Current PGO profile counts are not context sensitive. The branch probabilities
for the inlined functions are kept the same for all call-sites, and they might
be very different from the actual branch probabilities. These suboptimal
profiles can greatly affect some downstream optimizations, in particular for
the machine basic block placement optimization.
In this patch, we propose to have a post-inline PGO instrumentation/use pass,
which we called Context Sensitive PGO (CSPGO). For the users who want the best
possible performance, they can perform a second round of PGO instrument/use on
the top of the regular PGO. They will have two sets of profile counts. The
first pass profile will be manly for inline, indirect-call promotion, and
CGSCC simplification pass optimizations. The second pass profile is for
post-inline optimizations and code-gen optimizations.
A typical usage:
// Regular PGO instrumentation and generate pass1 profile.
> clang -O2 -fprofile-generate source.c -o gen
> ./gen
> llvm-profdata merge default.*profraw -o pass1.profdata
// CSPGO instrumentation.
> clang -O2 -fprofile-use=pass1.profdata -fcs-profile-generate -o gen2
> ./gen2
// Merge two sets of profiles
> llvm-profdata merge default.*profraw pass1.profdata -o profile.profdata
// Use the combined profile. Pass manager will invoke two PGO use passes.
> clang -O2 -fprofile-use=profile.profdata -o use
This change touches many components in the compiler. The reviewed patch
(D54175) will committed in phrases.
Differential Revision: https://reviews.llvm.org/D54175
llvm-svn: 354930
SITargetLowering::reassociateScalarOps() does not touch constants
so that DAGCombiner::ReassociateOps() does not revert the combine.
However a global address is not a ConstantSDNode.
Switched to the method used by DAGCombiner::ReassociateOps() itself
to detect constants.
Differential Revision: https://reviews.llvm.org/D58695
llvm-svn: 354926
Original implementation can't correctly handle __m256 and __m512 types
passed by reference through stack. This patch fixes it.
Patch by Wei Xiao!
Differential Revision: https://reviews.llvm.org/D57643
llvm-svn: 354921
Check that we do not crash if a parallelism group is explicitly set to
None. Permits usage of the following pattern.
[lit.common.cfg]
lit_config.parallelism_groups['my_group'] = None
if <condition>:
lit_config.parallelism_groups['my_group'] = 3
[project/lit.cfg]
config.parallelism_group = 'my_group'
Reviewers: rnk
Differential Revision: https://reviews.llvm.org/D58305
llvm-svn: 354912
Fix https://bugs.llvm.org/show_bug.cgi?id=38583: Describe
how memcpy/memmove/memset behave when len=0. Also fix
some fallout from when the alignment parameter was
replaced by an attribute.
This closes PR38583.
Patch by RalfJung (Ralf)
Differential Revision: https://reviews.llvm.org/D57600
llvm-svn: 354911
The previous sort comparator was not deterministic, i.e. in some
situations it would be possible for lhs < rhs && rhs < lhs. This was
discovered by an STL assertion in a Windows debug build of llvm-tblgen.
Differential Revision: https://reviews.llvm.org/D58687
llvm-svn: 354910
As discussed on llvm-dev:
http://lists.llvm.org/pipermail/llvm-dev/2019-February/130491.html
We can't remove the compare+select in the general case because
we are treating funnel shift like a standard instruction (as
opposed to a special instruction like select/phi).
That means that if one of the operands of the funnel shift is
poison, the result is poison regardless of whether we know that
the operand is actually unused based on the instruction's
particular semantics.
The motivating case for this transform is the more specific
rotate op (rather than funnel shift), and we are preserving the
fold for that case because there is no chance of introducing
extra poison when there is no anonymous extra operand to the
funnel shift.
llvm-svn: 354905
This patch enables the following
1) AMD family 17h "znver2" tune flag (-march, -mcpu).
2) ISAs that are enabled for "znver2" architecture.
3) For the time being, it uses the znver1 scheduler model.
4) Tests are updated.
5) Scheduler descriptions are yet to be put in place.
Reviewers: craig.topper
Differential Revision: https://reviews.llvm.org/D58343
llvm-svn: 354897
This patch aims to make sure that any such constant that can be generated
with a vector instruction (for example VGBM) is recognized as such during
legalization and kept as a target independent node through post-legalize
DAGCombining.
Two new functions named isVectorConstantLegal() and loadVectorConstant()
replace old ways of handling vector/FP constants.
A new struct named SystemZVectorConstantInfo is used to cache the results of
isVectorConstantLegal() and pass them onto loadVectorConstant().
Support for fp128 constants in the presence of FeatureVectorEnhancements1
(z14) has been added.
Review: Ulrich Weigand
https://reviews.llvm.org/D58270
llvm-svn: 354896
Rotate is a special-case of funnel shift that has different
poison constraints than the general case. That's not visible
yet in the existing tests, but it needs to be corrected.
llvm-svn: 354894
Dispatch stall cycles may be associated to multiple dispatch stall events.
Before this patch, each stall cycle was associated with a single stall event.
This patch also improves a couple of code comments, and adds a helper method to
query the Scheduler for dispatch stalls.
llvm-svn: 354877
This allows tools to parse/dump the architecture specific tags
like DT_MIPS_*, DT_PPC64_* and DT_HEXAGON_*
Also fixes a bug in DynamicTags.def which was revealed in this patch.
Differential revision: https://reviews.llvm.org/D58667
llvm-svn: 354876
The --disassembler-options, or -M, are used to customize
the disassembler and affect its output.
The two implemented options allow selecting register names on ARM:
* With -Mreg-names-raw, the disassembler uses rNN for all registers.
* With -Mreg-names-std it prints sp, lr and pc for r13, r14 and r15,
which is the default behavior of llvm-objdump.
Differential Revision: https://reviews.llvm.org/D57680
llvm-svn: 354870
If SADDSAT/SSUBSAT are legal, then we can expand SADDO/SSUBO by performing a ADD/SUB and a SADDO/SSUBO and then compare the results.
I looked at doing this for UADDO/USUBO as well but as we don't have to do as many range comparisons I didn't see any/much benefit.
Differential Revision: https://reviews.llvm.org/D58637
llvm-svn: 354866
For outgoing varargs arguments, it's necessary to check the OrigAlign field
of the corresponding OutputArg entry to determine argument alignment, rather
than just computing an alignment from the argument value type. This is
because types like fp128 are split into multiple argument values, with
narrower types that don't reflect the ABI alignment of the full fp128.
This fixes the printf("printfL: %4.*Lf\n", 2, lval); testcase.
Differential Revision: https://reviews.llvm.org/D58656
llvm-svn: 354846
As requested during review of D57601 <https://reviews.llvm.org/D57601> https://reviews.llvm.org/D57601, be equally conservative for atomic MMOs as for volatile MMOs in all in tree backends. At the moment, all atomic MMOs are also volatile, but I'm about to change that.
Differential Revision: https://reviews.llvm.org/D58490
Note: D58498 landed in several pieces as individual backends were approved. This is the last chunk.
llvm-svn: 354845
Summary: We shouldn't delete elements while iterating a ranged for loop.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58519
llvm-svn: 354844
Summary:
- Indent check lines to easily figure out try-catch-end structure
- Add the original C++ code the tests were genereated from
- Add a few more lines to make the structure more readable
- Rename a couple function / structures
- Add label and branch annotations to cfg-stackify-eh.ll
- Temporarily delete check lines for `test1` in `cfg-stackify-eh.ll`
because it will be updated in a later CL soon and there's no point of
making it look better here
Reviewers: dschuff
Subscribers: sunfish, sbc100, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58562
llvm-svn: 354842
Summary:
The llvm-cov tool needs to be able to find coverage names in the
executable, so the .lprfn and .lcovmap sections cannot be merged into
.rdata.
Also, the linker merges .lprfn$M into .lprfn, so llvm-cov needs to
handle that when looking up sections. It has to support running on both
relocatable object files and linked PE files.
Lastly, when loading .lprfn from a PE file, llvm-cov needs to skip the
leading zero byte added by the profile runtime.
Reviewers: vsk
Subscribers: hiraditya, #sanitizers, llvm-commits
Tags: #sanitizers, #llvm
Differential Revision: https://reviews.llvm.org/D58661
llvm-svn: 354840
Summary:
Use a custom calling convention handler for interrupts instead of fixing
up the locations in LowerMemArgument. This way, the offsets are correct
when constructed and we don't need to account for them in as many
places.
Depends on D56883
Replaces D56275
Reviewers: craig.topper, phil-opp
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D56944
llvm-svn: 354837
Try to use concat_vectors. Also remove unnecessary assert on
pointers. Fixes asserting for <4 x s16> operations and 64-bit pointers
for AMDGPU.
llvm-svn: 354828
We have all the necessary legalization, expansion and unrolling support required for the *.overflow intrinsics with vector types, so update the docs to make that clear.
Note: vectorization is not in place yet (the non-homogenous return types aren't well supported) so we still must explicitly use the vectors intrinsics and not reply on slp/loop.
Differential Revision: https://reviews.llvm.org/D58618
llvm-svn: 354821
Summary:
In D58580 i have noted that `llvm::to_string()` is a memory hog.
It uses `raw_string_ostream`, and since it was buffered,
every `raw_string_ostream` had a cost of `BUFSIZ` bytes
(which is `8192` at least here). So every `llvm::to_string()`
call, even to just print an `int`, costed `8192` bytes.
In D58580, getting rid of that buffering //had// significant
performance and memory consumption improvements for `llvm-xray convert`.
Similarly, in D58580 @rnk pointed out that the `raw_svector_ostream`
is already unbuffered, and `write_unsigned_impl` and friends
do internal buffering. So it should be ok performance-wise to just
make the `raw_string_ostream` itself unbuffered.
Here, i don't have any perf measurements.
Another letdown is that i'm leaving a loose-end - not deleting the
`flush()` method. I don't expect that cleanup to be anything more
than just fixing every new compiler error, but i'm presently unable
to do that. Will look into that later.
Reviewers: rnk, zturner
Reviewed By: rnk
Subscribers: kristina, jdoerfert, llvm-commits, rnk
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58643
llvm-svn: 354819
