Bug 329245 - vex amd64->IR: unhandled instruction bytes: 0x48 0xF 0x5A (cvtps2pd)
Summary: vex amd64->IR: unhandled instruction bytes: 0x48 0xF 0x5A (cvtps2pd)
Status: RESOLVED DUPLICATE of bug 278744
Alias: None
Product: valgrind
Classification: Developer tools
Component: memcheck (show other bugs)
Version: 3.9.0
Platform: Ubuntu Linux
: NOR normal
Target Milestone: ---
Assignee: Julian Seward
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2013-12-26 11:09 UTC by Gaetano Mendola
Modified: 2015-10-12 14:28 UTC (History)
3 users (show)

See Also:
Latest Commit:
Version Fixed In:


Attachments

Note You need to log in before you can comment on or make changes to this bug.
Description Gaetano Mendola 2013-12-26 11:09:17 UTC
While running my application under valgrind this is what I'm getting:

vex amd64->IR: unhandled instruction bytes: 0x48 0xF 0x5A 0x7 0x48 0xF 0x5A 0x4F
vex amd64->IR:   REX=1 REX.W=1 REX.R=0 REX.X=0 REX.B=0
vex amd64->IR:   VEX=0 VEX.L=0 VEX.nVVVV=0x0 ESC=0F
vex amd64->IR:   PFX.66=0 PFX.F2=0 PFX.F3=0
==30824== valgrind: Unrecognised instruction at address 0x66a3b40.
==30824==    at 0x66A3B40: ??? (in /opt/intel/composer_xe_2013.4.183/ipp/lib/intel64/libippsy8.so.7.1)


the "faulty" instruction is a call to ippsMean_32f function present int the Intel  IPP library.

Reproducible: Always

Steps to Reproduce:
Compile the following program:
====================================================================
#include <ipps.h>
int main() {
  float* a = new float[100];
  float myResult;
  ippsMean_32f(a, 100, &myResult, ippAlgHintAccurate);
}
====================================================================
g++ valgrind_ipp_bug.cpp -I /opt/intel/composerxe/ipp/include -lipps -L /opt/intel/composerxe/ipp/lib/intel64/



1.
2.
3.
Comment 1 Gregor Jasny 2015-10-02 20:04:56 UTC
This seems to be a duplicate of 278744 (https://bugs.kde.org/show_bug.cgi?id=278744)
Comment 2 Mark Wielaard 2015-10-12 14:28:19 UTC

*** This bug has been marked as a duplicate of bug 278744 ***