Some of the passes that calculates tentative layout like LongJmp and
Golang are expecting that only functions with valid index will be
located in hot text section. But currently functions with valid profiles
and not set index are breaking this logic, to fix this we can move the
hasValidProfile() condition from AssignSections pass to ReorderFunctions.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
Differential Revision: https://reviews.llvm.org/D127223
Emit warning when using deprecated option '-reorder-blocks=cache+'.
Auto switch to option '-reorder-blocks=ext-tsp'.
Test Plan:
```
ninja check-bolt
```
Added a new test cache+-deprecated.test.
Run and verify that the upstream tests are passed.
Reviewed By: rafauler, Amir, maksfb
Differential Revision: https://reviews.llvm.org/D126722
This reverts commit 3988bd1398.
Did not build on this bot:
https://lab.llvm.org/buildbot#builders/215/builds/6372
/usr/include/c++/9/bits/predefined_ops.h:177:11: error: no match for call to
‘(llvm::less_first) (std::pair<long unsigned int, llvm::bolt::BinaryBasicBlock*>&, const std::pair<long unsigned int, std::nullptr_t>&)’
177 | { return bool(_M_comp(*__it, __val)); }
One could reuse this functor instead of rolling out your own version.
There were a couple other cases where the code was similar, but not
quite the same, such as it might have an assertion in the lambda or other
constructs. Thus, I've not touched any of those, as it might change the
behavior in some way.
As per https://discourse.llvm.org/t/submitting-simple-nfc-patches/62640/3?u=steakhal
Chris Lattner
> LLVM intentionally has a “yes, you can apply common sense judgement to
> things” policy when it comes to code review. If you are doing mechanical
> patches (e.g. adopting less_first) that apply to the entire monorepo,
> then you don’t need everyone in the monorepo to sign off on it. Having
> some +1 validation from someone is useful, but you don’t need everyone
> whose code you touch to weigh in.
Differential Revision: https://reviews.llvm.org/D126068
Fix a bug where shrink-wrapping would use wrong stack offsets
because the stack was being aligned with an AND instruction, hence,
making its true offsets only available during runtime (we can't
statically determine where are the stack elements and we must give up
on this case).
Reviewed By: Amir
Differential Revision: https://reviews.llvm.org/D126110
Address warnings in Release build without assertions.
Tip @tschuett for reporting the issue #55404.
Reviewed By: rafauler
Differential Revision: https://reviews.llvm.org/D125475
Add an option to only peel ICP targets that can be subsequently inlined.
Yet there's no guarantee that they will be inlined.
The mode is independent from the heuristic used to choose ICP targets: by exec
count, mispredictions, or memory profile.
Reviewed By: rafauler
Differential Revision: https://reviews.llvm.org/D124900
`getInliningInfo` is useful in other passes that need to check inlining
eligibility for some function. Move the declaration and InliningInfo definition
out of Inliner class. Prepare for subsequent use in ICP.
Reviewed By: rafauler
Differential Revision: https://reviews.llvm.org/D124899
Rename `opts::IndirectCallPromotion*` to `opts::ICP*`, making option naming
uniform and easier to follow.
Reviewed By: rafauler
Differential Revision: https://reviews.llvm.org/D124879
Check that the function will be emitted in the final binary. Preserving
old function address is needed in case it is PLT trampiline, that is
currently not moved by the BOLT.
Differential Revision: https://reviews.llvm.org/D122098
BOLT treats aarch64 objects located in text as empty functions with
contant islands. Emit them with at least 8-byte alignment to the new
text section.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
Differential Revision: https://reviews.llvm.org/D122097
AArch64 requires CI to be aligned to 8 bytes due to access instructions
restrictions. E.g. the ldr with imm, where imm must be aligned to 8 bytes.
Differential Revision: https://reviews.llvm.org/D122065
It seems the earlier implementation does not follow the description
in LoopRotationPass.h: It rotates loops even if they are already laid out
correctly. The diff adjusts the behaviour.
Given that the impact of LoopInversionPass is minor, this change won't
yield significant perf differences. Tested on clang-10: there seems to be a
0.1%-0.3% cpu win and a small reduction of branch misses.
**Before:**
BOLT-INFO: 120 Functions were reordered by LoopInversionPass
**After:**
BOLT-INFO: 79 Functions were reordered by LoopInversionPass
Reviewed By: yota9
Differential Revision: https://reviews.llvm.org/D121921
Run tentativeLayoutRelocMode twice only if UseOldText option was passed.
Refactor BF loop to break on condtition met.
Differential Revision: https://reviews.llvm.org/D121825
Since LLVM MC now preserves redundant AdSize override prefix (0x67), remove it
in BOLT explicitly (-x86-strip-redundant-adsize, on by default).
Test Plan:
`bin/llvm-lit -a bolt/test/X86/addr32.s`
Reviewed By: rafauler
Differential Revision: https://reviews.llvm.org/D120975
The BinaryEmitter uses opts::AlignText value to align the hot text
section. Also check that the opts::AlignText is at least
equal opts::AlignFunctions for the same reason, as described in D121392.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
Differential Revision: https://reviews.llvm.org/D121728
The cold text section alignment is set using the maximum alignment value
passed to the emitCodeAlignment. In order to calculate tentetive layout
right we will set the minimum alignment of such sections to the maximum
possible function alignment explicitly.
Differential Revision: https://reviews.llvm.org/D121392
Fix data race reported by ThreadSanitizer in clang.test:
```
ThreadSanitizer: data race /data/llvm-project/bolt/lib/Passes/ShrinkWrapping.cpp:1359:28
in llvm::bolt::ShrinkWrapping::moveSaveRestores()
```
The issue is with incrementing global counters from multiple threads.
Reviewed By: yota9
Differential Revision: https://reviews.llvm.org/D120218
Summary:
- variable 'TotalSize' set but not used
- variable 'TotalCallsTopN' set but not used
- use of bitwise '|' with boolean operands
Reviewed By: maksfb
FBD33911129
Summary:
Move the annotation to avoid dynamic memory allocations.
Improves the CPU time of instrumenting a large binary by 1% (+-0.8%, p-value 0.01)
Test Plan: NFC
Reviewers: maksfb
FBD30091656
Summary:
Refactor bolt/*/Passes to follow the braces rule for if/else/loop from
[LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html).
(cherry picked from FBD33344642)
Summary:
The lower_bound might return the end iterator, the ignoring of which will
cause memory corruption.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
(cherry picked from FBD33307803)
Summary:
The patch moves the shortenInstructions and nop remove to separate binary
passes. As a result when llvm-bolt optimizations stage will begin the
instructions of the binary functions will be absolutely the same as it
was in the binary. This is needed for the golang support by llvm-bolt.
Some of the tests must be changed, since bb alignment nops might create
unreachable BBs in original functions.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
(cherry picked from FBD32896517)
Summary:
Refactor members of BinaryBasicBlock. Replace some std containers with
ADT equivalents. The size of BinaryBasicBlock on x86-64 Linux is reduced
from 232 bytes to 192 bytes.
(cherry picked from FBD33081850)
Vladislav Khmelevsky