Summary: | unhandled instruction bytes: 0xC5 0xFA 0x10 0x5 0x4F 0xC2 | ||
---|---|---|---|
Product: | [Developer tools] valgrind | Reporter: | bugs |
Component: | vex | Assignee: | Julian Seward <jseward> |
Status: | RESOLVED DUPLICATE | ||
Severity: | crash | CC: | Enrico_m, kdebugs, me |
Priority: | NOR | ||
Version: | 3.6.0 | ||
Target Milestone: | --- | ||
Platform: | Arch Linux | ||
OS: | Linux | ||
Latest Commit: | Version Fixed In: | ||
Sentry Crash Report: |
Description
bugs
2011-03-12 21:21:54 UTC
I'm encountering similar problems with real-world code. valgrind-3.6.1 gcc version 4.6.1 20110507 (prerelease) (Debian 4.6.0-7) model name : Intel(R) Core(TM) i5-2410M CPU @ 2.30GHz How to reproduce: int main(void) { int foo = 0; double bar = foo; return 0; } gcc -O0 -march=native foo.c -S results in this line: vcvtsi2sd -4(%rbp), %xmm0, %xmm0 or assembled + objdump: b: c5 fb 2a 45 fc vcvtsi2sdl -0x4(%rbp),%xmm0,%xmm0 -O0 is needed because the test case is too simple. With real code, -O2 etc. cause the same problem. I did not find a more specific flag for -march. Cheers Joern Heissler Yes, I can reproduce this problem with a 2nd gen i5 CPU. Valgrind from 3.7 SVN still crashes (gcc 4.5.3). *** This bug has been marked as a duplicate of bug 273475 *** |