Intel® Parallel Studio (Archived)

Parallel Inspector Gating Control

Hello List,

The Intel Parallel Inspector needs a gating control.

ie, I need to be able to specifystart log and end log commands via an API function call, or via a GUI.

This is required because waiting up to 300X the normal execution time is prohibitive.
I am sitting there waiting more than 10 minutes just for mygame to boot, then I have to navigate
menus and then wait 10 or minutes just to get into a level.

I am only interested in capturing full threading information for 1 to 10 frames of running gameplay.

Intel Larrabee Simulator

I would like to know if there is any Larabee simulator available where I can try Parallel studio. I have downloaded the evaluation version of Intel Parallel Studio and would like to know if I can run it on standard x86 machine or how I can simulate a parallel architecture.
Note: I have already worked on IBM Cell.

Would really appreciate help and guidance

Missing Symbol when using unsigned integers as index in parallel for-loops

When I'm using unsigned index-variables in optimized for-loops as it is allowed in OMP 3.0 the linker can't find the symbol "___kmpc_for_static_init_4u". Changing to signed integer will remove the problem. I linked with the libraries mkl_intel_c.lib, mkl_intel_thread.lib, mkl_core.lib. What's going wrong there ?

Details on the Intel Parallel Studio Parallelism Contest & Lab at the Intel Developer Forum San Francisco 2009

Intel Parallel Studio Retail Value $799 just for entering the contest!
Winners receive $250 Visa Gift Card and mention in the Intel Booth at IDF

If you are attending the Intel Developer Forum San Francisco 2009 and want to get started early on Intel Parallel Studio Parallelism Contest & Lab,here are all the details (note: you must attend IDF to enter the contest).

Intel OpenMP 3.0 and TBB Task Scheduler

Dear Intel Experts,

I would like to know whether Intel OpenMP 3.0 task scheduler using work-stealing approach for dynamic load-balancing.

Regarding TBB, I would like to know whether the new algorithms, Parallel_invoke and Parallel_foe_each, are using the work-stealing mechanism of TBB like Parallel_for and Parallel_reduce for dynamic load balancing.

Thanks in advance, Ami

OpenMP Tasks not working.


The following simple example does not work on my OS. I am evaluating the Parallel Studio.

The project properties have OpenMP enabled.

My OS is Vista x64 and the Composer is integrated into VS 2005 Academic Edition.

After starting the console application it goes into an infinite loop forcing me to reboot the OS.

It seems that no synchronisation points (taskwait) and termination conditions are considered.

Any tips on how to solve the issue are welcome.



#include "stdafx.h"

weird call stack

During evaulating intel parallel studio, it shows weird call tree so I cannot figure out the performance bottlenecks.
Here's one example. CriticalSection::Lock never calls IsExistant and Alloc.

Of course, the pdb file is up-to-date. I completely disabled compiler optimization settings and the problem continues.
Any helps are welcomed. Thanks in advance.

Get a free book "Optimizing Applications for Multi-Core Processors"

From now untilSep 30, 2009, the first 100 users* who meet the following requirements will get a free book "Optimizing Applications for Multi-Core Processors" based on Intel Integrated Performance Primitives (Intel IPP) , which is now part of Intel Parallel Studio/Composer.

Suscribirse a Intel® Parallel Studio (Archived)