I really needed this, like, factually, yesterday,
when verifying dependency breaking idioms for AMD Zen 3 scheduler model.
Consider the following example:
```
$ ./bin/llvm-exegesis --mode=inverse_throughput --snippets-file=/tmp/snippet.s --num-repetitions=1000000 --repetition-mode=duplicate
Check generated assembly with: /usr/bin/objdump -d /tmp/snippet-4a7e50.o
---
mode: inverse_throughput
key:
instructions:
- 'VPXORYrr YMM0 YMM0 YMM0'
config: ''
register_initial_values: []
cpu_name: znver3
llvm_triple: x86_64-unknown-linux-gnu
num_repetitions: 1000000
measurements:
- { key: inverse_throughput, value: 0.31025, per_snippet_value: 0.31025 }
error: ''
info: ''
assembled_snippet: C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C5FDEFC0C3
...
```
What does it tell us?
So wait, it can only execute ~3 x86 AVX YMM PXOR zero-idioms per cycle?
That doesn't seem right. That's even less than there are pipes supporting this type of op.
Now, second example:
```
$ ./bin/llvm-exegesis --mode=inverse_throughput --snippets-file=/tmp/snippet.s --num-repetitions=1000000 --repetition-mode=loop
Check generated assembly with: /usr/bin/objdump -d /tmp/snippet-2418b5.o
---
mode: inverse_throughput
key:
instructions:
- 'VPXORYrr YMM0 YMM0 YMM0'
config: ''
register_initial_values: []
cpu_name: znver3
llvm_triple: x86_64-unknown-linux-gnu
num_repetitions: 1000000
measurements:
- { key: inverse_throughput, value: 1.00011, per_snippet_value: 1.00011 }
error: ''
info: ''
assembled_snippet: 49B80800000000000000C5FDEFC0C5FDEFC04983C0FF75F2C3
...
```
Now that's just worse. Due to the looping, the throughput completely plummeted,
and now we can only do a single instruction/cycle!?
That's not great.
And final example:
```
$ ./bin/llvm-exegesis --mode=inverse_throughput --snippets-file=/tmp/snippet.s --num-repetitions=1000000 --repetition-mode=loop --loop-body-size=1000
Check generated assembly with: /usr/bin/objdump -d /tmp/snippet-c402e2.o
---
mode: inverse_throughput
key:
instructions:
- 'VPXORYrr YMM0 YMM0 YMM0'
config: ''
register_initial_values: []
cpu_name: znver3
llvm_triple: x86_64-unknown-linux-gnu
num_repetitions: 1000000
measurements:
- { key: inverse_throughput, value: 0.167087, per_snippet_value: 0.167087 }
error: ''
info: ''
assembled_snippet: 49B80800000000000000C5FDEFC0C5FDEFC04983C0FF75F2C3
...
```
So if we merge the previous two approaches, do duplicate this single-instruction snippet 1000x
(loop-body-size/instruction count in snippet), and run a loop with 1000 iterations
over that duplicated/unrolled snippet, the measured throughput goes through the roof,
up to 5.9 instructions/cycle, which finally tells us that this idiom is zero-cycle!
Reviewed By: courbet
Differential Revision: https://reviews.llvm.org/D102522
In many cases it is helpful to know at what address the resolved function starts.
This patch adds a new StartAddress member to the DILineInfo structure.
Reviewed By: jhenderson, dblaikie
Differential Revision: https://reviews.llvm.org/D102316
This patch adds JSON output style to llvm-symbolizer to better support CLI automation by providing a machine readable output.
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D96883
The option --use-symbol-table is now a noop and does not appear in the
help text, however it still appears in the command guide. This change
removes it from the command guide and updates the description of
--output-style .
Differential Revision: https://reviews.llvm.org/D102078
The internal `cl::opt` option --x86-asm-syntax sets the AsmParser and AsmWriter
dialect. The option is used by llc and llvm-mc tests to set the AsmWriter dialect.
This patch adds -M {att,intel} as GNU objdump compatible aliases (PR43413).
Note: the dialect is initialized when the MCAsmInfo is constructed.
`MCInstPrinter::applyTargetSpecificCLOption` is called too late and its MCAsmInfo
reference is const, so changing the `cl::opt` in
`MCInstPrinter::applyTargetSpecificCLOption` is not an option, at least without
large amount of refactoring.
Reviewed By: hoy, jhenderson, thakis
Differential Revision: https://reviews.llvm.org/D101695
The llvm-objdump command guide has the option --cfg which was removed
from the tool by 888320e9fa5eb33194c066f68d50f1e73c5fff5e in 2014. This
change updates the command guide to reflect this.
Differential Revision: https://reviews.llvm.org/D101648
Add a flag to change dsymutil's behavior and force a static variable to
keep its enclosing function. The test shows a situation where that could
be useful. I'm not convinced this behavior makes sense as a default,
which is why it's behind a flag.
rdar://74918374
Differential revision: https://reviews.llvm.org/D101337
This implements an LLVM tool that's flag- and output-compatible
with macOS's `otool` -- except for bugs, but from testing with both
`otool` and `xcrun otool-classic`, llvm-otool matches vanilla
otool's behavior very well already. It's not 100% perfect, but
it's a very solid start.
This uses the same approach as llvm-objcopy: llvm-objdump uses
a different OptTable when it's invoked as llvm-otool. This
is possible thanks to D100433.
Differential Revision: https://reviews.llvm.org/D100583
RVV intrinsics has new overloading rule, please see
82aac7dad4
Changed:
1. Rename `generic` to `overloaded` because the new rule is not using C11 generic.
2. Change HasGeneric to HasNoMaskedOverloaded because all masked operations
support overloading api.
3. Add more overloaded tests due to overloading rule changed.
Differential Revision: https://reviews.llvm.org/D99189
The option `--prefix-strip` is only used when `--prefix` is not empty.
It removes N initial directories from absolute paths before adding the
prefix.
This matches GNU's objdump behavior.
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D96679
This is a follow-up for:
D98604 [MCA] Ensure that writes occur in-order
When instructions are aligned by the order of writes, they retire
in-order naturally. There is no need for an RCU, so it is disabled.
Differential Revision: https://reviews.llvm.org/D98628
Lit as it exists today has three hacks that allow users to run tests earlier:
1) An entire test suite can set the `is_early` boolean.
2) A very recently introduced "early_tests" feature.
3) The `--incremental` flag forces failing tests to run first.
All of these approaches have problems.
1) The `is_early` feature was until very recently undocumented. Nevertheless it still lacks testing and is a imprecise way of optimizing test starting times.
2) The `early_tests` feature requires manual updates and doesn't scale.
3) `--incremental` is undocumented, untested, and it requires modifying the *source* file system by "touching" the file. This "touch" based approach is arguably a hack because it confuses editors (because it looks like the test was modified behind the back of the editor) and "touching" the test source file doesn't work if the test suite is read only from the perspective of `lit` (via advanced filesystem/build tricks).
This patch attempts to simplify and address all of the above problems.
This patch formalizes, documents, tests, and defaults lit to recording the execution time of tests and then reordering all tests during the next execution. By reordering the tests, high core count machines run faster, sometimes significantly so.
This patch also always runs failing tests first, which is a positive user experience win for those that didn't know about the hidden `--incremental` flag.
Finally, if users want, they can _optionally_ commit the test timing data (or a subset thereof) back to the repository to accelerate bots and first-time runs of the test suite.
Reviewed By: jhenderson, yln
Differential Revision: https://reviews.llvm.org/D98179
Add printf-style alternate form flag to prefix hex number with 0x when
present. This works on both empty numeric expression (e.g. variable
definition from input) and when matching a numeric expression. The
syntax is as follows:
[[#%#<precision specifier><format specifier>, ...]
where <precision specifier> and <format specifier> are optional and ...
can be a variable definition or not with an empty expression or not.
This feature was requested in https://reviews.llvm.org/D81144#2075532
for llvm/test/MC/ELF/gen-dwarf64.s
Reviewed By: jdenny
Differential Revision: https://reviews.llvm.org/D97845
Demonstrate how to generate vadd/vfadd intrinsic functions
1. add -gen-riscv-vector-builtins for clang builtins.
2. add -gen-riscv-vector-builtin-codegen for clang codegen.
3. add -gen-riscv-vector-header for riscv_vector.h. It also generates
ifdef directives with extension checking, base on D94403.
4. add -gen-riscv-vector-generic-header for riscv_vector_generic.h.
Generate overloading version Header for generic api.
https://github.com/riscv/rvv-intrinsic-doc/blob/master/rvv-intrinsic-rfc.md#c11-generic-interface
5. update tblgen doc for riscv related options.
riscv_vector.td also defines some unused type transformers for vadd,
because I think it could demonstrate how tranfer type work and we need
them for the whole intrinsic functions implementation in the future.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Reviewed By: jrtc27, craig.topper, HsiangKai, Jim, Paul-C-Anagnostopoulos
Differential Revision: https://reviews.llvm.org/D95016
This diff introduces --keep-undefined in llvm-objcopy/llvm-strip for Mach-O
which makes the tools preserve undefined symbols.
Test plan: make check-all
Differential revision: https://reviews.llvm.org/D97040
This patch adds a pipeline to support in-order CPUs such as ARM
Cortex-A55.
In-order pipeline implements a simplified version of Dispatch,
Scheduler and Execute stages as a single stage. Entry and Retire
stages are common for both in-order and out-of-order pipelines.
Differential Revision: https://reviews.llvm.org/D94928
The help text and documentation for the --discard-all option failed to
mention that the option also causes the removal of debug sections. This
change fixes both for both llvm-objcopy and llvm-strip.
Reviewed by: MaskRay
Differential Revision: https://reviews.llvm.org/D97662
For some build configurations, `check-all` calls lit multiple times to
run multiple lit test suites. Most recently, I've found this to be
true when configuring openmp as part of `LLVM_ENABLE_RUNTIMES`, but
this is not the first time.
If one test suite fails, none of the remaining test suites run, so you
cannot determine if your patch has broken them. It can then be
frustrating to try to determine which `check-` targets will run the
remaining tests without getting stuck on the failing tests.
When such cases arise, it is probably best to adjust the cmake
configuration for `check-all` to run all test suites as part of one
lit invocation. Because that fix will likely not be implemented and
land immediately, this patch introduces `--ignore-fail` to serve as a
workaround for developers trying to see test results until it does
land:
```
$ LIT_OPTS=--ignore-fail ninja check-all
```
One problem with `--ignore-fail` is that it makes it challenging to
detect test failures in a script, perhaps in CI. This problem should
serve as motivation to actually fix the cmake configuration instead of
continuing to use `--ignore-fail` indefinitely.
Reviewed By: jhenderson, thopre
Differential Revision: https://reviews.llvm.org/D96371
In semi-automated environments, XFAILing or filtering out known regressions without actually committing changes or temporarily modifying the test suite can be quite useful.
Reviewed By: yln
Differential Revision: https://reviews.llvm.org/D96662
With enough cores, the slowest tests can significantly change the total testing time if they happen to run late. With this change, a test suite can improve performance (for high-end systems) by listing just a few of the slowest tests up front.
Reviewed By: jdenny, jhenderson
Differential Revision: https://reviews.llvm.org/D96594
Some test systems do not use lit for test discovery but only for its
substitution and test selection because they use another way of managing
test collections, e.g. CTest. This forces those tests to be invoked with
lit --no-indirectly-run-check. When a mix of lit version is in use, it
requires to detect the availability of that option.
This commit provides a new config option standalone_tests to signal a
directory made of tests meant to run as standalone. When this option is
set, lit skips test discovery and the indirectly run check. It also adds
the missing documentation for --no-indirectly-run-check.
Reviewed By: jdenny
Differential Revision: https://reviews.llvm.org/D94766
1. Emit warnings for files without symbols.
2. Add -no_warning_for_no_symbols.
Test plan: make check-all
Differential revision: https://reviews.llvm.org/D95843
The few options are niche. They solved a problem which was traditionally solved
with more shell commands (`llvm-readelf -n` fetches the Build ID. Then
`ln` is used to hard link the file to a directory derived from the Build ID.)
Due to limitation, they are no longer used by Fuchsia and they don't appear to
be used elsewhere (checked with Google Search and Debian Code Search). So delete
them without a transition period.
Announcement: https://lists.llvm.org/pipermail/llvm-dev/2021-February/148446.html
Differential Revision: https://reviews.llvm.org/D96310
This puts it in alphabetical order, matching the rest of the list.
Reviewed by: MaskRay, saugustine
Differential Revision: https://reviews.llvm.org/D94481
This is an enhancement to LLVM Source-Based Code Coverage in clang to track how
many times individual branch-generating conditions are taken (evaluate to TRUE)
and not taken (evaluate to FALSE). Individual conditions may comprise larger
boolean expressions using boolean logical operators. This functionality is
very similar to what is supported by GCOV except that it is very closely
anchored to the ASTs.
Differential Revision: https://reviews.llvm.org/D84467
Introduce CHECK modifiers that change the behavior of the CHECK
directive. Also add a LITERAL modifier for cases where matching could
end requiring escaping strings interpreted as regex where only
literal/fixed string matching is desired (making the CHECK's more
difficult to write/fragile and difficult to interpret).
This stack of changes introduces `llvm-profgen` utility which generates a profile data file from given perf script data files for sample-based PGO. It’s part of(not only) the CSSPGO work. Specifically to support context-sensitive with/without pseudo probe profile, it implements a series of functionalities including perf trace parsing, instruction symbolization, LBR stack/call frame stack unwinding, pseudo probe decoding, etc. Also high throughput is achieved by multiple levels of sample aggregation and compatible format with one stop is generated at the end. Please refer to: https://groups.google.com/g/llvm-dev/c/1p1rdYbL93s for the CSSPGO RFC.
This change supports context-sensitive profile data generation into llvm-profgen. With simultaneous sampling for LBR and call stack, we can identify leaf of LBR sample with calling context from stack sample . During the process of deriving fall through path from LBR entries, we unwind LBR by replaying all the calls and returns (including implicit calls/returns due to inlining) backwards on top of the sampled call stack. Then the state of call stack as we unwind through LBR always represents the calling context of current fall through path.
we have two types of virtual unwinding 1) LBR unwinding and 2) linear range unwinding.
Specifically, for each LBR entry which can be classified into call, return, regular branch, LBR unwinding will replay the operation by pushing, popping or switching leaf frame towards the call stack and since the initial call stack is most recently sampled, the replay should be in anti-execution order, i.e. for the regular case, pop the call stack when LBR is call, push frame on call stack when LBR is return. After each LBR processed, it also needs to align with the next LBR by going through instructions from previous LBR's target to current LBR's source, which we named linear unwinding. As instruction from linear range can come from different function by inlining, linear unwinding will do the range splitting and record counters through the range with same inline context.
With each fall through path from LBR unwinding, we aggregate each sample into counters by the calling context and eventually generate full context sensitive profile (without relying on inlining) to driver compiler's PGO/FDO.
A breakdown of noteworthy changes:
- Added `HybridSample` class as the abstraction perf sample including LBR stack and call stack
* Extended `PerfReader` to implement auto-detect whether input perf script output contains CS profile, then do the parsing. Multiple `HybridSample` are extracted
* Speed up by aggregating `HybridSample` into `AggregatedSamples`
* Added VirtualUnwinder that consumes aggregated `HybridSample` and implements unwinding of calls, returns, and linear path that contains implicit call/return from inlining. Ranges and branches counters are aggregated by the calling context. Here calling context is string type, each context is a pair of function name and callsite location info, the whole context is like `main:1 @ foo:2 @ bar`.
* Added PorfileGenerater that accumulates counters by ranges unfolding or branch target mapping, then generates context-sensitive function profile including function body, inferring callee's head sample, callsite target samples, eventually records into ProfileMap.
* Leveraged LLVM build-in(`SampleProfWriter`) writer to support different serialization format with no stop
- `getCanonicalFnName` for callee name and name from ELF section
- Added regression test for both unwinding and profile generation
Test Plan:
ninja & ninja check-llvm
Reviewed By: hoy, wenlei, wmi
Differential Revision: https://reviews.llvm.org/D89723
This does the same as `--mcpu=help` but was only
documented in the user guide.
* Added a test for both options.
* Corrected the single dash in `-mcpu=help` text.
Reviewed By: jhenderson
Differential Revision: https://reviews.llvm.org/D92305
llvm-symbolizer used to use the DIA SDK for symbolization on
Windows; this patch switches to using native symbolization, which was
implemented recently.
Users can still make the symbolizer use DIA by adding the `-dia` flag
in the LLVM_SYMBOLIZER_OPTS environment variable.
Differential Revision: https://reviews.llvm.org/D91814
This stack of changes introduces `llvm-profgen` utility which generates a profile data file from given perf script data files for sample-based PGO. It’s part of(not only) the CSSPGO work. Specifically to support context-sensitive with/without pseudo probe profile, it implements a series of functionalities including perf trace parsing, instruction symbolization, LBR stack/call frame stack unwinding, pseudo probe decoding, etc. Also high throughput is achieved by multiple levels of sample aggregation and compatible format with one stop is generated at the end. Please refer to: https://groups.google.com/g/llvm-dev/c/1p1rdYbL93s for the CSSPGO RFC.
This change enables disassembling the text sections to build various address maps that are potentially used by the virtual unwinder. A switch `--show-disassembly` is being added to print the disassembly code.
Like the llvm-objdump tool, this change leverages existing LLVM components to parse and disassemble ELF binary files. So far X86 is supported.
Test Plan:
ninja check-llvm
Reviewed By: wmi, wenlei
Differential Revision: https://reviews.llvm.org/D89712
