In our previous episode, Jonas Maebe said:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is on non-x86 machines, because it's
missing memory barriers (and I
Helmut Hartl pisze:
-Original message-
From: Dariusz Mazur dar...@emadar.com
Sent: Fri 18-09-2009 16:24
To: FPC-Pascal users discussions fpc-pascal@lists.freepascal.org;
Subject: Re: [fpc-pascal] getting started with threads
David Emerson pisze:
I am getting started
Jonas Maebe wrote:
on x86 too). Atomic operations are not memory barriers by themselves,
and the fact that you perform an atomic operation does not mean that
afterwards all cpu's will immediately see this new value.
Explain? Isn't the point of an atomic update that it doesn't matter
whether
On 19 Sep 2009, at 10:36, Micha Nelissen wrote:
Jonas Maebe wrote:
on x86 too). Atomic operations are not memory barriers by
themselves, and the fact that you perform an atomic operation does
not mean that afterwards all cpu's will immediately see this new
value.
Explain? Isn't the
David Emerson schreef:
I am getting started with threads (linux/cthreads) and I'm very happy so
far, but unsure of the best way to tackle my situation.
I have a program that needs to perform about 10,000 independent tasks,
which usually involve waiting for I/O; thus it makes sense to use
David Emerson pisze:
I am getting started with threads (linux/cthreads) and I'm very happy so
far, but unsure of the best way to tackle my situation.
I have a program that needs to perform about 10,000 independent tasks,
which usually involve waiting for I/O; thus it makes sense to use
On 18 Sep 2009, at 16:24, Dariusz Mazur wrote:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is on non-x86 machines, because it's
missing memory barriers (and I
Jonas Maebe schrieb:
On 18 Sep 2009, at 16:24, Dariusz Mazur wrote:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is on non-x86 machines, because it's missing
Jonas Maebe pisze:
On 18 Sep 2009, at 16:24, Dariusz Mazur wrote:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is on non-x86 machines, because it's
missing memory
On 18 Sep 2009, at 21:30, Dariusz Mazur wrote:
On 18 Sep 2009, at 16:24, Dariusz Mazur wrote:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is on non-x86
Jonas Maebe pisze:
On 18 Sep 2009, at 21:30, Dariusz Mazur wrote:
On 18 Sep 2009, at 16:24, Dariusz Mazur wrote:
I use own lockfree FIFO http://www.emadar.com/fpc/lockfree.htm to
distribute task between threads
its much faster and well scaling on multicore.
Note that it won't work as is
On 18 Sep 2009, at 23:04, Dariusz Mazur wrote:
But is this optimal solution:
procedure SysThreadSwitch;
begin
Sleep(0);
end;
WinThreadManager.ThreadSwitch :=...@systhreadswitch;
procedure ThreadSwitch;
begin
CurrentTM.ThreadSwitch;
end;
We have 2 unnecessary invoke
-Original message-
From: Dariusz Mazur dar...@emadar.com
Sent: Fri 18-09-2009 16:24
To: FPC-Pascal users discussions fpc-pascal@lists.freepascal.org;
Subject: Re: [fpc-pascal] getting started with threads
David Emerson pisze:
I am getting started with threads (linux/cthreads) and I'm
I am getting started with threads (linux/cthreads) and I'm very happy so
far, but unsure of the best way to tackle my situation.
I have a program that needs to perform about 10,000 independent tasks,
which usually involve waiting for I/O; thus it makes sense to use
several threads so that some
Nice to see you posted this. Love, Dad
On Thursday 17 September 2009 06:07:48 pm David Emerson wrote:
I am getting started with threads (linux/cthreads) and I'm very happy so
far, but unsure of the best way to tackle my situation.
I have a program that needs to perform about 10,000
15 matches
Mail list logo
