Hello,
Recently, I started learning TBB. I tried to implement RBF calculation using the following program. Unfortunately, but working on 4 cores obtained performance similar to or worse than serial programs. I will be grateful for a hint on how to improve the program.
Thanks,
Stan
#include <iostream>
#include "parallel_1.h"
#include <tbb\tick_count.h>
#include <tbb\parallel_reduce.h>
#include <tbb\task_group.h>
#include <mkl_vml.h>
#include <mkl_blas.h>
Hi,
I am trying to figure out what exactly happens when a task calls wait_for_all(), in a scenario like this one:
------------------------------------------------------------
FibTask& a = *new(allocate_child() ) FibTask(n-1,&x);
FibTask& b = *new(allocate_child() ) FibTask(n-2,&y);
set_ref_count(3);
spawn(b);
spawn(a);
wait_for_all();
//continuation code
------------------------------------------------------------
Hello everyone !
I am facing a small issue when using both OpenMP and TBB in the same application, when this application uses the thread-binding feature of OpenMP, which is enabled by setting the OMP_PROC_BIND environment variable to "true" (more details here http://gcc.gnu.org/onlinedocs/libgomp/OMP_005fPROC_005fBIND.html).
Hi,
I am amit and currently i am exploring intel TBB for our business purpose. I have couple of queries which are listed below. Can you plz help me out?
1. As i have studied that TBB scheduler has unfair and non preemptive scheduling. In our project on multicore platform, we want to develop a time critical application and in which there is requirement like to interrupt a TBB task because of high priority interrupt and my qus is can we preempt a TBB task or Can we acknowledge that interrupt in real time applicatons?
I have a multithread program which uses concurrent_unordered_map (latest tbb version, built from src). It will crashes after several hours running. The core dump is
Does anyone have suggestions for how I can use TBB to solve the following problem?
Hi guys,
Can anyone tell me what's going on with TBB support for condition variables?
I'm developing an app that is using TBB for multi-tasking, and I need condition variables. I found an article here: http://software.intel.com/en-us/blogs/2010/10/01/condition-variable-supp... suggesting that they're supported by TBB.
0 down vote favorite
Is there a way to access concurrent_queue elements without popping, like 'at' function in std::deque. I am accessing the queue elements in different iterations. If i pop the elements in queue, then i have to fill the queue which will be overhead. please suggest me.
Hi,
I would like to develop my application using Intel TBB and Intel's OpenCL driver on Linux. However, when I try to do so, I get a deadlock with the following relevant stack trace below. Note that on stack frame #3, the OpenCL driver calls into MyApp's libtbb.so.2 which was compiled usingTBB 4.0 Update 1. If I look in the OpenCL driver's directory, I see:
$ ls *tbb* /opt/intel/opencl-1.2-3.0.56860/lib64
libtbbmalloc.so libtbbmalloc.so.2 libtbb_preview.so libtbb_preview.so.2
Hi,
I haven't been to the Intel TBB website recently and was pleasantly surprised at the improvements! However, the downloads page seems to no longer indicate which of the OSS releases are the commercially aligned ones. So the question is which of the TBB 4.1 updates is "commercially aligned"?
Thanks,
-Edward
