[fpc-pascal] fast integer multiplication

Gerhard Scholz gs at g--s.de
Mon Aug 1 23:58:04 CEST 2005


...
>>The code generated for the above sample is:
>># [16] c:=3Da*b;
>>    movl    U_P$PROJECT1_A,%edx
>>    movl    U_P$PROJECT1_B,%eax
>>    mull    %edx
>>    movl    $0,%edx
>>    movl    %eax,U_P$PROJECT1_C
>>    movl    %edx,U_P$PROJECT1_C+4
>>
>>What I want is the above code, but without the "movl $0,%edx"
>>instruction. Is there a way to do this (wihtout using fpc_mul_qword).
>
>
> Only assembler for now. Any suggestions how the compiler could be told
> to generate such code?
...
>function UI32x32To64(A,B: Longword): QWord;
>assembler; register; nostackframe;
>asm
>    mull %edx
>end;
>
>It is fast but certainly much less than if it were inlined.

My suggestion would be:

  FUNCTION lmul ( CONST a,
                        b : LongInt ) : int64 ; inline ;

    BEGIN
{$ifdef cpu86}
      ASM
        movl    a,%eax
        imull   b
        movl    %eax,lmul
        movl    %edx,lmul+4
       END ;
{$else}
{$ifdef cpu68k}
      lmul :=3D int64 ( a ) * b ;
{$else}
{$ifdef cpusparc}
      lmul :=3D int64 ( a ) * b ;
{$else}
{$ifdef cpualpha}
      lmul :=3D int64 ( a ) * b ;
{$else}
{$ifdef cpupowerpc}
      lmul :=3D int64 ( a ) * b ;
{$else}
      lmul :=3D int64 ( a ) * b ;
{$endif}
{$endif}
{$endif}
{$endif}
{$endif}
     END ;

and similar for unsigned mul.

(shortened here; full code in ulmul.pas; liitle test in tmuls.pas, timing
routines in
wtimer/tdrsc1)

Is portable so code doesn't need to be rewritten when compiled for other
processors (but not optimal then)

Tested only on i386.

Seems to be faster than standard multiplication (interesting: significantly
faster for signed mul than for unsigned mul), can be assembly-coded in the
branches for the other cpus
(if there are opcodes for such a multiplication - I don't know), could go to
unit math.pp.

It seems that routines which contain assembler are not inlined; on the day
somebody finds a trick to inline such code they should be really fast.

Gerhard
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ULMUL.pas
Type: application/octet-stream
Size: 2604 bytes
Desc: not available
Url : http://lists.freepascal.org/lists/fpc-pascal/attachments/20050801/86c=
de070/ULMUL.obj
-------------- next part --------------
A non-text attachment was scrubbed...
Name: tmuls.pas
Type: application/octet-stream
Size: 1291 bytes
Desc: not available
Url : http://lists.freepascal.org/lists/fpc-pascal/attachments/20050801/86c=
de070/tmuls.obj
-------------- next part --------------
A non-text attachment was scrubbed...
Name: WTIMER.pas
Type: application/octet-stream
Size: 1645 bytes
Desc: not available
Url : http://lists.freepascal.org/lists/fpc-pascal/attachments/20050801/86c=
de070/WTIMER.obj
-------------- next part --------------
A non-text attachment was scrubbed...
Name: TDRSC1.pas
Type: application/octet-stream
Size: 2879 bytes
Desc: not available
Url : http://lists.freepascal.org/lists/fpc-pascal/attachments/20050801/86c=
de070/TDRSC1.obj


More information about the fpc-pascal mailing list