- User Since
- Mar 5 2014, 4:23 PM (350 w, 4 d)
Tue, Nov 3
LGTM, an example of a gep with inbounds wouldbe nice. there are some test cases like: CodeGen/2009-02-13-zerosize-union-field.c, CodeGen/2010-07-14-ref-off-end.c etc from where we can take a reduced example for the doc.
@vsk Let me know if you dont have bandwidth to land. I can land it otherwise.
Oct 24 2020
Please fix clang-format issues.
Instcombine also expands small (16 bytes, hardcoded) memcpy's
or if you prefer, I can land it in its current state.
Oct 20 2020
Good to have these tests. I'd wait for the previous patches in the stack to be reviewed.
@rjf do you have numbers on Firefox. Let us know.
It'll be nice to know if this patch worked fine with a set of regression tests.
results on LLVM testsuite, or clang bootstrap will really help.
Oct 3 2020
Sep 9 2020
Any plans to merge this patch?
Aug 28 2020
nit: If FIXME's are mostly future works, then please replace them with TODOs.
Aug 21 2020
Is the test failure related to this patch?
Aug 17 2020
Self approving because this is NFC change to outline function definitions.
then it may be possible to construct a synthetic/fake profile as a pre-processing step
Addressed fhahn's comments
please run clang-format
Aug 15 2020
Aug 14 2020
FWIW C++ doesn't really have a lattice anymore: https://wg21.link/p0418
Is there a guidance for the users of 'isStrongerThan', isStrongerThanUnordered etc.?
Is this patch still useful now that D53514 has landed?
please run clang-format.
..anyway I can try to describe how thing work using some example. Is this what you are looking for?
yes. Thank you.
Can we add more test cases to include eh_pad, invokeinst,
please run clang-format on the patch.
Overall approach looks good to me even when we don't see good SPEC-17 numbers as the optimization is intended to reduce page faults. The improvements would be more pronounced in large applications. I'll review the code in more detail in the next few days. Thanks for working on this.
Aug 13 2020
Is this work based on any paper/implementation?
Can we add some documentation at the top of the file to get an overall idea of the cost model?
Fixed the bug in: https://bugs.llvm.org/show_bug.cgi?id=45442
Updated test cases.
FYI: libstdc++ patch sent for review: https://gcc.gnu.org/pipermail/gcc-patches/2020-August/551934.html
Self approving as it is a trivial change and fixes PR45442
The patch looks legit. Wonder if such a patch should be sent to libstdc++ too.
Aug 12 2020
https://bugs.llvm.org/show_bug.cgi?id=42283 has been fixed.
Added a patch to libcxxabi: https://reviews.llvm.org/D85873
I don't think we need to mark the object constructor as cold. We want to mark inlined slow paths of local static variables (the call to __cxa_guard_acquire, the call to the object constructor, etc.,) as cold.
It doesn’t make sense to me to make alternations to standard library functions within the compiler. It seems better to simply patch the standard library.
Aug 10 2020
Please fix clang-tidy warnings.
Aug 9 2020
Thanks for adding the results, could you share the script to measure bootstrap numbers?
Aug 7 2020
cc: @t.p.northover does this fix look reasonable for PR37240?
We evaluated the Machine Function Splitter pass on clang bootstrap and SPECInt 2017.
LGTM. nice find!
Aug 6 2020
Aug 5 2020
Please share performance numbers for publicly available workload(s).
Aug 4 2020
Fixed in: D85232
Fixed in: D85232
The ARM build bots do not compile this target as part of their build, causing this test to abort when '-codegenprepare' is added without any REQUIRES clause.