I need a default value of the number of maximum threads. Is there already some RTL function that can be used for that?

For example if the program runs on a 2 x quad core it would be nice to get 8.
Hyperthreading multipliers should be applied.

Mattias

No, but having some functions returning information about the CPUs would be nice.

Mattias Gaertner pisze:

I've found something on:
http://blogs.msdn.com/oldnewthing/archive/2005/12/16/504659.aspx

function AvailableProcessorCount: DWORD;
//returns total number of processors available to system including
logical hyperthreaded processors
var
i: Integer;
ProcessAffinityMask, SystemAffinityMask: DWORD;
Mask: DWORD;
begin
if GetProcessAffinityMask(GetCurrentProcess, ProcessAffinityMask,
SystemAffinityMask) then begin
Result := 0;
for i := 0 to 31 do begin
Mask := 1 shl i;
if (ProcessAffinityMask and Mask)0 then begin
inc(Result);
end;
end;
end else begin
//can't get the affinity mask so we just report the total number of
processors
Result := OperatingSystemInfo.ProcessorCount;
end;
end; (* AvailableProcessorCount *)

Blender (http://www.blender.org/) source code has function to do that (they needed this to set the default number of threads for renderer). So you could try converting to Pascal the code of "BLI_system_thread_count" function from:

https://svn.blender.org/svnroot/bf-blender/trunk/blender/source/blender/blenlib/intern/threads.c

Doesn't seem that complicated on 1st look. It's basically appropriate GetSystemInfo call on Windows, sysctl on Mac OS, and sysconf (from Libc) call on most Unixes.

HTH,
Michalis

In our previous episode, Michalis Kamburelis said: [ Charset ISO-8859-1 unsupported, converting... ]

Sysconf is not standarized yet. Unit libc is linux/x86 only.

On freebsd, the sysctl modeled works, but note the typecast. (probably a K&R void* <-> char* problem)

uses ctypes,sysctl;
var mib : array[0..1] of cint;
   len:cint;
    t :cint;
begin
	mib[0] := CTL_HW;
        mib[1] := HW_NCPU;
        len := sizeof(t);
        fpsysctl(pchar(@mib), 2, @t, @len, Nil, 0);
	writeln(t); // prints 2 on our dual CPU (Athlon MPs)
end.

If we implement something like this, I propose we do it properly. There are different numbers important:
- numa nodes
- physical cpus
- cache sharing cores
- logical/execution unit sharing cores

Which one are considered important?

- Completely different kinds of cores, e.g., on the Cell you have a "hyper-threaded" ppc64 and 6 to 8 available SPU vector processors.
- And then there's stuff like CUDA (and its Open* variant) coming up, of course.

Which one are considered important?

I personally don't think it's possible to generally deal with this at the application level, there's too much variety and complexity. It's also only going to get worse in the future, as reconfigurable computing is a very hot topic. And so are heterogenous multicores, and not just the Cell way; e.g. different cores implementing the same ISA, but with different pipeline and functional unit designs so they are all better suited at different kinds of tasks/threads (and simulations indicate that such designs give much better overall power/performance than the current crop of homogeneous multi-core desktop & server cpus if you use some fairly simple performance counter based heuristics in your scheduler).

Jonas

Thanks for all the hints.

At the moment I have the attached function.
It returns only 4 on a 2 x quad core Mac.
Maybe someone can test under windows?

Mattias

Hello Mattias,

Saturday, December 13, 2008, 5:17:31 PM, you wrote:

MG> At the moment I have the attached function.
MG> It returns only 4 on a 2 x quad core Mac.
MG> Maybe someone can test under windows?

Windows XP running P3000 hyperthreading returns 2 cores (as expected) but using FPC 2.2.2 the line:

Mask := 1 shl i;

must be changed by

Mask := DWORD(1) shl i;

or it raises a runtime 201 error when i = 31.

I tested this out on my Windows 7-based laptop (running the 64 bit edition) and this is what I get:

E:\lazarus>ppcx64 test
Free Pascal Compiler version 2.2.2 [2008/10/05] for x86_64 Copyright (c) 1993-2008 by Florian Klaempfl
Target OS: Win64 for x64
Compiling test.pas
Linking test.exe
7 lines compiled, 0.6 sec , 39984 bytes code, 1648 bytes data

E:\lazarus>test

2 CPUs online.

The function returns 2 on my Pentium 4 (Win XP)

Howard Page-Clark

Mattias Gaertner wrote

At the moment I have the attached function. It returns only 4 on a 2 x quad core Mac. Maybe someone can test under windows?

returns 4 on a quadcore xp64

Marc

2008/12/14 Marc Weustink :

Return 2 on Intel Core Duo