As discussed in [0], add a `weight` field to temporal profiling traces found in profiles. This allows users to use the `--weighted-input=` flag in the `llvm-profdata merge` command to weight traces from different scenarios differently.
Note that this is a breaking change, but since [1] landed very recently and there is no way to "use" this trace data, there should be no users of this feature. We believe it is acceptable to land this change without bumping the profile format version.
[0] https://reviews.llvm.org/D147812#4259507
[1] https://reviews.llvm.org/D147287
Reviewed By: snehasish
Differential Revision: https://reviews.llvm.org/D148150
This patch adds in documentation for the --use-dummy-perf-counters
option (introduced in D146301).
Reviewed By: kpdev42
Differential Revision: https://reviews.llvm.org/D147842
D147710 introduced a new annotation-count subcommand to llvm-remarkutil
and added in documentation. However, the reference added under the
subcommands list never actually pointed to anything. This patch adds a
marker for the reference to point to so that the link works and the
sphinx build finishes without any errors.
This adds a `annotation-count` option to llvm-remarkutil.
```
llvm-remarkutil annotation-count -remark=REMARK
```
This will print out the remark count for a pass that uses annotation remarks.
Differential Revision: https://reviews.llvm.org/D147710
For profile staleness report, before it only counts for the top-level function samples in the nested profile, the samples in the inlinees are ignored. This could affect the quality of the metrics when there are heavily inlined functions. This change adds a feature to flatten the nested profile and we're changing to use flatten profile as the input for stale profile detection and matching.
Example for profile flattening:
```
Original profile:
_Z3bazi:20301:1000
1: 1000
3: 2000
5: inline1:1600
1: 600
3: inline2:500
1: 500
Flattened profile:
_Z3bazi:18701:1000
1: 1000
3: 2000
5: 600 inline1:600
inline1:1100:600
1: 600
3: 500 inline2: 500
inline2:500:500
1: 500
```
This feature could be useful for offline analysis, like understanding the hotness of each individual function. So I'm adding the support to `llvm-profdata merge` under `--gen-flattened-profile`.
Reviewed By: hoy, wenlei
Differential Revision: https://reviews.llvm.org/D146452
Currently, the llvm-exegesis documentation page has all
snippet annotation information under an example. This patch refactors
the annotation documentation to a separate section to make things more
clear and to make adding future annotations easier. This patch also
significantly expands the documentation on the memory scratch space to
which a pointer can be passed through a register as the documentation on
this was quite sparse previously.
Reviewed By: courbet
Differential Revision: https://reviews.llvm.org/D146890
Currently the filetype flag is not documented, and knowing the behavior
of this flag is fairly important for doing anything other than
disassembling to text assembly.
Reviewed By: lattner
Differential Revision: https://reviews.llvm.org/D146878
This adds the --check-binary-id flag that makes sure that an object file
is available for every binary ID mentioned in the given profile. This
should help make the tool more robust in CI environments where it's
expected that coverage mappings should be available for every object
contributing to the profile.
Reviewed By: gulfem
Differential Revision: https://reviews.llvm.org/D144308
This adds functionality to readelf/readobj to specifically handle
MTE-related bits, like the AARCH64_MEMTAG_* dynamic entries, and a
decoder for the Android-specific ELF note.
Reviewed By: jhenderson, MaskRay
Differential Revision: https://reviews.llvm.org/D143693
Since binary ID lookup makes CLI object arguments optional, it should be
possible to pass a list of source files without a binary. Unfortunately,
the current syntax will always interpret the first source file as a
binary. This change adds a `-sources` option to cause all later
positional arguments to be considered sources.
Reviewed By: gulfem
Differential Revision: https://reviews.llvm.org/D144207
While "skip measurements mode" is super useful for test coverage,
i've come to discover it's trade-offs. It still calls back-end
to actually codegen the target assembly, and that is what is taking
80%+ of the time regardless of whether or not we skip the measurements.
On the other hand, just being able to see that exegesis can come up
with a snippet to measure something, is already very useful,
and takes maybe a second for a all-opcode sweep.
Reviewed By: gchatelet
Differential Revision: https://reviews.llvm.org/D140702
By default, all benchmark results are analysed, but sometimes it may be useful
to only look at those that to not involve memory, or vice versa. This option
allows to either keep all benchmarks, or filter out (ignore) either all the
ones that do involve memory (involve instructions that may read or write to
memory), or the opposite, to only keep such benchmarks.
Personally, so far i have found the benchmarks that do involve memory
to have dubious results. But the ones that do not involve memory,
are generally actionable. So i would like to have a toggle to declutter results.
Reviewed By: courbet
Differential Revision: https://reviews.llvm.org/D140734
Noticed while trying to use llvm-exegesis to get some accurate capture numbers on some old Atom/Silverment hardware as part of the work with D103695.
These targets' frontends are particularly poor and the use of the xmm8-xmm15 SSE registers results in longer instruction encodings which were affecting the latency/throughput estimates.
Thanks to @lebedev.ri for the --skip-measurements command line argument which made testing much easier!
Differential Revision: https://reviews.llvm.org/D138832
Sometimes we only want to ensure that we can produce snippets (all the way
through `SnippetRepetitor`!), but don't care for the execution.
E.g. all of our tests are this way.
I've built LLVM without PFM and removed my CPU from `X86PfmCounters.td`,
and this produces the expected results in that configuration.
Reviewed By: courbet
Differential Revision: https://reviews.llvm.org/D139448
On x86 and AArch, SIMD instructions encode all of the scheduling information in the instruction
itself. For example, VADD.I16 q0, q1, q2 is a neon instruction that operates on 16-bit integer
elements stored in 128-bit Q registers, which leads to eight 16-bit lanes in parallel. This kind
of information impacts how the instruction takes to execute and what dependencies this may cause.
On RISCV however, the data that impacts scheduling is encoded in CSR registers such as vtype or
vl, in addition with the instruction itself. But MCA does not track or use the data in these
registers. This patch fixes this problem by introducing Instruments into MCA.
* Replace `CodeRegions` with `AnalysisRegions`
* Add `Instrument` and `InstrumentManager`
* Add `InstrumentRegions`
* Add RISCV Instrument and `InstrumentManager`
* Parse `Instruments` in driver
* Use instruments to override schedule class
* RISCV use lmul instrument to override schedule class
* Fix unit tests to pass empty instruments
* Add -ignore-im clopt to disable this change
A prior version of this patch was commited in 5e82ee537321. 2323a4ee610f reverted
that change because the unit test files caused build errors. The change with fixes
were committed in b88b8307bf9e but reverted once again e8e92c8313a0 due to more
build errors.
This commit adds the prior changes and fixes the build error.
Differential Revision: https://reviews.llvm.org/D137440
On x86 and AArch, SIMD instructions encode all of the scheduling information in the instruction
itself. For example, VADD.I16 q0, q1, q2 is a neon instruction that operates on 16-bit integer
elements stored in 128-bit Q registers, which leads to eight 16-bit lanes in parallel. This kind
of information impacts how the instruction takes to execute and what dependencies this may cause.
On RISCV however, the data that impacts scheduling is encoded in CSR registers such as vtype or
vl, in addition with the instruction itself. But MCA does not track or use the data in these
registers. This patch fixes this problem by introducing Instruments into MCA.
* Replace `CodeRegions` with `AnalysisRegions`
* Add `Instrument` and `InstrumentManager`
* Add `InstrumentRegions`
* Add RISCV Instrument and `InstrumentManager`
* Parse `Instruments` in driver
* Use instruments to override schedule class
* RISCV use lmul instrument to override schedule class
* Fix unit tests to pass empty instruments
* Add -ignore-im clopt to disable this change
A prior version of this patch was commited in. It was reverted in
5e82ee5373211db8522181054800ccd49461d9d8. 2323a4ee610f5e1db74d362af4c6fb8c704be8f6 reverted
that change because the unit test files caused build errors. This commit adds the original changes
and the fixed test files.
Differential Revision: https://reviews.llvm.org/D137440
On x86 and AArch, SIMD instructions encode all of the scheduling information in the instruction
itself. For example, VADD.I16 q0, q1, q2 is a neon instruction that operates on 16-bit integer
elements stored in 128-bit Q registers, which leads to eight 16-bit lanes in parallel. This kind
of information impacts how the instruction takes to execute and what dependencies this may cause.
On RISCV however, the data that impacts scheduling is encoded in CSR registers such as vtype or
vl, in addition with the instruction itself. But MCA does not track or use the data in these
registers. This patch fixes this problem by introducing Instruments into MCA.
* Replace `CodeRegions` with `AnalysisRegions`
* Add `Instrument` and `InstrumentManager`
* Add `InstrumentRegions`
* Add RISCV Instrument and `InstrumentManager`
* Parse `Instruments` in driver
* Use instruments to override schedule class
* RISCV use lmul instrument to override schedule class
* Fix unit tests to pass empty instruments
* Add -ignore-im clopt to disable this change
Differential Revision: https://reviews.llvm.org/D137440
Remove the `--src-root` option from the deprecated llvm-config tool.
None of the llvm-project projects use this option anymore. The value
was only meaningful for in-tree use and usually became no longer correct
once LLVM was installed -- either because it was built in a temporary
directory, or installed from a binary package and built on a different
system entirely. Therefore, third-party tools could not have been
relying on it anyway.
The LLVM_SRC_ROOT #define is left intact, as it is used to compute
includedir when llvm-config is used in-source.
Differential Revision: https://reviews.llvm.org/D137144
This was previously attempted in 2016 by colinl's D18770, but LLD tests
were missed, which caused the change to be reverted.
Setting --print-imm-hex by default brings llvm-objdump's behavior closer
in line with objdump, and it makes it easier to read addresses and
alignment from the disassembly. It may make non-address immediates
harder to interpret, but it still seems the better default, barring more
context-sensitive base selection logic.
Differential Revision: https://reviews.llvm.org/D136972
llvm-debuginfo-analyzer is a command line tool that processes debug
info contained in a binary file and produces a debug information
format agnostic “Logical View”, which is a high-level semantic
representation of the debug info, independent of the low-level
format.
The code has been divided into the following patches:
1) Interval tree
2) Driver and documentation
3) Logical elements
4) Locations and ranges
5) Select elements
6) Warning and internal options
7) Compare elements
8) ELF Reader
9) CodeView Reader
Full details:
https://discourse.llvm.org/t/llvm-dev-rfc-llvm-dva-debug-information-visual-analyzer/62570
This patch:
Driver and documentation
- Command line options.
- Full documentation.
- String Pool table.
Reviewed By: psamolysov, probinson
Differential Revision: https://reviews.llvm.org/D125777
This updates the `--function-starts` argument to now accept 3 different
modes, `addrs` for just printing the addresses of the function starts
(previous behavior), `names` for just printing the names of the function
starts, and `both` to print them both side by side.
In general if you're debugging function starts issues it's useful to see
the symbol name alongside the address. This also mirrors Apple's
`dyldinfo -function_starts` command which prints both.
Differential Revision: https://reviews.llvm.org/D119050
In https://reviews.llvm.org/D135127 we created the show flag
`--output-format` which was confusing because it behaved differently
than the same flag in the merge command. So, rename the flag to
`--show-format`. This also allows us to add the `text` option to mean
"normal text output" rather than "text-encoded profiles" like it does
for the merge command.
Reviewed By: wenlei
Differential Revision: https://reviews.llvm.org/D135467
Add `--output-format` option for the `llvm-profdata show` command to select the type of output. The existing `--text` flag is used to emit text encoded profiles. To avoid confusion, `--output-format=text-encoding` indicates that the output will be profiles encoded in the text format, and `--output-format=text` indicates the default text output that doesn't necessarily represent a profile.
`--output-format=json` is an alias for `--json` and `--output-format=yaml` will be used in D134770.
Reviewed By: phosek
Differential Revision: https://reviews.llvm.org/D135127
I forgot to add documentation for these options when I added them to the `show` command, so add them now.
Reviewed By: phosek
Differential Revision: https://reviews.llvm.org/D135383
