coregrind/m_machine.c | 4 4 + 0 - 0 !
1 file changed, 4 insertions(+)

 workaround sigsegv on ppc
 Signed-off-by: Pierre Habouzit <madcoder@debian.org>

callgrind/callgrind_control.in | 2 1 + 1 - 0 !
1 file changed, 1 insertion(+), 1 deletion(-)

 fix callgrind_control that should look for valgrind.bin and not valgrind

docs/xml/manual-core-adv.xml | 2 1 + 1 - 0 !
1 file changed, 1 insertion(+), 1 deletion(-)

 fix spelling-error-in-manpage found by lintian

configure.ac | 21 11 + 10 - 0 !
mpi/Makefile.am | 11 0 + 11 - 0 !
2 files changed, 11 insertions(+), 21 deletions(-)

 use pkg-config to detect mpi

coregrind/m_gdbserver/remote-utils.c | 6 2 + 4 - 0 !
1 file changed, 2 insertions(+), 4 deletions(-)

 fix path to vgdb executable in output message

configure.ac | 2 1 + 1 - 0 !
1 file changed, 1 insertion(+), 1 deletion(-)

 fix ftbfs on armhf

configure.ac | 4 2 + 2 - 0 !
1 file changed, 2 insertions(+), 2 deletions(-)

 do not require neon on armhf

coregrind/m_redir.c | 6 6 + 0 - 0 !
coregrind/m_trampoline.S | 45 45 + 0 - 0 !
coregrind/pub_core_trampoline.h | 1 1 + 0 - 0 !
3 files changed, 52 insertions(+)

 [patch] add ppc64le linux hardwire for ld64.so.2 strcmp

When dlopen is used we might end up in an assembly powerpc/strcmp.S
variant that is optimized in a way memcheck cannot proof correct. We
try to intercept strcmp in ld.so, but might fail when strcmp is called
before our interception code is loaded. Having an hardwire for ld.so
strcmp (earlier intercept) would solve this.

https://bugs.kde.org/show_bug.cgi?id=508145

(cherry picked from commit 78fe3625f6b8ed4de28527d71c4a98d70e5b3035)