Intel® Cilk++ Software Development Kit (Archived)

creating dll for a cilk++ file

hello 

i tried to create a dll for simple cilk++ file in vs2008 

the code is

the header file is

#pragma once

#include "stdio.h"
#pragma once

class myclass
{
public:
void hello();
};

the body is

#include "header.h"

void hello()
{
printf("hello world\n");
}

int cilk_main()
{
cilk_spawn hello();
cilk_spawn hello();
cilk_sync;
return 0;
}

i am trying to create dll for above file using this code which is in another file

Assigning tasks to Cilk++ workers in a NUMA system

I have a NUMA system. There is a thread for each core in the system. Threads that process similar data are assigned to the same node to reuse the data in the large L3 cache of the node. I want threads that are assigned to the same node should steal each other's jobs. If all jobs on a node have finished, these threads should steal jobs assigned to threads on other nodes. How can I implement this via Cilk++?

Pinning Cilk++ threads to nodes

I have a set of tasks 1 to N. Each task i accesses data[i]. I have W number of workers. W << N. Most of data processed in specific tasks are same so these tasks must be executed on the same core for cache reuse. The data is allocated on memory of specific nodes. The similarity among chunks of data processed in tasks are determined on runtime.

Error While Trying to use CilkScreen or CilkView

Hi All,

I have installed the latest version of Intel Parallel studio in 32-bit Linux Mint( Cinnamom 14 Nadia)  and icpc is working fine. I downloaded the latest SDK packages for Cilk utilities. I am getting the following error when I am trying to execute the sample quick-sort race example with Cilkscreen or Cilkview.

:Source/pin/vm_ia32_l/jit_region_ia32_linux.cpp:XlateSysCall:34: Sysenter is supported on IA32 only and the expected location is inside Linux Gate

cilk::reducer_opadd<boost::numeric::ublas::matrix<double>>

Hi all,

Say, I'd like to 'reduce' (sum some values) to a 2D array.

I don't know it's size during compile-time. Though, it's size is constant during execution.

When cilk creates multiple strands, it won't initialize arrays...

(

to create an array, filled with zeros one need:

boost::numeric::ublas::matrix<double> m (100, 100);

m.clear();

)

but with current cilk_oppadd I'm unable to pass array's size. Also worker's arrays seem to be not initialized....

Possible solutions:

speedup was not optimized while increasing the number of threads

Hi, 

I have installed ubuntu 10.04 in dual boot with windows 7;then I have installed cilk++ in ubuntu 

while running my cilk++ program, the speedup was not optimized while increasing the number of threads.

this problem can be related to the installation of ubuntu in dual boot with windows .? 

cilk++ compiling problem

HI, I was trying to run cilk++ code in cluster with intel-12.0 compiler. However, everytime when I was using the command 'icpc -o test test.cpp', there was a error called: name followed by "::" must be a class or namespace name I used cilk::run() function in my code. And not only this function cannot work well, but also all other cilk functions just get the same problem. I hope you guys can help me with this problem. Best, Lingchen

multithreading program

Hi, I want to run a program on a set of threads but Iobserve that the program appears toconsume all the resources of all the processors in the system, even when there is no parallel work to perform. I follewed the exampleQuickDemo andI create a computation thread using operating-system facilities (_beginthreadex) ...

but also there is no performance Can you tell me wat's wrong please , thanks , this is my source code #define Second (1000) int qmain (void *ArgList) { FPgrowth *fpgrowth = new FPgrowth(); char *file = "retail.dat" ; fpgrowth->setData(file,3);

Подписаться на Intel® Cilk++ Software Development Kit (Archived)