- User Since
- Sep 24 2015, 4:45 AM (120 w, 5 d)
Thu, Jan 11
Ah, I think I understand your plan now.
Wed, Jan 10
Ok, I think, I now understood the change.
Tue, Jan 9
@omalyshe AFAIK this issue is Case#: 03138964
I would have expected, that
printf("%" PRIu64 ": &lock: %lu\n", ompt_get_thread_data()->value, (unsigned long) &lock);
would also fix the issue.
As I understand the issue, this is not a fault in the test code, but the value provided by parallel-begin is wrong? In that case, I suggest to pass NULL for this architecture/compiler.
Mon, Jan 8
Tue, Jan 2
Updated the README
Updated the README
Sun, Dec 24
Removed 32 bit ARM from the list of supported architectures until it is tested.
Sat, Dec 23
I added the requirement for hardware architecture support to LIBOMP_HAVE_OMPT_SUPPORT.
This way one would also get an error when manually turing LIBOMP_OMPT_SUPPORT=on on an unsupported architecture.
Fri, Dec 22
Thu, Dec 21
I think, the address needs to be reset on return. Please include commit 45a3a39 to this patch.
Dec 13 2017
This change is more a performace optimization. (reset the bit in the bitmap to 0)
The callback was set to NULL before and all callback invocation checks for the NULL-pointer.
Dec 8 2017
Dec 7 2017
Dec 5 2017
Nov 29 2017
@omalyshe Which version of icc introduced the ident information for workshare constructs?
Nov 24 2017
Nov 22 2017
@kcc I would still be interested in this change :)
Nov 10 2017
We might want to add another RUN-line for 3, where the first tool returns NULL for ompt_start_tool and only the second tool in the list is initialized.
We can add this test in a later patch
Fix potentially uninitialized value. Thanks, Jonas!
Using Olga's code to only trigger a single warning. Tested and works for me.
Remove warning for fini
Addressing Olgas suggestions
Nov 9 2017
Sections seems reasonable, for the single I would suggest to use the conditional.
Nov 8 2017
Instead of saving the address and printing it in a new team afterwards, you could also use CHECK-DAG and print the address, where you store it.
In that case, you should add another, unrelated match in between (e.g., the thread_begin event)
Nov 5 2017
Subsumed by D38185
Nov 2 2017
Updated diff after merging in master with TR4 patch.
Oct 27 2017
Remove the forward declaration in ompt-internal.h.
Remove unnecessary includes of ompt-internal.h.
Replace all _builtin_expect by the UNLIKELY macro.
Addressing Jonas latest comments.
Addressing the last remaining comments.
Avoid inlining for the ompt_enabled case as Hansang pointed out
Fixed the return of void. Run clang-format again.
Since prerequisites are already in master, now the diff against master. (As Jonas pointed out, the last diff missed the clang-format in the base)
Oct 26 2017
Please update the diff with the clang-format changes I pushed to the branch.
Now with proper clang-format
Renaming of ompt_frame_t split out as suggested by Jonas
The latest update replaces things like "REQUIRES taskgroup" by explicit "XFAIL gcc" for testcases that are expected to fail because either gcc or the gomp interface of libomp don't support the construct or the construct has no runtime call. (see D38880)
Oct 23 2017
Oct 19 2017
Oct 18 2017
Addressing Jonas' comments
Oct 17 2017
Addressed latest comments by jlpeyton
Oct 16 2017
Applied old clang-format file.
Removed all changes in .clang-format, removed all comments from this file.
runtime/src/ $ clang-format -style=file -i *.cpp *.h
Oct 14 2017
Implemented more requested changes
Marked comments that are solved by latest diff as done.
This diff fixes many of the comments. (I will walk over the comments and mark them as done)
This diff is against master + parent dependent differentals
I tried to update the attached diff, but accidently created a new differential: https://reviews.llvm.org/D38920
I built a clang-format using the source suggested by AndreyChurbanov. I still get a diff for the source of master.
Oct 12 2017
For current HEAD of master I get a different result for any combination of the added values (unless I add the DisableFormat=true).
The smallest diff I get if I only add
Changes to clang-format factored out into D38837
Sep 22 2017
Sep 14 2016
Remove regression of already removed if 0 block.
Fix issue pointed out by Jonas
Sep 13 2016
removed single line, that was commented out