`counter_bias` is incompatible to Bitmap. The distance between Counters
and Bitmap is different between on-memory sections and profraw image.
Reference to `__llvm_profile_bitmap_bias` is generated only if
`-fcoverge-mcdc` `-runtime-counter-relocation` are specified. The
current implementation rejected their options.
```
Runtime counter relocation is presently not supported for MC/DC bitmaps
```
In comparison to non-instrumented binaries, PGO instrumentation binaries
can be significantly slower. For highly threaded programs, this slowdown
can
reach 10x due to data races or false sharing within counters.
This patch incorporates sampling into the PGO instrumentation process to
enhance the speed of instrumentation binaries. The fundamental concept
is similar to the one proposed in https://reviews.llvm.org/D63949.
Three sampling modes are introduced:
1. Simple Sampling: When '-sampled-instr-bust-duration' is set to 1.
2. Fast Burst Sampling: When not using simple sampling, and
'-sampled-instr-period' is set to 65535. This is the default mode of
sampling.
3. Full Burst Sampling: When neither simple nor fast burst sampling is
used.
Utilizing this sampled instrumentation significantly improves the
binary's
execution speed. Measurements show up to 5x speedup with default
settings. Fast burst sampling now results in only around 20% to 30%
slowdown (compared to 8 to 10x slowdown without sampling).
Out tests show that profile quality remains good with sampling,
with edge counts typically showing more than 90% overlap.
For applications whose behavior changes due to binary speed,
sampling instrumentation can enhance performance.
Observations have shown some apps experiencing up to
a ~2% improvement in PGO.
A potential drawback of this patch is the increased binary size
and compilation time. The Sampling method in this patch does
not improve single threaded program instrumentation binary
speed.
This pull request is the first part of an ongoing effort to extends PGO
instrumentation to GPU device code. This PR makes the following changes:
- Adds blank registration functions to device RTL
- Gives PGO globals protected visibility when targeting a supported GPU
- Handles any addrspace casts for PGO calls
- Implements PGO global extraction in GPU plugins (currently only dumps
info)
These changes can be tested by supplying `-fprofile-instrument=clang`
while targeting a GPU.
`rmw_or` is defined as "private alwaysinline". At the moment, it has
just only simple "Read, Or, and Write", which is just same as the
current implementation.
By storing possible test vectors instead of combinations of conditions,
the restriction is dramatically relaxed.
This introduces two options to `cc1`:
* `-fmcdc-max-conditions=32767`
* `-fmcdc-max-test-vectors=2147483646`
This change makes coverage mapping, profraw, and profdata incompatible
with Clang-18.
- Bitmap semantics changed. It is incompatible with previous format.
- `BitmapIdx` in `Decision` points to the end of the bitmap.
- Bitmap is packed per function.
- `llvm-cov` can understand `profdata` generated by `llvm-profdata-18`.
RFC:
https://discourse.llvm.org/t/rfc-coverage-new-algorithm-and-file-format-for-mc-dc/76798
--
Change(s) since llvmorg-19-init-14288-g7ead2d8c7e91
- Update compiler-rt/test/profile/ContinuousSyncMode/image-with-mcdc.c
This broke the lit tests on Mac:
https://green.lab.llvm.org/job/llvm.org/job/clang-stage1-RA/1096/
> By storing possible test vectors instead of combinations of conditions,
> the restriction is dramatically relaxed.
>
> This introduces two options to `cc1`:
>
> * `-fmcdc-max-conditions=32767`
> * `-fmcdc-max-test-vectors=2147483646`
>
> This change makes coverage mapping, profraw, and profdata incompatible
> with Clang-18.
>
> - Bitmap semantics changed. It is incompatible with previous format.
> - `BitmapIdx` in `Decision` points to the end of the bitmap.
> - Bitmap is packed per function.
> - `llvm-cov` can understand `profdata` generated by `llvm-profdata-18`.
>
> RFC:
> https://discourse.llvm.org/t/rfc-coverage-new-algorithm-and-file-format-for-mc-dc/76798
This reverts commit 7ead2d8c7e9114b3f23666209a1654939987cb30.
By storing possible test vectors instead of combinations of conditions,
the restriction is dramatically relaxed.
This introduces two options to `cc1`:
* `-fmcdc-max-conditions=32767`
* `-fmcdc-max-test-vectors=2147483646`
This change makes coverage mapping, profraw, and profdata incompatible
with Clang-18.
- Bitmap semantics changed. It is incompatible with previous format.
- `BitmapIdx` in `Decision` points to the end of the bitmap.
- Bitmap is packed per function.
- `llvm-cov` can understand `profdata` generated by `llvm-profdata-18`.
RFC:
https://discourse.llvm.org/t/rfc-coverage-new-algorithm-and-file-format-for-mc-dc/76798
(The profile format change is split into a standalone change into https://github.com/llvm/llvm-project/pull/81691)
* For InstrFDO value profiling, implement instrumentation and lowering for virtual table address.
* This is controlled by `-enable-vtable-value-profiling` and off by default.
* When the option is on, raw profiles will carry serialized `VTableProfData` structs and compressed vtables as payloads.
* Implement profile reader and writer support
* Raw profile reader is used by `llvm-profdata` but not compiler. Raw profile reader will construct InstrProfSymtab with symbol names, and map profiled runtime address to vtable symbols.
* Indexed profile reader is used by `llvm-profdata` and compiler. When initialized, the reader stores a pointer to the beginning of in-memory compressed vtable names and the length of string. When used in `llvm-profdata`, reader decompress the string to show symbols of a profiled site. When used in compiler, string decompression doesn't
happen since IR is used to construct InstrProfSymtab.
* Indexed profile writer collects the list of vtable names, and stores that to index profiles.
* Text profile reader and writer support are added but mostly follow the implementation for indirect-call value type.
* `llvm-profdata show -show-vtables <args> <profile>` is implemented.
rfc in
https://discourse.llvm.org/t/rfc-dynamic-type-profiling-and-optimizations-in-llvm/74600#pick-instrumentation-points-and-instrument-runtime-types-7
Whether runtime registration is needed is not dependent on the OS but
the file format. For ELF, COFF, Mach-O or XCOFF, we can always use the
linker support. This is important for baremetal platforms such as RTOS
and UEFI platforms where there is no OS but we still don't want to use
runtime registration and rely on linker support instead.
## Motivation
Since we don't need the metadata sections at runtime, we can somehow
offload them from memory at runtime. Initially, I explored [debug info
correlation](https://discourse.llvm.org/t/instrprofiling-lightweight-instrumentation/59113),
which is used for PGO with value profiling disabled. However, it
currently only works with DWARF and it's be hard to add such artificial
debug info for every function in to CodeView which is used on Windows.
So, offloading profile metadata sections at runtime seems to be a
platform independent option.
## Design
The idea is to use new section names for profile name and data sections
and mark them as metadata sections. Under this mode, the new sections
are non-SHF_ALLOC in ELF. So, they are not loaded into memory at runtime
and can be stripped away as a post-linking step. After the process
exits, the generated raw profiles will contains only headers + counters.
llvm-profdata can be used correlate raw profiles with the unstripped
binary to generate indexed profile.
## Data
For chromium base_unittests with code coverage on linux, the binary size
overhead due to instrumentation reduced from 64M to 38.8M (39.4%) and
the raw profile files size reduce from 128M to 68M (46.9%)
```
$ bloaty out/cov/base_unittests.stripped -- out/no-cov/base_unittests.stripped
FILE SIZE VM SIZE
-------------- --------------
+121% +30.4Mi +121% +30.4Mi .text
[NEW] +14.6Mi [NEW] +14.6Mi __llvm_prf_data
[NEW] +10.6Mi [NEW] +10.6Mi __llvm_prf_names
[NEW] +5.86Mi [NEW] +5.86Mi __llvm_prf_cnts
+95% +1.75Mi +95% +1.75Mi .eh_frame
+108% +400Ki +108% +400Ki .eh_frame_hdr
+9.5% +211Ki +9.5% +211Ki .rela.dyn
+9.2% +95.0Ki +9.2% +95.0Ki .data.rel.ro
+5.0% +87.3Ki +5.0% +87.3Ki .rodata
[ = ] 0 +13% +47.0Ki .bss
+40% +1.78Ki +40% +1.78Ki .got
+12% +1.49Ki +12% +1.49Ki .gcc_except_table
[ = ] 0 +65% +1.23Ki .relro_padding
+62% +1.20Ki [ = ] 0 [Unmapped]
+13% +448 +19% +448 .init_array
+8.8% +192 [ = ] 0 [ELF Section Headers]
+0.0% +136 +0.0% +80 [7 Others]
+0.1% +96 +0.1% +96 .dynsym
+1.2% +96 +1.2% +96 .rela.plt
+1.5% +80 +1.2% +64 .plt
[ = ] 0 -99.2% -3.68Ki [LOAD #5 [RW]]
+195% +64.0Mi +194% +64.0Mi TOTAL
$ bloaty out/cov-cor/base_unittests.stripped -- out/no-cov/base_unittests.stripped
FILE SIZE VM SIZE
-------------- --------------
+121% +30.4Mi +121% +30.4Mi .text
[NEW] +5.86Mi [NEW] +5.86Mi __llvm_prf_cnts
+95% +1.75Mi +95% +1.75Mi .eh_frame
+108% +400Ki +108% +400Ki .eh_frame_hdr
+9.5% +211Ki +9.5% +211Ki .rela.dyn
+9.2% +95.0Ki +9.2% +95.0Ki .data.rel.ro
+5.0% +87.3Ki +5.0% +87.3Ki .rodata
[ = ] 0 +13% +47.0Ki .bss
+40% +1.78Ki +40% +1.78Ki .got
+12% +1.49Ki +12% +1.49Ki .gcc_except_table
+13% +448 +19% +448 .init_array
+0.1% +96 +0.1% +96 .dynsym
+1.2% +96 +1.2% +96 .rela.plt
+1.2% +64 +1.2% +64 .plt
+2.9% +64 [ = ] 0 [ELF Section Headers]
+0.0% +40 +0.0% +40 .data
+1.2% +32 +1.2% +32 .got.plt
+0.0% +24 +0.0% +8 [5 Others]
[ = ] 0 -22.9% -872 [LOAD #5 [RW]]
-74.5% -1.44Ki [ = ] 0 [Unmapped]
[ = ] 0 -76.5% -1.45Ki .relro_padding
+118% +38.8Mi +117% +38.8Mi TOTAL
```
A few things to note:
1. llvm-profdata doesn't support filter raw profiles by binary id yet,
so when a raw profile doesn't belongs to the binary being digested by
llvm-profdata, merging will fail. Once this is implemented,
llvm-profdata should be able to only merge raw profiles with the same
binary id as the binary and discard the rest (with mismatched/missing
binary id). The workflow I have in mind is to have scripts invoke
llvm-profdata to get all binary ids for all raw profiles, and
selectively choose the raw pnrofiles with matching binary id and the
binary to llvm-profdata for merging.
2. Note: In COFF, currently they are still loaded into memory but not
used. I didn't do it in this patch because I noticed that `.lcovmap` and
`.lcovfunc` are loaded into memory. A separate patch will address it.
3. This should works with PGO when value profiling is disabled as debug
info correlation currently doing, though I haven't tested this yet.
Akin other passes - refactored the name to `InstrProfilingLoweringPass` to better communicate what it does, and split the pass part and the transformation part to avoid needing to initialize object state during `::run`.
A subsequent PR will move `InstrLowering` to the .cpp file and rename it to `InstrLowerer`.
We'd like to make various instrprof globals large to make them not
contribute to relocation pressure since there are no direct accesses
to them in the module.
Similar to what was done for asan_globals in #74514.
This affects the __llvm_prf_vals, __llvm_prf_vnds, and __llvm_prf_names
sections.
The reland fixes platform.ll.
We'd like to make various instrprof globals large to make them not
contribute to relocation pressure since there are no direct accesses
to them in the module.
Similar to what was done for asan_globals in #74514.
This affects the __llvm_prf_vals, __llvm_prf_vnds, and __llvm_prf_names
sections.
If a suspend happens in the resume part (this can happen in the case of chained coroutines), and that's part of a loop, the pre-split CFG has the suspend block as an exit of that loop. PGO Counter Promotion will then try to commit the temporary counter to the global in that "exit" block (it also does that in the other loop exit BBs, which also includes
the "destroy" case). This interferes with symmetric transfer.
We don't need to commit the counter in the suspend case - it's not a loop exit from the perspective of the behavior of the program. The regular loop exit, together with the "destroy" case, completely cover any updates that may need to happen to the global counter.
Fixes a bug introduced by
commit f95b2f1acf11 ("Reland [InstrProf][compiler-rt] Enable MC/DC
Support in LLVM Source-based Code Coverage (1/3)")
The InstrProfiling pass was refactored when introducing support for
MC/DC such that the creation of the data variable was abstracted and
called only once per function from ::run(). Because ::run() only
iterated over functions there were not fully inlined, and because it
only created the data variable for the first intrinsic that it saw, data
variables corresponding to functions fully inlined into other
instrumented callers would end up without a data variable, resulting in
loss of coverage information. This patch does the following:
1.) Move the call of createDataVariable() to getOrCreateRegionCounters()
so that the creation of the data variable will happen indirectly either
from ::new() or during profile intrinsic lowering when it is needed.
This effectively restores the behavior prior to the refactor and ensures
that all data variables are created when needed (and not duplicated).
2.) Process all MC/DC bitmap parameter intrinsics in ::run() prior to
calling getOrCreateRegionCounters(). This ensures bitmap regions are
created for each function including functions that are fully inlined. It
also ensures that the bitmap region is created for each function prior
to the creation of the data variable because it is referenced by the
data variable. Again, duplication is prevented if the same parameter
intrinsic is inlined into multiple functions.
3.) No longer pass the MC/DC intrinsic to createDataVariable(). This
decouples the creation of the data variable from a specific MC/DC
intrinsic. Instead, with #2 above, store the number of bitmap bytes
required in the PerFunctionProfileData in the ProfileDataMap along with
the function's CounterRegion and BitmapRegion variables. This ties the
bitmap information directly to the function to which it belongs, and the
data variable created for that function can reference that.
Fixes a bug introduced by
commit f95b2f1acf11 ("Reland [InstrProf][compiler-rt] Enable MC/DC
Support in LLVM Source-based Code Coverage (1/3)")
createDataVariable() needs to check that a data variable wasn't already
created before creating it. Previously, this was done inadvertantly in
getOrCreateRegionCounters(), which checked that the RegionCounters was
not created multiple times before creating the counter section and the
data variable. When the creation of the data variable was abstracted
into its own function (createDataVariable()), there was no corresponding
check. This was failing on a case in which an instrumented function was
being inlined into multiple functions and a duplicate data variable was
created, which led to a segfault in emitNameData(). Test case added
based on the repro that also ensures a single data variable was created
in this case.
Part 1 of 3. This includes the LLVM back-end processing and profile
reading/writing components. compiler-rt changes are included.
Differential Revision: https://reviews.llvm.org/D138846
This will make it possible to add visibility attributes to these
variables. This also fixes some type mismatches between the
declaration and the definition.
Reviewed By: bogner, huangjd
Differential Revision: https://reviews.llvm.org/D156599
This reverts commit 32db121b29f78e4c41116b2a8f1c730f9522b202 and subsequent commits.
This causes time regression on llvm-cov even with debug info correlation off.
Partial progress towards removing in-tree uses of `getPointerTo()`,
by employing the following options:
* Drop the call entirely if the sole purpose of it is to support a no-op
bitcast (remove the no-op bitcast as well).
* Replace with `PointerType::get()`/`PointerType::getUnqual()`
This is a NFC cleanup effort.
Reviewed By: barannikov88
Differential Revision: https://reviews.llvm.org/D155232
This seems to cause Clang to crash, see comments on the code review. Reverting
until the problem can be investigated.
> Part 1 of 3. This includes the LLVM back-end processing and profile
> reading/writing components. compiler-rt changes are included.
>
> Differential Revision: https://reviews.llvm.org/D138846
This reverts commit a50486fd736ab2fe03fcacaf8b98876db77217a7.
Part 1 of 3. This includes the LLVM back-end processing and profile
reading/writing components. compiler-rt changes are included.
Differential Revision: https://reviews.llvm.org/D138846
Debug info correlation is an option in InstrProfiling pass, which is used by
both IR instrumentation and front-end instrumentation. So, Clang coverage can
also benefits the binary size saving from it.
Reviewed By: ellis
Differential Revision: https://reviews.llvm.org/D157913
Emit warnings when `InstrProfCorrelator` finds problems with debug info for lightweight instrumentation profile correlation. To prevent excessive printing, only emit the first 5 warnings.
In addition, remove a diagnostic about missing debug info in `InstrProfiling.cpp`. Some compiler-generated functions, e.g., `__clang_call_terminate`, does not emit debug info and will fail a build if `-Werror` is used. This warning is not actionable by the user and I have not seen non-compiler-generated functions fail this test.
Reviewed By: smeenai
Differential Revision: https://reviews.llvm.org/D156006
As described in [0], this extends IRPGO to support //Temporal Profiling//.
When `-pgo-temporal-instrumentation` is used we add the `llvm.instrprof.timestamp()` intrinsic to the entry of functions which in turn gets lowered to a call to the compiler-rt function `INSTR_PROF_PROFILE_SET_TIMESTAMP()`. A new field in the `llvm_prf_cnts` section stores each function's timestamp. Then in `llvm-profdata merge` we convert these function timestamps into a //trace// and add it to the indexed profile.
Since these traces could significantly increase the profile size, we've added `-max-temporal-profile-trace-length` and `-temporal-profile-trace-reservoir-size` to limit the length of a trace and the number of traces in a profile, respectively.
In a future diff we plan to use these traces to construct an optimized function order to reduce the number of page faults during startup.
Special thanks to Julian Mestre for helping with reservoir sampling.
[0] https://discourse.llvm.org/t/rfc-temporal-profiling-extension-for-irpgo/68068
Reviewed By: snehasish
Differential Revision: https://reviews.llvm.org/D147287
This diff implements minimal block coverage instrumentation. When the `-pgo-block-coverage` option is used, basic blocks will be instrumented for block coverage using single byte booleans. The coverage of some basic blocks can be inferred from others, so not every basic block is instrumented. In fact, we found that only ~60% of basic blocks need to be instrumented. These differences lead to less size overhead when compared to instrumenting block counts. For example, block coverage on the clang binary has an overhead of 20 Mi (17%) compared to 56 Mi (47%) with block counts.
Even though block coverage profiles have less precision than block count profiles, they can still be used to guide optimizations. In `PGOUseFunc` we use block coverage to populate edge weights such that BFI gives nonzero counts to only covered blocks. We do this by 1) setting the entry count of covered functions to a large value, i.e., 10000 and 2) populating edge weights using block coverage. In the next diff https://reviews.llvm.org/D125743 we use BFI to guide the machine outliner to avoid outlining covered blocks. This `-pgo-block-coverage` option provides a trade off of generating less precise profiles for faster and smaller instrumented binaries.
The `BlockCoverageInference` class defines the algorithm to find the minimal set of basic blocks that need to be instrumented for coverage. This is different from the Kirchhoff circuit law optimization that is used for edge **counts** because that does not work for block **coverage**. The reason for this is that edge counts can be added together to find a missing count while block coverage cannot since they store boolean values. So we need a new algorithm to find which blocks must be instrumented.
The details on this algorithm can be found in this paper titled "Minimum Coverage Instrumentation": https://arxiv.org/abs/2208.13907
Special thanks to Julian Mestre for creating this block coverage inference algorithm.
Binary size of `clang` using `-O2`:
* Base
* `.text`: 65.8 Mi
* Total: 119 Mi
* IRPGO (`-fprofile-generate -mllvm -disable-vp -mllvm -debug-info-correlate`)
* `.text`: 93.0 Mi
* `__llvm_prf_cnts`: 14.5 Mi
* Total: 175 Mi
* Minimal Block Coverage (`-fprofile-generate -mllvm -disable-vp -mllvm -debug-info-correlate -mllvm -pgo-block-coverage`)
* `.text`: 82.1 Mi
* `__llvm_prf_cnts`: 1.38 Mi
* Total: 139 Mi
Reviewed By: spupyrev, kyulee
Differential Revision: https://reviews.llvm.org/D124490
`instrprof` currently does not set `__llvm_prf_vnds`'s alignment after creating it. The consequence is that the alignment is set to 16 later (c0f3ac1d00/llvm/lib/IR/DataLayout.cpp (L1019)). This can lead to undefined behaviour when we calculate `NumVNodes` in `lprofGetLoadModuleSignature` (c0f3ac1d00/compiler-rt/lib/profile/InstrProfilingMerge.c (L32)). The reason is that when the `__llvm_prf_vnds` array is 16 byte aligned, `__llvm_profile_end_vnodes() - __llvm_profile_begin_vnodes()` may not be a multiple of the size of ValueProfNode (which is 24, 20 on 32 bit targets).
This patch sets `__llvm_prf_vnds`'s alignment to its ABI alignment, which always divides its size. Then `__llvm_profile_end_vnodes() - __llvm_profile_begin_vnodes()` will be a multiple of `sizeof(ValueProfNode)`.
Reviewed By: w2yehia, MaskRay
Differential Revision: https://reviews.llvm.org/D144302
In many cases, we can use an alias to avoid a symbolic relocations,
instead of using the public, interposable symbol. When the instrumented
function is in a COMDAT, we can use a hidden alias, and still avoid
references to discarded sections.
Previous versions of this patch allowed the compiler to name the
generated alias, but that would only be valid when the functions were
local. Since the alias may be used across TUs we use a more
deterministic naming convention, and add a ".local" suffix to the alias
name just as we do for relative vtables aliases.
https://reviews.llvm.org/rG20894a478da224bdd69c91a22a5175b28bc08ed9
removed an incorrect assertion on Mach-O which caused assertion failures in LLD.
We prevent duplicate symbols under ThinLTO + PGO + CFI by disabling
alias generation when the target function has MD_type metadata used in
CFI.
Reviewed By: phosek
Differential Revision: https://reviews.llvm.org/D137982
