On Tue, Oct 7, 2008 at 12:28 PM, Przemyslaw Czerpak <[EMAIL PROTECTED]> wrote:
> The results are as wrong as in other tests but I forgot about one thing.
> Your CPU just like mine strongly interacts with simultaneous assign the
> same memory cell and the code which makes it in main HVM loop is covered
> by #ifndef HB_GUI ... #endif.
> To disable it you will have to rebuild Harbour with C_USR=-DHB_GUI
> or at least compile this tests with -gc3 - it causes that except codeblocks
> for the rest of code C code is generated not PCODE evaluated by main HVM
> loop. I would like to ask you about yet another test. The same but using
> Harbour recompiled with export C_USR=-DHB_GUI or with speedtst.prg compiled
> with -gc3 switch, f.e.:
> hbmk -n -w -es2 -gc3 -mt speedtst
That's it!! :)
Using -gc3 I have the results below.
best regards,
Lorenzo
10/07/08 12:42:43 Linux 2.6.26.5-45.fc9.i686 i686
Harbour 1.1.0dev (Rev. 9564) (MT)+ GNU C 4.3 (32 bit)
THREADS: 2
N_LOOPS: 1000000
excluded tests: 029 030 023 025 027 040 041 043 052 053 019 022 031 032 054
1 th. 2 th. factor
============================================================================
[ T001: x := L_C ]____________________________________ 0.16 0.09 -> 1.88
[ T002: x := L_N ]____________________________________ 0.10 0.05 -> 1.96
[ T003: x := L_D ]____________________________________ 0.09 0.05 -> 1.74
[ T004: x := S_C ]____________________________________ 0.18 0.15 -> 1.18
[ T005: x := S_N ]____________________________________ 0.13 0.07 -> 2.02
[ T006: x := S_D ]____________________________________ 0.12 0.07 -> 1.80
[ T007: x := M_C ]____________________________________ 0.20 0.12 -> 1.60
[ T008: x := M_N ]____________________________________ 0.14 0.12 -> 1.15
[ T009: x := M_D ]____________________________________ 0.14 0.08 -> 1.75
[ T010: x := P_C ]____________________________________ 0.18 0.13 -> 1.46
[ T011: x := P_N ]____________________________________ 0.13 0.07 -> 1.93
[ T012: x := P_D ]____________________________________ 0.14 0.07 -> 1.94
[ T013: x := F_C ]____________________________________ 0.42 0.25 -> 1.73
[ T014: x := F_N ]____________________________________ 0.41 0.25 -> 1.60
[ T015: x := F_D ]____________________________________ 0.24 0.18 -> 1.36
[ T016: x := o:GenCode ]______________________________ 0.39 0.29 -> 1.32
[ T017: x := o[8] ]___________________________________ 0.28 0.19 -> 1.45
[ T018: round( i / 1000, 2 ) ]________________________ 0.49 0.31 -> 1.56
[ T020: val( s ) ]____________________________________ 0.59 0.43 -> 1.37
[ T021: val( a [ i % 16 + 1 ] ) ]_____________________ 0.96 0.57 -> 1.68
[ T024: eval( bc := { || i % 16 } ) ]_________________ 0.59 0.42 -> 1.41
[ T026: eval( bc := { |x| x % 16 }, i ) ]_____________ 0.56 0.31 -> 1.81
[ T028: eval( bc := { |x| f1( x ) }, i ) ]____________ 0.66 0.48 -> 1.39
[ T033: x := a[ i % 16 + 1 ] == s ]___________________ 0.79 0.40 -> 1.98
[ T034: x := a[ i % 16 + 1 ] = s ]____________________ 0.70 0.51 -> 1.36
[ T035: x := a[ i % 16 + 1 ] >= s ]___________________ 0.68 0.52 -> 1.31
[ T036: x := a[ i % 16 + 1 ] <= s ]___________________ 0.68 0.41 -> 1.68
[ T037: x := a[ i % 16 + 1 ] < s ]____________________ 0.75 0.44 -> 1.70
[ T038: x := a[ i % 16 + 1 ] > s ]____________________ 0.68 0.44 -> 1.55
[ T039: ascan( a, i % 16 ) ]__________________________ 0.66 0.44 -> 1.50
[ T042: x := a ]______________________________________ 0.20 0.12 -> 1.67
[ T044: f0() ]________________________________________ 0.25 0.12 -> 2.02
[ T045: f1( i ) ]_____________________________________ 0.33 0.23 -> 1.42
[ T046: f2( c[1...8] ) ]______________________________ 0.33 0.22 -> 1.53
[ T047: f2( c[1...40000] ) ]__________________________ 0.33 0.23 -> 1.43
[ T048: f2( @c[1...40000] ) ]_________________________ 0.34 0.20 -> 1.71
[ T049: f2( @c[1...40000] ), c2 := c ]________________ 0.35 0.20 -> 1.78
[ T050: f3( a, a2, s, i, s2, bc, i, n, x ) ]__________ 0.88 0.56 -> 1.56
[ T051: f2( a ) ]_____________________________________ 0.34 0.20 -> 1.67
============================================================================
[ TOTAL ]_________________________________________ 15.57 9.97 -> 1.56
============================================================================
[ total application time: ]....................................30.19
[ total real time: ]...........................................25.54
_______________________________________________
Harbour mailing list
Harbour@harbour-project.org
http://lists.harbour-project.org/mailman/listinfo/harbour
