A bug in zgelsd in MKL 15.0

Hi there, 

Thank you for reading this post. 

I got these error messages when calling zgelsd  in MKL 15.0 to solve  a fairly large matrix,

Intel MKL INTERNAL ERROR: Condition 1 detected in function DLASD4.

Intel MKL INTERNAL ERROR: Condition 1 detected in function DLASD8.

I googled online and found the exact issue here, where it said the bug had been fixed in MKL 11 update 5.

pin-2.14-71313 and WinSock library

I have a problem trying to start my pintool built with WinSock library (ws2_32.lib) - it immediately exits with message "Failure to open DLL file WS2_32.dll".
I've prepared a simple pintool to illistrate the problem:

#include "pin.H"

namespace WINDOWS
#include <Ws2tcpip.h>
void *p = WSAStartup;

int main(int argc, char *argv[])
if (PIN_Init(argc, argv)) return 1;
return 0;

Package update on the target is required

I am trying to remotely collect data on my target machine using the VTune Amplifier. The passwordless connection is already set up. When I try to connect to the remote machine, this is the message I get:

Detected VTune Amplifier build #367959 on the target system at ..path/to/vtune/installation... with the build #393444 on the host. Package update on the target is required. Amplifier cannot detect remote machine configuration.

ipp lead to decrease performance


i have a system with 15 -750 cpu and windows 8.1 and I use IPP8.2 .

my program have a greate number Array Mul ,Div or sqrt.

i write a small code with ipp and use both ippm and ipps for mul array and compare that code performance with my simple array mul.

my code is this:


    Ipp64f* src=new Ipp64f[200]();
    for(int i=0;i<200;i++)
        src[i]=i; // initialize source array with values
    Ipp64f* res=new Ipp64f[200]();

Ivy Bridge, counting cycles stalled due to LLC cache load misses?


On Ivy Bridge there are the following counters:


but no CYCLE_ACTIVITY.CYCLES_LLC_PENDING. I have performed some profiling and my results suggest you cannot just subtract the first two counters from the third counter, to get the LLC value. There are three counters for the number of times there is a cache miss, but I want to know the effect of stalling.

Inspector fails on most of OmpScr benchmarks


I am running inspector on the OmpScr benchmark. The benchmark allow you to specify a problem size for each of the programs. When I run inspector using small size problem it is able to finish the verification process most of the time but for some of the problem (i.e. c_loopB.badSolution1.par). I get the error:

Error: Internal error. Please contact Intel customer support team.

Compiler bug?

I am a PhD student and am working at classification of code fragments on a binary level. For that, I used the Intel compiler to compile several open source projects. While analyzing the code, I stumbled upon an interesting code snippet I cannot find another explanation than a potential bug.

Suscribirse a Vectorización