Некорректное поведение valgrind в Gentoo

$ ./test

ecko@localhost ~/develop $ ./test
m=5

ecko@localhost ~/develop $ cat /etc/portage/make.conf | grep CFLAGS
CFLAGS="-march=native -O2 -pipe -msse4.2 -mcx16 --param l1-cache-size=16 --param l1-cache-line-size=64 --param l2-cache-size=2048"
CXXFLAGS="${CFLAGS}"

ecko@peka ~ $ cat /etc/portage/env/splitdebug.conf 
CFLAGS="-march=native -O2 -pipe -ggdb"
FEATURES="splitdebug"

ecko@peka ~ $ cat /proc/cpuinfo | head -n 26
processor	: 0
vendor_id	: AuthenticAMD
cpu family	: 21
model		: 16
model name	: AMD A10-4600M APU with Radeon(tm) HD Graphics
stepping	: 1
microcode	: 0x6001116
cpu MHz		: 2300.000
cache size	: 2048 KB
physical id	: 0
siblings	: 4
core id		: 0
cpu cores	: 2
apicid		: 16
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 13
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 popcnt aes xsave avx f16c lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs xop skinit wdt lwp fma4 tce nodeid_msr tbm topoext perfctr_core perfctr_nb arat cpb hw_pstate npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold bmi1
bogomips	: 4591.59
TLB size	: 1536 4K pages
clflush size	: 64
cache_alignment	: 64
address sizes	: 48 bits physical, 48 bits virtual
power management: ts ttp tm 100mhzsteps hwpstate cpb eff_freq_ro

ecko@peka ~ $ lscpu 
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                4
On-line CPU(s) list:   0-3
Thread(s) per core:    2
Core(s) per socket:    2
Socket(s):             1
NUMA node(s):          1
Vendor ID:             AuthenticAMD
CPU family:            21
Model:                 16
Model name:            AMD A10-4600M APU with Radeon(tm) HD Graphics
Stepping:              1
CPU MHz:               2300.000
CPU max MHz:           2300,0000
CPU min MHz:           1400,0000
BogoMIPS:              4591.59
Virtualization:        AMD-V
L1d cache:             16K
L1i cache:             64K
L2 cache:              2048K
NUMA node0 CPU(s):     0-3

$ valgrind --leak-check=yes ./test.c
==6557== Memcheck, a memory error detector
==6557== Copyright (C) 2002-2013, and GNU GPL'd, by Julian Seward et al.
==6557== Using Valgrind-3.9.0 and LibVEX; rerun with -h for copyright info
==6557== Command: ./test.c
==6557== 

valgrind:  Fatal error at startup: a function redirection
valgrind:  which is mandatory for this platform-tool combination
valgrind:  cannot be set up.  Details of the redirection are:
valgrind:  
valgrind:  A must-be-redirected function
valgrind:  whose name matches the pattern:      strlen
valgrind:  in an object with soname matching:   ld-linux-x86-64.so.2
valgrind:  was not found whilst processing
valgrind:  symbols from the object with soname: ld-linux-x86-64.so.2
valgrind:  
valgrind:  Possible fixes: (1, short term): install glibc's debuginfo
valgrind:  package on this machine.  (2, longer term): ask the packagers
valgrind:  for your Linux distribution to please in future ship a non-
valgrind:  stripped ld.so (or whatever the dynamic linker .so is called)
valgrind:  that exports the above-named function using the standard
valgrind:  calling conventions for this platform.  The package you need
valgrind:  to install for fix (1) is called
valgrind:  
valgrind:    On Debian, Ubuntu:                 libc6-dbg
valgrind:    On SuSE, openSuSE, Fedora, RHEL:   glibc-debuginfo
valgrind:  
valgrind:  Cannot continue -- exiting now.  Sorry.

$ gcc -O2 -ggdb -march=native test.c -o test
$ valgrind --leak-check=yes ./test
==8721== Memcheck, a memory error detector
==8721== Copyright (C) 2002-2013, and GNU GPL'd, by Julian Seward et al.
==8721== Using Valgrind-3.9.0 and LibVEX; rerun with -h for copyright info
==8721== Command: ./test
==8721==
m=5
==8721==
==8721== HEAP SUMMARY:
==8721==     in use at exit: 0 bytes in 0 blocks
==8721==   total heap usage: 0 allocs, 0 frees, 0 bytes allocated
==8721==
==8721== All heap blocks were freed -- no leaks are possible
==8721==
==8721== For counts of detected and suppressed errors, rerun with: -v
==8721== ERROR SUMMARY: 0 errors from 0 contexts (suppressed: 1 from 1)

$ grep -i cflags /etc/portage/make.conf
CFLAGS="-march=native -O2 -fomit-frame-pointer -pipe -ggdb"
CXXFLAGS="${CFLAGS}"
$ equery l valgrind ; equery l glibc ; equery l gcc
[IP-] [  ] dev-util/valgrind-3.9.0:0
[IP-] [  ] sys-libs/glibc-2.19-r1:2.2
[IP-] [  ] sys-devel/gcc-4.8.3:4.8

CFLAGS="-O2 -pipe -march=native -msse4.2 -mavx -maes -mpclmul
USE="3dnow 3dnowext fpu mmx mmxext smp sse sse2 sse3 ssse3 sse4a sse4 sse41 sse4_1 sse42 sse4_2"

#include<iostream>
#include<immintrin.h>

int main(){
  volatile __m128i a={2,2};
  __m128i c=_mm_add_epi8(a,a);

  std::cerr<<sizeof c<<' '<<c[0]<<' '<<c[1]<<std::endl;}

$ g++ test.cc&& ./a.out
16 4 4

$ g++ test.cc -mno-sse2
In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/4.9.1/include/xmmintrin.h:1258:0,
                 from /usr/lib/gcc/x86_64-pc-linux-gnu/4.9.1/include/immintrin.h:29,
                 from test.cc:32:
/usr/lib/gcc/x86_64-pc-linux-gnu/4.9.1/include/emmintrin.h: In function 'int main()':
/usr/lib/gcc/x86_64-pc-linux-gnu/4.9.1/include/emmintrin.h:1007:1: error: inlining failed in call to always_inline '__m128i _mm_add_epi8(__m128i, __m128i)': target specific option mismatch
 _mm_add_epi8 (__m128i __A, __m128i __B)
 ^
test.cc:36:29: error: called from here
   __m128i c=_mm_add_epi8(a,a);

 18 #include <string.h>
 19 #include <memcopy.h>
 20
 21 #undef strcmp
 22
 23 /* Compare S1 and S2, returning less than, equal to or
 24    greater than zero if S1 is lexicographically less than,
 25    equal to or greater than S2.  */
 26 int
 27 strcmp (p1, p2)
 28      const char *p1;
 29      const char *p2;
 30 {
 31   const unsigned char *s1 = (const unsigned char *) p1;
 32   const unsigned char *s2 = (const unsigned char *) p2;
 33   unsigned char c1, c2;
 34
 35   do
 36     {
 37       c1 = (unsigned char) *s1++;
 38       c2 = (unsigned char) *s2++;
 39       if (c1 == '\0')
 40     return c1 - c2;
 41     }
 42   while (c1 == c2);
 43
 44   return c1 - c2;
 45 }
 46 libc_hidden_builtin_def (strcmp)