On Tue, Aug 29, 2017 at 9:32 AM, Martin Liška <mli...@suse.cz> wrote:
> On 08/28/2017 09:15 PM, Martin Liška wrote:
>> On 08/28/2017 04:06 PM, Jeff Law wrote:
>>> On 08/28/2017 01:16 AM, Martin Liška wrote:
>>>> Hello.
>>>>
>>>> I've just repeatedly seen stuck in build process:
>>>>
>>>> make[5]: Entering directory
>>>> `/home/marxin/Programming/gcc/objdir/powerpc64le-unknown-linux-gnu/libstdc++-v3/po'
>>>> msgfmt -o de.mo ../../../../libstdc++-v3/po/de.po
>>>>
>>>> 49 __asm volatile ("sc; mfcr %0"
>>>> Missing separate debuginfos, use: debuginfo-install
>>>> gettext-0.18.2.1-4.el7.ppc64le
>>>> (gdb) bt
>>>> #0 0x00003fff85d8bac8 in sys_futex0 (val=-1, op=128, addr=0x3fff85db0520
>>>> <acc_device_lock>) at ../../../libgomp/config/linux/powerpc/futex.h:49
>>>> #1 futex_wait (val=-1, addr=0x3fff85db0520 <acc_device_lock>) at
>>>> ../../../libgomp/config/linux/powerpc/futex.h:62
>>>> #2 do_wait (val=-1, addr=<optimized out>) at
>>>> ../../../libgomp/config/linux/wait.h:67
>>>> #3 gomp_mutex_lock_slow (mutex=0x3fff85db0520 <acc_device_lock>,
>>>> oldval=<optimized out>) at ../../../libgomp/config/linux/mutex.c:63
>>>> #4 0x00003fff85d98b04 in gomp_mutex_lock (mutex=0x3fff85db0520
>>>> <acc_device_lock>) at ../../../libgomp/config/linux/mutex.h:57
>>>> #5 goacc_register (disp=0x3fff85db0090 <host_dispatch>) at
>>>> ../../../libgomp/oacc-init.c:74
>>>> #6 0x00003fff85d983fc in goacc_host_init () at
>>>> ../../../libgomp/oacc-host.c:265
>>>> #7 0x00003fff85d99c88 in goacc_runtime_initialize () at
>>>> ../../../libgomp/oacc-init.c:657
>>>> #8 0x00003fff85d7882c in initialize_env () at ../../../libgomp/env.c:1340
>>>> #9 0x00003fff86525c74 in _dl_init_internal () from /lib64/ld64.so.2
>>>> #10 0x00003fff865119cc in _dl_start_user () from /lib64/ld64.so.2
>>>>
>> I did the same with the same result. Note that I can see the same problem
>> on gcc110 machine :/
>>
[...]
>
> Looks it uses different invocation of futex syscall. In order to have it
> working I needed to configure gettext w/ --disable-openmp.
> Note that the former invocation of msgfmt contains just a single futex
> syscall, so should not be blocked by anything else.
Then it looks very much like libgomp got its memory barriers wrong for
powerpc64.
