[Harbour] 2008-10-05 17:53 UTC+0200 Przemyslaw
Czerpak(druzus/at/priv.onet.pl)
Lorenzo Fiorini
lorenzo.fiorini at gmail.com
Sun Oct 5 15:52:44 EDT 2008
On Sun, Oct 5, 2008 at 9:04 PM, Przemyslaw Czerpak <druzus at acn.waw.pl> wrote:
> Thank you very much. As I can see you two CPU machine and in all tests
> which does not allocate new memory you have the factor close to 2.0.
> Very nice. Also:
> [ T004: x := S_C ]______________________________ 2.09 1.39 -> 1.51
> Is quite good so the overhead caused by operating on the same reference
> counter is relatively small. At least much smaller then in my machine.
> So probably the same will be with spinlocks.
> If you can please also make test for:
> speedtst --thread=2 --scale --exclude=mem
> It will be much shorter due the less number of threads and tests.
Just for report, here is my cat /proc/cpuinfo:
model name : Intel(R) Core(TM)2 Duo CPU E6750 @ 2.66GHz
I'm faster but I'm far from 2.0 using:
./speedtst --thread=2 --scale --exclude=mem &> speedtst.log
under Fedora 9.
Is it expected?
best regards,
Lorenzo
10/05/08 21:43:57 Linux 2.6.26.5-45.fc9.i686 i686
Harbour 1.1.0dev (Rev. 9551) (MT)+ GNU C 4.3 (32 bit)
THREADS: 2
N_LOOPS: 1000000
excluded tests: 029 030 023 025 027 040 041 043 052 053 019 022 031 032
1 th. 2 th. factor
============================================================================
[ T001: x := L_C ]____________________________________ 0.25 0.21 -> 1.20
[ T002: x := L_N ]____________________________________ 0.18 0.16 -> 1.13
[ T003: x := L_D ]____________________________________ 0.17 0.16 -> 1.05
[ T004: x := S_C ]____________________________________ 0.23 0.22 -> 1.04
[ T005: x := S_N ]____________________________________ 0.17 0.16 -> 1.02
[ T006: x := S_D ]____________________________________ 0.17 0.16 -> 1.08
[ T007: x := M_C ]____________________________________ 0.25 0.20 -> 1.25
[ T008: x := M_N ]____________________________________ 0.19 0.20 -> 0.97
[ T009: x := M_D ]____________________________________ 0.18 0.19 -> 0.99
[ T010: x := P_C ]____________________________________ 0.24 0.19 -> 1.30
[ T011: x := P_N ]____________________________________ 0.19 0.19 -> 0.98
[ T012: x := P_D ]____________________________________ 0.19 0.18 -> 1.05
[ T013: x := F_C ]____________________________________ 0.50 0.28 -> 1.79
[ T014: x := F_N ]____________________________________ 0.48 0.27 -> 1.74
[ T015: x := F_D ]____________________________________ 0.27 0.18 -> 1.51
[ T016: x := o:GenCode ]______________________________ 0.43 0.25 -> 1.71
[ T017: x := o[8] ]___________________________________ 0.34 0.27 -> 1.27
[ T018: round( i / 1000, 2 ) ]________________________ 0.57 0.37 -> 1.52
[ T020: val( s ) ]____________________________________ 0.62 0.36 -> 1.71
[ T021: val( a [ i % 16 + 1 ] ) ]_____________________ 0.95 0.59 -> 1.61
[ T024: eval( bc := { || i % 16 } ) ]_________________ 0.56 0.43 -> 1.30
[ T026: eval( bc := { |x| x % 16 }, i ) ]_____________ 0.57 0.47 -> 1.23
[ T028: eval( bc := { |x| f1( x ) }, i ) ]____________ 0.76 0.66 -> 1.15
[ T033: x := a[ i % 16 + 1 ] == s ]___________________ 0.76 0.60 -> 1.27
[ T034: x := a[ i % 16 + 1 ] = s ]____________________ 0.81 0.58 -> 1.39
[ T035: x := a[ i % 16 + 1 ] >= s ]___________________ 0.80 0.60 -> 1.33
[ T036: x := a[ i % 16 + 1 ] <= s ]___________________ 0.80 0.59 -> 1.36
[ T037: x := a[ i % 16 + 1 ] < s ]____________________ 0.80 0.60 -> 1.34
[ T038: x := a[ i % 16 + 1 ] > s ]____________________ 0.78 0.60 -> 1.29
[ T039: ascan( a, i % 16 ) ]__________________________ 0.72 0.48 -> 1.52
[ T042: x := a ]______________________________________ 0.26 0.20 -> 1.31
[ T044: f0() ]________________________________________ 0.30 0.31 -> 0.97
[ T045: f1( i ) ]_____________________________________ 0.38 0.36 -> 1.06
[ T046: f2( c[1...8] ) ]______________________________ 0.45 0.37 -> 1.22
[ T047: f2( c[1...40000] ) ]__________________________ 0.45 0.38 -> 1.19
[ T048: f2( @c[1...40000] ) ]_________________________ 0.46 0.39 -> 1.17
[ T049: f2( @c[1...40000] ), c2 := c ]________________ 0.49 0.46 -> 1.09
[ T050: f3( a, a2, s, i, s2, bc, i, n, x ) ]__________ 1.06 0.80 -> 1.33
[ T051: f2( a ) ]_____________________________________ 0.45 0.42 -> 1.08
[ T054: f_prv( c ) ]__________________________________ 1.23 0.86 -> 1.43
============================================================================
[ TOTAL ]_________________________________________ 19.48 14.95 -> 1.30
============================================================================
[ total application time: ]....................................44.97
[ total real time: ]...........................................34.43
More information about the Harbour
mailing list