.83GHz 310/880 1400 1500 (-g)/(-O2 -g)
138(j)xeon-osx 2600 2900 -
139
140(p)ibm-aix-regatta 730/1750 1050 700 (-O -g)/(-O3)
141(p)ibm-aix-meso 1250/3600 (-O -g)/(-O3)
142----------------------------------------------------------------------
143
144
145A/ Compilation tout SOPHYA
146----------------------------
147csh> time make all (1)
148ou
149csh> time make -j 2 all (2)
150 Temps CPU
151 Indice de performance 100*(1000/TCPU)
152 Temps elapsed (vrai)
153 Temps vrai / TCPU
154
155
156----------------------------------------------------------------------
157 CPU(s) IndPerf TElapsed , TCPU/Elapsed %
158----------------------------------------------------------------------
159(a)xeon-lx-2.4GHz (2) 615 s 162 410 s 150%
160 avec -O3 -g (2) 1300 s 77 760 s 172%
161(b)xeon-lx-2.8GHz (2) 755 s 132 540 s 140%
162(c)amd-lx (2) 336 s 297 175 s 192%
163
164(d)osf-asc (1) 1920 s 52 2340 s 83% (??)
165(e)osf-xp1000 (1) 533 s 187 660 s 80%
166(f)superosf (1) 895 s 112 910 s 98%
167
168(g)G5-osx-2GHz (2) 453 s 221 250 s 182%
169 -tune=G5 1100 s 90
170 -g -O 740 s 380 s 195%
171(h)G4-osx-1.25GHz (1) 660 s 151 710 s 93% [-g]
172 1500 s 94% [-O2 -g]
173(i)core-osx-1.83GHz (2) 209 s 478 116 s 180%
174 -O2 (1) 367 s 272 381 96%
175(j)xeon-osx
176
177(p)ibm-aix
178----------------------------------------------------------------------
179
180Taille shared libs :
181(a)
182(c) 33 MO
183(f) = (e) = 57 MO
184(g) 80 MO
185(i) 83 MO
186
187B/ Calcul brut (Tableaux de SOPHYA) avec / sans threads
188--------------------------------------------------------
189
190B.1/ Version corrige de zthr.cc (apres 23/05/07)
191 arr = (c1*a1) + (c2*a2)
192 ~ 3 x 4. 10^6 operations int_4 sur 3 x 4 10^6 int_4
193 12 M.Ops int_4 / ~ 50 MO
194
195(1) time cpupower 0 # compile avec -O (/ -O -g)
196(2) time zthr arr 1 2000 1 thread
197(3) time zthr arr 2 2000 2 thread
198(4) time zthr arr 4 2000 4 thread
199(5) time zthr arr 6 2000 6 thread
200(6) time zthr arr 8 2000 8 thread
201
202-----------------------------------------------------------------------------------
203 (1)MFLOPS (2)CPU/Elap/% (3)CPU/Elap/% (4)CPU/Elap/%
204-----------------------------------------------------------------------------------
205(a)xeon-lx-2.4GHz 53 0.5/1/43% 1/1.1/88% 2.8/1/262%
206 (5) 4.5/1.8/246% (6) 6.1/2.1/310%
207
208
209(b)xeon-lx-2.8GHz 65
210
211(c)amd-lx 95 0.23/1/22% 0.44/1/51% 1/1/102% [-O -g]
212 (5) 1.6/1/106% (6) 2.2/1.2/100%
213
214
215(d)osf-asc
216
217(e')osf-cool 32 0.43/1.2/35% 0.6/1.33/44% 1.1/1.3/82% [-O -g]
218 (5) 1.45/1.7/85% (6) 1.83/2.16/84%
219(f)superosf
220
221(g)G5-osx-2GHz 88 1.5/1.5/100% 3.2/1.7/185% 6.6/3.5/188% [-O -g]
222(g)G5-osx-2GHz 88 0.4/1/40% 0.9/1.0/90% 2/1.2/169% [-tune=G5 -g]
223 (5) 3.3/2/164% (6) 4.3/2.6/165%
224(h)G4-osx-1.25GHz 25 3/3/95% [-O2 -g]
225
226(i)core-osx-1.83GHz [-O2 -g]
227
228(j)xeon-osx
229
230
231(p)ibm-aix-regatta 130
232
233(q)ibm-aix-meso 150 0.6/1/58% 1/1/91% 1.7/1.2/132% [-O3]
234 (5) 2.4/1.2/193% (6) 4.25/1.6/265%
235
236
237(s)sgi-magique 460
238 -----------------------------------------------------------------------------------
239
240B.1.bis/ ancienne version de zthr (avant 23/05/07)
241 On faisait 2 multiplications par ctye suivi d'un produit matriciel !
242 arr = c1*a1*c2*a2 ( ~ 3 10^6 op. double)
243(1) time cpupower 2 # compile avec -O3 (/ -O -g)
244(2) time zthr arr 1 1000 1 thread
245(3) time zthr arr 2 1000 2 thread
246(4) time zthr arr 4 1000 4 thread
247(5) time zthr arr 6 1000 6 thread
248(6) time zthr arr 8 1000 8 thread
249
250-----------------------------------------------------------------------------------
251 (1)MFLOPS (2)CPU/Elap/% (2)IndPerf (3)CPU/Elap/% (3)IndPerf
252-----------------------------------------------------------------------------------
253(a)xeon-lx-2.4GHz 1167 5.15/5.2/99% 11.4/5.8/196%
254 (4)36.6/9.28/394%
255 -O3 -g 4.9/5./99%
256(b)xeon-lx-2.8GHz 920 2.3/2.3/100% 6.2/3.1/198%
257 (4)26/6.6/396%
258(c)amd-lx 690 3.6/3.6/99% 6.8/4/171%
259 (4)13.5/7/193%
260 (5)20.3/10.23/198%
261(cc)amd2-lx 675 2/2/99% 4.15/2.1/197%
262 (4)8.25/4.15/198%
263 (5)13.6/4.6/292%
264 (6)19.8/6.5/300%
265
266(d)osf-asc 420 6.3s/6.5s/99% 16.9/8.8/192%
267 (4)29.9/15.7/191%
268(e)osf-xp1000 648 5.1/5.3/96.6% 11.4/11.4/99%
269 (4)25.2/25.5/99%
270(f)superosf 842 2.87/2.88/99.6% 6.25/4.1/153%
271 (4)11.6/3.06/379%
272
273(h)G4-osx-1.25GHz 92 44s/48s/91% 86.7/99.8/92% [-g]
274 380 12.2/12.9/95% 24/25.3/95% [-O2 -g]
275(g)G5-osx-2GHz 1151 20s/20s/99% 40s/23s/170%
276 (4) 80.8/45/180%
277 -O -g 4.5/4.9/91% 9.3/4.7/197%
278 (4) 18.3/9.4/197%
279 -tune=G5 3.35/3.8/88% 7.1/3.6/196%
280(h)G4-osx-1.25GHz 92 44s/48s/91% 86.7/99.8/92% [-g]
281 380 12.2/12.9/95% 24/25.3/95% [-O2 -g]
282 (4) 14/7.5/187%
283(i)core-osx-1.83GHz 855 11.5/11.5/100% 23/11.6/192% [-g]
284 (4) 46/23/199%
285 -O2 3.85/3.89/99% 7.7/3.9/198% [-O2 -g]
286 (4) 15.4/7.77/198%
287
288(j)xeon-osx 2600 2.5/2.5/100% 5.1/2.6/199%
289 (4) 11.5/3.2/362%
290 (5) 17.4/4.77/365%
291
292(p)ibm-aix-regatta 1750/730 6.8/6.9/98% 13.1/6.75/195%
293 (4) 26.3/11.7/225%
294(q)ibm-aix-meso 3600/1250 3.6/3.75/96% 7.35/3.7/197%
295 (4) 12.46/4.2/298%
296 (5) 219/6.7/280%
297 (6) 24/4.5/530%
298
299
300(s)sgi-magique 460 60/60/99%
301 -----------------------------------------------------------------------------------
302
303
304B.2/ Multiplication de matrices mtx = mtx1 * mtx2
305 ~ 2 10^9 op. double / thread
306(1) time cpupower 2 (-O3 / -O -g)
307(2) time zthr mtx 1 1000 1 thread
308(3) time zthr mtx 2 1000 2 thread
309(4) time zthr mtx 4 1000 4 thread
310(5) time zthr mtx 6 1000 6 thread
311(6) time zthr mtx 8 1000 8 thread
312
313-----------------------------------------------------------------------------------
314 (1)MFLOPS (2)CPU/Elap/% (2)IndPerf (3)CPU/Elap/% (3)IndPerf
315-----------------------------------------------------------------------------------
316(a)xeon-lx-2.4GHz 1167 6.5/6.5/100% 17.4/8.8/198%
317 (4) 80.5/20.3/397%
318 (5) 114.5/29.6/387%
319 (6) 160/40.3/387%
320
321(b)xeon-lx-2.8GHz 920 3.4/3.4/100% 12/6.1/199%
322 (4) 55.8/14/400%
323(c)amd-lx 690 6.98/6.98/100% 14.1/8.15/173%
324 (4) 27.7/14.23/194%
325 (5) 41.4/21.07/196%
326 (6) 55.4/27.9/198.7%
327(cc)amd2-lx 675 4.1/4.1/100% 9.55/4.8/198%
328 (4) 20/10.27/195%
329 (5) 32.8/11.16/294%
330 (6) 42.75/13.8/309%
331
332
333(d)osf-asc 420 13.5s/13.7s/98% 32/16.5/194%
334 (4) 67.5/34.4/196%
335(e)osf-xp1000 648 13/14.1/92% 27.1/27.4/99%
336 (4) 54/54.7/99.6%
337 (5) 80.6/81/99.6%
338 (6) 107.8/108.3/99.5%
339(f)superosf 842 6.1/7.24/84% 12.35/6.29/196%
340 (4) 24.3/6.31/385%
341 (5) 36.5/10.9/335%
342 (6) 50.1/18.15/276%
343
344(g)G5-osx-2GHz 1151 23/23.7/97% 46.5/27.5/170%
345 (4) 93.4/49.4/189%
346 -O -g 6.2/6.2/100% 14.2/7.2/197%
347 (4) 28.3/14.36/197%
348 -tune=G5 5.7/5.8/98% 13.3/6.8/197%
349 (4) 26.8/13.56/197%
350 (6) 53.8/27.25/197%
351(h)G4-osx-1.25GHz 333 23.5/24.5/96% [-O2]
352(i)core-osx-1.83GHz 855 12.6/12.7/100% 25.8/13.4/194%
353 (4) 51.6/26/199%
354 -O2 4.25/4.5/94% 10.6/5.36/198%
355 (4) 20.87/10.68/198%
356 -O2 2 jobs // 2 x 5/5.4/92%
357(j)xeon-osx 2600 2.8/2.8/99% 9.3/4.66/199%
358 (4) 31.4/8.6/364%
359 (5) 47.1/12.96/364%
360 (6) 62.8/17.38/362%
361
362(p)ibm-aix-regatta 1750/730 9.5/9.7/98% 18.3/16.0/114%
363 (4) 38.3/24.7/155%
364(p)ibm-aix-meso 3600/1250 2.3/2.3/99% 5.1/2.64/194% (compil avec -O3)
365 (4) 11.4/4.16/272%
366 (5) 20.2/5.85/344%
367 (6) 29.9/6.74/442%
368
369(s)sgi-magique 460 49/49/99% 101/56/181%
370
371 -----------------------------------------------------------------------------------
372
373
374B.4/ Operations sur tableaux doubles- mesures avec spar
375 csh> time spar 2 1 2000 2000
376 (1) cpupower 2 MFLOPS
377 (2) MFLOPS (double) spar
378 (3) time spar 2 5 1000 2000 CPU/Elap/%
379-----------------------------------------------------------------------------------
380 (1)MFLOPS (2)CPU / % (3)CPU/Elap/%
381-----------------------------------------------------------------------------------
382(a)xeon-lx-2.4GHz 53 ~ 20-35 MFLOPS , 90% 20/20.2/99% [-g -O]
383
384
385(b)xeon-lx-2.8GHz 65
386
387(c)amd-lx 95 ~ 20-40 MFLOPS , 99% 17.2/17.2/100% [-g -O]
388
389
390(d)osf-asc
391
392(e)osf-xp1000 32 ~ 15-25 MFLOPS , 90% 37.6/41.2/91% [-g -O]
393(f)superosf
394
395(g)G5-osx-2GHz 88 ~ 10-25 MFLOPS , 99% 45/45/100% [-g -O] ou [-g -O2]
396(h)G4-osx-1.25GHz 25 ~ 8-16 MFLOPS , 92% 45.5/52/90% [-g -O2]
397
398(i)core-osx-1.83GHz
399
400(j)xeon-osx
401
402
403(p)ibm-aix-regatta 130
404
405(q)ibm-aix-meso 150 ~ 80-100 MFLOPS , 90% 5./23/22% [-O3]
406
407
408
409(s)sgi-magique 460
410 -----------------------------------------------------------------------------------
411
412B.5/ Calcul/comparaison avec JET/tjet
413csh> time tjet 10 2000 2000 OU tjet 10 2000 1000
414 (1) TCPU EltAccess C/pointeurs
415 (2) TCPU m1*c1+m2*c2+m3*c3 C/pointeurs
416 (3) TCPU EltAccess SOPHYA
417 (4) TCPU m1*c1+m2*c2+m3*c3 SOPHYA / Methodes (MultCst, AddArr ...)
418 (5) TCPU m1*c1+m2*c2+m3*c3 SOPHYA JET
419
420 -----------------------------------------------------------------------------------
421 (1) (2) (3) (4) (5)
422 -----------------------------------------------------------------------------------
423(b)xeon-lx-2.8GHz-icc 0.87 0.63 1.55 2.7/1.6 0.57
424(c)amd-lx 0.94 0.79 1.85 3.4/2.1 0.76
425
426(e')osf-cool 2.85 2.45 3.1 6.5/5.5 4.1
427
428(g)G5-osx-2GHz 1.5 0.61 2.1 4.1/1.6 0.6 (-g -O2)
429 -tune=G5 -fast 1.1 0.62 1.3 4.1/1.6 0.58
430(h)G4-osx-1.25GHz 3.86 2.2 5 9.4/6.2 3 (-g -O2)
431(i)core-osx-1.83GHz 1.1 0.49 1.6 2.8/1.7 0.68
432
433(q)ibm-aix-meso 0.43 0.27 0.52 1.12/0.75 0.35
434-----------------------------------------------------------------------------------
435
436
437C/ Calcul fft (FFTW , FFTPack )
438-------------------------------
439
440(1) time cpupower 2
441(2) time tfft 2000000 W d 0 0 (avec FFTW)
442(3) time tfft 2000000 P d 0 0 (avec FFTPack_Sophya)
443
444IndPerf=1000/TCPU
445
446
447-----------------------------------------------------------------------------------
448 (1)MFLOPS (2)CPU/Elap/% (2)IndPerf (3)CPU/Elap/% (3)IndPerf
449-----------------------------------------------------------------------------------
450(a)xeon-lx-2.4GHz 1167 5.5/5.6/97% 180 7.4/7.4/100% 135
451 -O3 -g 6.8/7.1/96% 147
452(b)xeon-lx-2.8GHz 920
453(c)amd-lx 690 3.2/3.75/86% 4.2/4.2/100% 238
454 ~2x 4.7/4.7/99%
455(cc)amd2-lx 675 2.8/2.8/99% 3.56/3.58/99%
456
457(d)osf-asc 420 13.3/13.9/95.7% 75 12.2/17.6/70% 82
458(e)osf-xp1000 648 9.9/10.2/97% 101 9.3/9.46/98.5% 107
459(e')cool 9.1/9.3/98%
460(f)superosf 842 6./6.22/96.7% 166 5.1/5.18/97.4% 196
461
462(g)G5-osx-2GHz 1151 8.5/8.7/97.5% 120 11.5/11.6/99% 87
463 -O -g 5.1/5.2/98% 190 5.4/5.5/99% 180
464 -tune=G5 5/5.1/98% 200 5.5/5.6/97% 180
465(h)G4-osx-1.25GHz 92 15.2/15.9/96% 66 23.8/34.1/70% 42 [-g]
466 380 8.8/10.3/86% 14.7/20.9/65% [-O2 -g]
467(i)core-osx-1.83GHz 855 4.6/4.75/97% 217 7/7.08/99% 142
468 -O2 3.2/3.2/99% 312 3.6/3.6/99% 277
469 -O2 2 jobs // 2 x 3.9/4.3/90% 2x 4.7/5/91% 200
470(j)xeon-osx 2600 2.6/2.6/98% 384
471 2 jobs // ~2x 3.6/4.1/87% 250
472 4 jobs //
473
474(p)ibm-aix-regatta 1750/730 6.25/18.9/33% 160 5.25/15.7/33% 190
475(q)ibm-aix-meso 3600/1250 3.95/4.3/91% 250 3.82/4./94% 260
476 2 jobs // ~2x 3.88/4.2/92% 250
477
478
479(s)sgi-magique 460 22/22/98% 42 24.5/25/99% 40
480 -----------------------------------------------------------------------------------
481
482
483D/ Calcul inversion par lapack
484-------------------------------
485
486lpk inverse 1000,1000 0
487---> temps de calcul inversion par lapack
488-------------------------------------------------------------------------------------------
489 CPU/Elap/% (1)
490-------------------------------------------------------------------------------------------
491(a)xeon-lx-2.4GHz 5.6/~100%
492(b)xeon-lx-2.8GHz
493(c)amd-lx 5.5/5.5/99%
494
495(d)osf-asc
496(e')cool 2.8/2.9/95%
497(f)superosf
498
499(f)G4-osx-1.25GHz 2.3/~100% [-O2 -g]
500(h)G5-osx-2GHz 0.8/~100%
501 -O -g 0.86/~100%
502(i)core-osx-1.83GHz 1.93/~100%
503 -O2
504(p)ibm-aix-regatta
505(q)ibm-aix-meso 0.55/~100%
506
507--------------------------------------------------------------------------------------------
508
509
510K/ Efficacite de gestion de lock (mutex) avec les threads et tableaux
511----------------------------------------------------------------------
512(32 threads - operant sur 2000 vecteurs ~ 64000 lock/unlock/wait/broadcast)
513
514(1) time zthr syncp 32 2000 4
515(2) time zthr sync 32 2000 4
516(1) time zthr syncp 4 15000 130
517(2) time zthr sync 4 15000 130
518-------------------------------------------------------------------------------------------
519 CPU/Elap/% (1) (2) (3) (4)
520-------------------------------------------------------------------------------------------
521(a)xeon-lx-2.4GHz 23.5/14/168% 4.3/1.2/365% 7.9/5.5/142% 4/2.15/190%
522 Avant ThSafeOp 17/178%
523 avec -O3 -g
524(b)xeon-lx-2.8GHz (2)
525(c)amd-lx 0.6/1/63% 0.6/1/60% 3.5/3.5/102% 2.6/2.7/98%
526
527(d)osf-asc 4.5/3.4/132% 3.35/2/170% 15.8/10.5/150% 13/8/163%
528 5.4/100%(NoThSafe)
529(e')cool 1.3/1.37/95% 1.35/1.5/89% 5.3/5.3/99% 5.2/5.2/99%
530(e)superosf (1)
531
532
533(g)G5-osx-2GHz (2) 2.6/130% (NoThSafe)
534 -O -g 2.6/1.7/150% 6.8/3.7/187% 4/2.75/142% 4.7/3/155%
535(h)G4-osx-1.25GHz (1) 40.5/42.6/95% 42.2/43.5/97% [-g]
536 3.9/4.3/89% 3.5/4/89% 3.8/4/95% 4.3/4.6/93%
537
538(i)core-osx-1.83GHz 7.7/7.1/108% 7.8/6.7/116% 30.2/29.6/102% 30.3/29.2/104% [-g]
539 -O2 2.7/1.8/152% 6/3.16/190% 3.4/2.4/142% 3.2/2.5/164% [-O2 -g]
540(j)xeon-osx
541 Avant ThSafeOp 2.55/143%
542
543(p)ibm-aix-regatta 4.7/111%
544(q)ibm-aix-meso 7.5/2.8/300% 17/3.8/450% 8.2/3.05/270% 4.85/2.43/200%
545
546--------------------------------------------------------------------------------------------
547
548
549
550L/ I/O et PPF
551-----------------
552Ecriture/lecture de n=10^7 lignes de int+6double, Total ~ 500 MO
553(1) time tstdtable w xx.ppf swap 10000000 1024 0
554(2) time tstdtable r xx.ppf swap 10000000 1024 0
555(3) time tstdtable w xx.ppf swap 50000000 1024 0
556(4) time tstdtable r xx.ppf swap 50000000 1024 0
557
558-------------------------------------------------------------------------------------------
559 CPU/Elap/% (1) (2) (3) (4)
560-------------------------------------------------------------------------------------------
561(a)xeon-lx-2.4GHz 17/26/63% 5.5/5.6/94%
562(b)xeon-lx-2.8GHz
563(c)amd-lx 5.9/6./97% 3.4/3.4/100% 30/32/93% 24/165/13% ?
564
565(d)osf-asc
566(e')cool 15/30/50% 13/13/99%
567(f)superosf
568
569(g)G5-osx-2GHz 14/14.2/98% 6/6.14/99%
570
571(h)G4-osx-1.25GHz 26/29.7/87% 15.7/38.6/41% [-O2 -g]
572(i)core-osx-1.83GHz 37/37.8/98% 22/48.4/45% [-g]
573 -O2 10.5/17.4/55% 11.2/41.2/27% [-O2 -g]
574(p)ibm-aix-regatta
575(q)ibm-aix-meso 5.5/16.8/38% 5.7/13.2/43% 32.7/85/39% 29/60/49%
576
577--------------------------------------------------------------------------------------------
578
579
580
Note: See TracBrowser for help on using the repository browser.