View previous topic :: View next topic |
Author |
Message |
justincataldo Guru
Joined: 15 Jun 2005 Posts: 376 Location: Australia
|
Posted: Thu Sep 01, 2005 4:29 am Post subject: CPU Benchmarking? |
|
|
I've got two Gentoo boxes now... and I want to run some benchmarking on both of them. Can anyone suggest some software I can use?
Bearing in mind that one of them is a dual CPU machine, so the program needs to take this into account to properly compare them. |
|
Back to top |
|
|
Dlareh Advocate
Joined: 06 Aug 2005 Posts: 2102
|
Posted: Thu Sep 01, 2005 4:36 am Post subject: |
|
|
Code: | openssl speed 2>&1 | tee openssl.log |
_________________ "Mr Thomas Edison has been up on the two previous nights discovering 'a bug' in his phonograph." --Pall Mall Gazette (1889)
Are we THERE yet? |
|
Back to top |
|
|
justincataldo Guru
Joined: 15 Jun 2005 Posts: 376 Location: Australia
|
Posted: Thu Sep 01, 2005 6:29 am Post subject: |
|
|
Wow!
Code: |
Doing md2 for 3s on 16 size blocks: 289324 md2's in 3.00s
Doing md2 for 3s on 64 size blocks: 157634 md2's in 3.01s
Doing md2 for 3s on 256 size blocks: 56825 md2's in 3.00s
Doing md2 for 3s on 1024 size blocks: 15847 md2's in 3.00s
Doing md2 for 3s on 8192 size blocks: 2015 md2's in 3.00s
Doing mdc2 for 3s on 16 size blocks: 453225 mdc2's in 3.01s
Doing mdc2 for 3s on 64 size blocks: 127210 mdc2's in 3.00s
Doing mdc2 for 3s on 256 size blocks: 32688 mdc2's in 3.00s
Doing mdc2 for 3s on 1024 size blocks: 8264 mdc2's in 3.00s
Doing mdc2 for 3s on 8192 size blocks: 1037 mdc2's in 3.00s
Doing md4 for 3s on 16 size blocks: 1808679 md4's in 3.01s
Doing md4 for 3s on 64 size blocks: 1605831 md4's in 3.00s
Doing md4 for 3s on 256 size blocks: 1021069 md4's in 3.00s
Doing md4 for 3s on 1024 size blocks: 403729 md4's in 3.00s
Doing md4 for 3s on 8192 size blocks: 61865 md4's in 3.00s
Doing md5 for 3s on 16 size blocks: 1757182 md5's in 3.00s
Doing md5 for 3s on 64 size blocks: 1482178 md5's in 3.01s
Doing md5 for 3s on 256 size blocks: 1023437 md5's in 3.00s
Doing md5 for 3s on 1024 size blocks: 456945 md5's in 3.00s
Doing md5 for 3s on 8192 size blocks: 72186 md5's in 3.00s
Doing hmac(md5) for 3s on 16 size blocks: 1659145 hmac(md5)'s in 3.00s
Doing hmac(md5) for 3s on 64 size blocks: 1437301 hmac(md5)'s in 3.00s
Doing hmac(md5) for 3s on 256 size blocks: 1000983 hmac(md5)'s in 3.01s
Doing hmac(md5) for 3s on 1024 size blocks: 452265 hmac(md5)'s in 3.00s
Doing hmac(md5) for 3s on 8192 size blocks: 73762 hmac(md5)'s in 3.00s
Doing sha1 for 3s on 16 size blocks: 1773231 sha1's in 3.00s
Doing sha1 for 3s on 64 size blocks: 1454693 sha1's in 3.00s
Doing sha1 for 3s on 256 size blocks: 898493 sha1's in 3.01s
Doing sha1 for 3s on 1024 size blocks: 373377 sha1's in 3.00s
Doing sha1 for 3s on 8192 size blocks: 56645 sha1's in 3.00s
Doing rmd160 for 3s on 16 size blocks: 985337 rmd160's in 3.00s
Doing rmd160 for 3s on 64 size blocks: 734280 rmd160's in 3.00s
Doing rmd160 for 3s on 256 size blocks: 448572 rmd160's in 3.00s
Doing rmd160 for 3s on 1024 size blocks: 157843 rmd160's in 3.00s
Doing rmd160 for 3s on 8192 size blocks: 22202 rmd160's in 3.01s
Doing rc4 for 3s on 16 size blocks: 10424583 rc4's in 3.00s
Doing rc4 for 3s on 64 size blocks: 2908742 rc4's in 3.00s
Doing rc4 for 3s on 256 size blocks: 752795 rc4's in 3.00s
Doing rc4 for 3s on 1024 size blocks: 189688 rc4's in 3.00s
Doing rc4 for 3s on 8192 size blocks: 23709 rc4's in 3.01s
Doing des cbc for 3s on 16 size blocks: 5286472 des cbc's in 3.00s
Doing des cbc for 3s on 64 size blocks: 1323053 des cbc's in 3.00s
Doing des cbc for 3s on 256 size blocks: 330235 des cbc's in 3.00s
Doing des cbc for 3s on 1024 size blocks: 82837 des cbc's in 3.00s
Doing des cbc for 3s on 8192 size blocks: 10367 des cbc's in 3.00s
Doing des ede3 for 3s on 16 size blocks: 1991354 des ede3's in 3.01s
Doing des ede3 for 3s on 64 size blocks: 510466 des ede3's in 3.00s
Doing des ede3 for 3s on 256 size blocks: 127881 des ede3's in 3.00s
Doing des ede3 for 3s on 1024 size blocks: 32107 des ede3's in 3.00s
Doing des ede3 for 3s on 8192 size blocks: 4001 des ede3's in 3.00s
Doing aes-128 cbc for 3s on 16 size blocks: 5720674 aes-128 cbc's in 3.01s
Doing aes-128 cbc for 3s on 64 size blocks: 1508129 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 256 size blocks: 384767 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 1024 size blocks: 96178 aes-128 cbc's in 3.00s
Doing aes-128 cbc for 3s on 8192 size blocks: 12061 aes-128 cbc's in 3.00s
Doing aes-192 cbc for 3s on 16 size blocks: 5007776 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 64 size blocks: 1297794 aes-192 cbc's in 3.01s
Doing aes-192 cbc for 3s on 256 size blocks: 329925 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 1024 size blocks: 83942 aes-192 cbc's in 3.00s
Doing aes-192 cbc for 3s on 8192 size blocks: 10488 aes-192 cbc's in 3.00s
Doing aes-256 cbc for 3s on 16 size blocks: 4354168 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 64 size blocks: 1161227 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 256 size blocks: 297103 aes-256 cbc's in 3.01s
Doing aes-256 cbc for 3s on 1024 size blocks: 75051 aes-256 cbc's in 3.00s
Doing aes-256 cbc for 3s on 8192 size blocks: 9374 aes-256 cbc's in 3.00s
Doing idea cbc for 3s on 16 size blocks: 1790016 idea cbc's in 3.00s
Doing idea cbc for 3s on 64 size blocks: 456048 idea cbc's in 3.00s
Doing idea cbc for 3s on 256 size blocks: 114998 idea cbc's in 3.00s
Doing idea cbc for 3s on 1024 size blocks: 28780 idea cbc's in 3.01s
Doing idea cbc for 3s on 8192 size blocks: 3597 idea cbc's in 3.00s
Doing rc2 cbc for 3s on 16 size blocks: 1359752 rc2 cbc's in 3.00s
Doing rc2 cbc for 3s on 64 size blocks: 380482 rc2 cbc's in 3.00s
Doing rc2 cbc for 3s on 256 size blocks: 95821 rc2 cbc's in 3.00s
Doing rc2 cbc for 3s on 1024 size blocks: 23908 rc2 cbc's in 3.01s
Doing rc2 cbc for 3s on 8192 size blocks: 2976 rc2 cbc's in 3.00s
Doing rc5-32/12 cbc for 3s on 16 size blocks: 11317978 rc5-32/12 cbc's in 3.00s
Doing rc5-32/12 cbc for 3s on 64 size blocks: 2801618 rc5-32/12 cbc's in 3.00s
Doing rc5-32/12 cbc for 3s on 256 size blocks: 706968 rc5-32/12 cbc's in 3.00s
Doing rc5-32/12 cbc for 3s on 1024 size blocks: 177224 rc5-32/12 cbc's in 3.00s
Doing rc5-32/12 cbc for 3s on 8192 size blocks: 22157 rc5-32/12 cbc's in 3.01s
Doing blowfish cbc for 3s on 16 size blocks: 9228212 blowfish cbc's in 3.00s
Doing blowfish cbc for 3s on 64 size blocks: 2585662 blowfish cbc's in 3.00s
Doing blowfish cbc for 3s on 256 size blocks: 677970 blowfish cbc's in 3.00s
Doing blowfish cbc for 3s on 1024 size blocks: 171252 blowfish cbc's in 3.00s
Doing blowfish cbc for 3s on 8192 size blocks: 21141 blowfish cbc's in 3.01s
Doing cast cbc for 3s on 16 size blocks: 4025216 cast cbc's in 3.00s
Doing cast cbc for 3s on 64 size blocks: 1032257 cast cbc's in 3.00s
Doing cast cbc for 3s on 256 size blocks: 259815 cast cbc's in 3.00s
Doing cast cbc for 3s on 1024 size blocks: 65033 cast cbc's in 3.00s
Doing cast cbc for 3s on 8192 size blocks: 8037 cast cbc's in 3.00s
Doing 512 bit private rsa's for 10s: 7053 512 bit private RSA's in 10.00s
Doing 512 bit public rsa's for 10s: 76379 512 bit public RSA's in 10.00s
Doing 1024 bit private rsa's for 10s: 1390 1024 bit private RSA's in 10.01s
Doing 1024 bit public rsa's for 10s: 26522 1024 bit public RSA's in 10.00s
Doing 2048 bit private rsa's for 10s: 233 2048 bit private RSA's in 10.03s
Doing 2048 bit public rsa's for 10s: 8050 2048 bit public RSA's in 10.01s
Doing 4096 bit private rsa's for 10s: 36 4096 bit private RSA's in 10.21s
Doing 4096 bit public rsa's for 10s: 2348 4096 bit public RSA's in 10.00s
Doing 512 bit sign dsa's for 10s: 8448 512 bit DSA signs in 10.00s
Doing 512 bit verify dsa's for 10s: 6957 512 bit DSA verify in 10.00s
Doing 1024 bit sign dsa's for 10s: 2791 1024 bit DSA signs in 10.01s
Doing 1024 bit verify dsa's for 10s: 2403 1024 bit DSA verify in 10.00s
Doing 2048 bit sign dsa's for 10s: 850 2048 bit DSA signs in 10.00s
Doing 2048 bit verify dsa's for 10s: 692 2048 bit DSA verify in 10.00s
OpenSSL 0.9.7e 25 Oct 2004
built on: Fri Sep 2 16:03:00 EST 2005
options:bn(64,32) md2(int) rc4(idx,int) des(ptr,risc1,16,long) aes(partial) idea(int) blowfish(idx)
compiler: i686-pc-linux-gnu-gcc -fPIC -DZLIB_SHARED -DZLIB -DOPENSSL_THREADS -D_REENTRANT -DDSO_DLFCN -DHAVE_DLFCN_H -DOPENSSL_NO_KRB5 -DL_ENDIAN -DTERMIO -Wall -march=i686 -pipe -O2 -Wa,--noexecstack -DSHA1_ASM -DMD5_ASM -DRMD160_ASM
available timing options: TIMES TIMEB HZ=100 [sysconf value]
timing function used: times
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes
md2 1543.06k 3351.69k 4849.07k 5409.11k 5502.29k
mdc2 2409.17k 2713.81k 2789.38k 2820.78k 2831.70k
md4 9614.24k 34257.73k 87131.22k 137806.17k 168932.69k
md5 9371.64k 31514.75k 87333.29k 155970.56k 197115.90k
hmac(md5) 8848.77k 30662.42k 85133.44k 154373.12k 201419.43k
sha1 9457.23k 31033.45k 76416.68k 127446.02k 154678.61k
rmd160 5255.13k 15664.64k 38278.14k 53877.08k 60424.85k
rc4 55597.78k 62053.16k 64238.51k 64746.84k 64526.29k
des cbc 28194.52k 28225.13k 28180.05k 28275.03k 28308.82k
des ede3 10585.27k 10889.94k 10912.51k 10959.19k 10925.40k
idea cbc 9546.75k 9729.02k 9813.16k 9790.94k 9822.21k
rc2 cbc 7252.01k 8116.95k 8176.73k 8133.49k 8126.46k
rc5-32/12 cbc 60362.55k 59767.85k 60327.94k 60492.46k 60302.37k
blowfish cbc 49217.13k 55160.79k 57853.44k 58454.02k 57537.23k
cast cbc 21467.82k 22021.48k 22170.88k 22197.93k 21946.37k
aes-128 cbc 30408.90k 32173.42k 32833.45k 32828.76k 32934.57k
aes-192 cbc 26708.14k 27594.29k 28153.60k 28652.20k 28639.23k
aes-256 cbc 23222.23k 24772.84k 25268.56k 25617.41k 25597.27k
sign verify sign/s verify/s
rsa 512 bits 0.0014s 0.0001s 705.3 7637.9
rsa 1024 bits 0.0072s 0.0004s 138.9 2652.2
rsa 2048 bits 0.0430s 0.0012s 23.2 804.2
rsa 4096 bits 0.2836s 0.0043s 3.5 234.8
sign verify sign/s verify/s
dsa 512 bits 0.0012s 0.0014s 844.8 695.7
dsa 1024 bits 0.0036s 0.0042s 278.8 240.3
dsa 2048 bits 0.0118s 0.0145s 85.0 69.2
|
Uh, so what on earth is that supposed to tell me? |
|
Back to top |
|
|
Dlareh Advocate
Joined: 06 Aug 2005 Posts: 2102
|
Posted: Thu Sep 01, 2005 6:51 am Post subject: |
|
|
justincataldo wrote: | Uh, so what on earth is that supposed to tell me? |
There relative speed of your two boxes at crunching a lot of hashes and encryption schemes. _________________ "Mr Thomas Edison has been up on the two previous nights discovering 'a bug' in his phonograph." --Pall Mall Gazette (1889)
Are we THERE yet? |
|
Back to top |
|
|
nxsty Veteran
Joined: 23 Jun 2004 Posts: 1556 Location: .se
|
Posted: Thu Sep 01, 2005 10:02 am Post subject: |
|
|
Try app-benchmarks/nbench. |
|
Back to top |
|
|
justincataldo Guru
Joined: 15 Jun 2005 Posts: 376 Location: Australia
|
Posted: Mon Sep 12, 2005 3:23 am Post subject: |
|
|
The only problem with these two benchmarking programs is that they only use one CPU. Is there some way I can get them to use both CPUs? |
|
Back to top |
|
|
Dlareh Advocate
Joined: 06 Aug 2005 Posts: 2102
|
Posted: Mon Sep 12, 2005 3:30 am Post subject: |
|
|
justincataldo wrote: | The only problem with these two benchmarking programs is that they only use one CPU. Is there some way I can get them to use both CPUs? | Sure! Just divide the times taken by two _________________ "Mr Thomas Edison has been up on the two previous nights discovering 'a bug' in his phonograph." --Pall Mall Gazette (1889)
Are we THERE yet? |
|
Back to top |
|
|
justincataldo Guru
Joined: 15 Jun 2005 Posts: 376 Location: Australia
|
Posted: Mon Sep 12, 2005 1:15 pm Post subject: |
|
|
Dlareh wrote: | justincataldo wrote: | The only problem with these two benchmarking programs is that they only use one CPU. Is there some way I can get them to use both CPUs? | Sure! Just divide the times taken by two |
That's not going to be a true representation of what it would do if there were two separate threads though... |
|
Back to top |
|
|
Master Shake l33t
Joined: 10 Apr 2005 Posts: 755 Location: Wilmington, Delaware
|
Posted: Mon Sep 12, 2005 3:50 pm Post subject: |
|
|
Its hard to benchmark a multicore or multicpu computer with a single core program. Try running two simultaneous instances (or how ever many processors/cores you have) of the program. _________________ System Specs:
64-bit gentoo linux
Q6600 @ 3.2Ghz
P35 Chipset
4 Gigs 800mhz 4-4-4-12
Nvidia GeForce 8800 GTX @ 630mhz |
|
Back to top |
|
|
pjv Guru
Joined: 02 Jul 2003 Posts: 353 Location: Belgium
|
Posted: Mon Sep 12, 2005 5:30 pm Post subject: |
|
|
acovea perhaps |
|
Back to top |
|
|
justincataldo Guru
Joined: 15 Jun 2005 Posts: 376 Location: Australia
|
Posted: Mon Sep 12, 2005 10:49 pm Post subject: |
|
|
pjv wrote: | acovea perhaps |
I emerged it and tried to run:
Code: | runacovea -config gcc34_pentium4.acovea -bench huffbench.c |
I guess this would be best for dual Xeons???
I get lots of errors like this:
Code: |
COMPILE FAILED:
gcc -lrt -lm -std=gnu99 -O1 -march=pentium4 -o ACOVEAC469EA54 -fno-merge-constants -fno-thread-jumps -fno-guess-branch-probability -fno-cprop-registers -fno-if-conversion -fno-if-conversion2 -fno-delayed-branch -fno-loop-optimize -fno-crossjumping -fstrength-reduce -frerun-loop-opt -fschedule-insns -freorder-functions -falign-jumps -fweb -ffloat-store -fmove-all-movables -fno-inline -ftracer -fnew-ra -funroll-all-loops -maccumulate-outgoing-args -momit-leaf-frame-pointer -funsafe-math-optimizations -fno-trapping-math -ffinite-math-only -fno-signaling-nans /usr/share/acovea/benchmarks/huffbench.c
cc1: error: unrecognized option `-fweb'
cc1: error: unrecognized option `-funswitch-loops'
cc1: error: unrecognized option `-fbranch-target-load-optimize'
COMPILE FAILED:
gcc -lrt -lm -std=gnu99 -O1 -march=pentium4 -o ACOVEA9B7868B8 -fno-merge-constants -fno-thread-jumps -fno-guess-branch-probability -foptimize-sibling-calls -fcse-follow-jumps -frerun-loop-opt -fforce-mem -fschedule-insns2 -fregmove -fstrict-aliasing -fdelete-null-pointer-checks -freorder-functions -falign-jumps -falign-labels -falign-functions -frename-registers -fweb -fprefetch-loop-arrays -fmove-all-movables -freduce-all-givs -ftracer -fnew-ra -funswitch-loops -fbranch-target-load-optimize -malign-double -mno-push-args -minline-all-stringops -mfpmath=387 -fomit-frame-pointer -funsafe-math-optimizations -fno-trapping-math -finline-limit=700 /usr/share/acovea/benchmarks/huffbench.c
------------------------------------------------------------
iteration 1: average fitness = 4.85799, best fitnesses = 1e+09 1e+09 4.80829 4.08464 4.54751
|
At the end it gives me a fault:
Code: |
-funsafe-math-optimizations 0 0 0 1 1 2
-fno-trapping-math 0 0 1 1 0 2
-ffinite-math-only 0 0 0 1 1 2
-fno-signaling-nans 0 0 1 1 1 3
-finline-limit 0 0 1 1 1 3
value options:
Segmentation fault
|
|
|
Back to top |
|
|
pjv Guru
Joined: 02 Jul 2003 Posts: 353 Location: Belgium
|
Posted: Tue Sep 13, 2005 7:08 pm Post subject: |
|
|
So you do wanna optimalise compiling for your cpu rather than just compare two cpu's? About the errors, check if the config is still up to date and if it is appropriate for your system. You can also create your own ofcourse by looking up some information about CFLAGS etc. at the gcc site. About the segfault, it obviously shouldn't do that, ask the maker of acovea, i think he even hangs around on this forum. Anyway I'm not really an expert, there are tons of people who can give better advice about this than me, and if so they should step in now (HINT HINT ). |
|
Back to top |
|
|
|