Jordan Jacobelli
92286e1d4a
devcontainer: replace VAULT_HOST with AWS_ROLE_ARN ( #187 )
...
* devcontainer: replace VAULT_HOST with AWS_ROLE_ARN
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
* Update devcontainers base image to support AWS_ROLE_ARN
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
* Bump cuda latest version to 12.6
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
* Replace ubuntu18.04 with ubuntu20.04
Ubuntu 18.04 is not supported anymore
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
* Use DOOD stategy to keep supporting ubuntu18.04
See https://github.com/NVIDIA/cccl/pull/1779
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
---------
Signed-off-by: Jordan Jacobelli <jjacobelli@nvidia.com >
2024-10-25 11:49:02 -04:00
Sergey Pavlov
a171514056
Added cudaGetLastError() calls to reset benchmarking kernel errors (issue 88). ( #173 )
...
* Create and use NVBENCH_CUDA_CALL_RESET_ERROR.
* Moved cudaGetLastError() call to NVBENCH_CUDA_CALL macro
---------
Co-authored-by: Sergey Pavlov <psvvsp89@gmail.com >
2024-05-31 11:32:01 -04:00
Cliff Burdick
088c9ee658
Removed extraneous break statements that caused nvc++ to give warnings ( #171 )
2024-05-17 16:35:11 -04:00
Allison Piper
961fa91258
Don't fail CI when ninja_summary fails. ( #172 )
2024-05-17 14:35:12 -04:00
Allison Piper
555d628e9b
Use a reproducible seed in test rng. ( #164 )
2024-04-12 11:55:05 -04:00
Allison Piper
60761e0946
Enable extra NVBench features in windows build. ( #169 )
...
* Enable extra NVBench features in windows build.
These were delayed as they required changes to the devcontainers.
* Revamp nvml.dll logic.
2024-04-10 13:45:53 -04:00
Allison Piper
5ee8811a1a
Fix and test using RAII global state in main. ( #168 )
2024-04-09 17:27:49 -04:00
Allison Piper
165cf924c5
Refactor main implementation to improve reusability and customization. ( #165 )
...
* Refactor main implementation to improve reusability and customization.
Move the implementation of `main` out of macros and into separate
functions. This allows for easier reuse and customization of the macros.
Existing macro usage should still work as expected, and new
customization points will simplify common tasks like argument parsing
going forward.
* Add tests that validate common main customizations.
2024-04-09 12:45:58 -04:00
Allison Piper
9e8efa2c88
Preserve .devcontainers/img/ when cleaning. ( #166 )
2024-04-08 18:24:07 -04:00
Allison Piper
044e22411e
Move CUPTI disablement to build script. ( #167 )
2024-04-08 18:23:38 -04:00
Allison Piper
a0f2fab72b
Squashed commit of the following:
...
commit c5b2fc0a8balliepiper16@gmail.com >
Date: Sat Apr 6 21:48:20 2024 +0000
Add supported compilers and tools in README.md.
commit 92fe366da5alliepiper16@gmail.com >
Date: Sat Apr 6 20:45:30 2024 +0000
Fix issues discovered by header tests.
commit f7f6c92143alliepiper16@gmail.com >
Date: Sat Apr 6 20:45:06 2024 +0000
Setup header tests, add C++20 header tests + examples.
The core library will always be built with C++17, but
we test our headers / examples under 17 and 20.
commit 4b24f26b66alliepiper16@gmail.com >
Date: Sat Apr 6 16:21:42 2024 +0000
Pass CUDA FLAGS to install tests.
commit 4fb672ae91alliepiper16@gmail.com >
Date: Sat Apr 6 15:43:41 2024 +0000
Add newer GCC (13) and Clang (17, 18).
2024-04-06 22:05:40 +00:00
Allison Piper
a2f88ff790
Set CUDA_MODULE_LOADING=EAGER before main. ( #157 )
...
* Set `CUDA_MODULE_LOADING=EAGER` before `main`.
Fixes #136
* Portability for `setenv`.
* Remove pre-main CUDART usage and setup env in main.
* Fail examples if they deadlock.
This is the best way we have to diagnose a regression for
NVIDIA/nvbench#136 .
* Add an initialize method to benchmark_manager for CUDA-related setup.
Benchmarks are created statically, so their constructors cannot call the CUDA APIs without breaking the CUDA_MODULE_LOAD setup.
This method is called from `main` after the environment has been configured.
2024-04-06 11:03:42 -04:00
Allison Piper
e8c8877d36
Squashed commit of the following:
...
commit 4b309e6ad8alliepiper16@gmail.com >
Date: Sat Apr 6 13:19:14 2024 +0000
Minor cleanups
commit 476ed2ceaealliepiper16@gmail.com >
Date: Sat Apr 6 12:53:37 2024 +0000
WAR compiler ice in nlohmann json.
Only seeing this on GCC 9 + CTK 11.1. Seems to be
having trouble with the `[[no_unique_address]]` optimization.
commit a9bf1d3e42alliepiper16@gmail.com >
Date: Sat Apr 6 00:24:47 2024 +0000
Bump nlohmann json.
commit 80980fe373alliepiper16@gmail.com >
Date: Sat Apr 6 00:22:07 2024 +0000
Fix llvm filesystem support
commit f6099e6311alliepiper16@gmail.com >
Date: Fri Apr 5 23:18:44 2024 +0000
Drop MSVC 2017 testing.
commit 5ae50a8ef5alliepiper16@gmail.com >
Date: Fri Apr 5 23:02:32 2024 +0000
Add mroe missing headers.
commit b2a9ae04d9alliepiper16@gmail.com >
Date: Fri Apr 5 22:37:56 2024 +0000
Remove old CUDA+MSVC builds and make windows build-only.
commit 5b18c26a28alliepiper16@gmail.com >
Date: Fri Apr 5 22:37:07 2024 +0000
Fix header for std::min/max.
Why do I always think it's utility instead of algorithm....
commit 6a409efa2dalliepiper16@gmail.com >
Date: Fri Apr 5 22:18:18 2024 +0000
Temporarily disable CUPTI on all windows builds.
commit f432f88866alliepiper16@gmail.com >
Date: Fri Apr 5 21:42:52 2024 +0000
Fix warnings on MSVC.
commit 829787649balliepiper16@gmail.com >
Date: Fri Apr 5 21:03:16 2024 +0000
More flailing about in powershell.
commit 21742e6beaalliepiper16@gmail.com >
Date: Fri Apr 5 20:36:08 2024 +0000
Cleanup filesystem header handling.
commit de3d202635alliepiper16@gmail.com >
Date: Fri Apr 5 20:09:00 2024 +0000
Windows CI debugging.
commit a4151667ffalliepiper16@gmail.com >
Date: Fri Apr 5 19:45:40 2024 +0000
Quotation mark madness
commit dd04f3befealliepiper16@gmail.com >
Date: Fri Apr 5 19:27:27 2024 +0000
Temporarily disable NVML on windows CI until new containers are ready.
commit f3952848c4alliepiper16@gmail.com >
Date: Fri Apr 5 19:25:22 2024 +0000
WAR issues on gcc-7.
commit 198986875ealliepiper16@gmail.com >
Date: Fri Apr 5 19:25:04 2024 +0000
More matrix/devcontainer updates.
commit b9712f8696alliepiper16@gmail.com >
Date: Fri Apr 5 18:30:35 2024 +0000
Fix windows build scripts.
commit 943f268280alliepiper16@gmail.com >
Date: Fri Apr 5 18:18:33 2024 +0000
Fix warnings with clang host compiler.
commit 7063e1d60aalliepiper16@gmail.com >
Date: Fri Apr 5 18:14:28 2024 +0000
More devcontainer hijinks.
commit 06532fde81alliepiper16@gmail.com >
Date: Fri Apr 5 17:51:25 2024 +0000
More matrix updates.
commit 78a265ea55alliepiper16@gmail.com >
Date: Fri Apr 5 17:34:00 2024 +0000
Support CLI CMake options for windows ci scripts.
commit 670895c867alliepiper16@gmail.com >
Date: Fri Apr 5 17:31:59 2024 +0000
Add missing devcontainers.
commit b121823e74alliepiper16@gmail.com >
Date: Fri Apr 5 17:22:54 2024 +0000
Build for `all-major` architectures in presets.
We can get away with this because we require CMake 3.23.1.
This was added in 3.23.
commit fccfd44685alliepiper16@gmail.com >
Date: Fri Apr 5 17:22:08 2024 +0000
Update matrix file.
commit e7d43ba90ealliepiper16@gmail.com >
Date: Fri Apr 5 16:23:48 2024 +0000
Consolidate build/test jobs.
commit c4044056ecalliepiper16@gmail.com >
Date: Fri Apr 5 16:04:11 2024 +0000
Add missing build script.
2024-04-06 13:56:10 +00:00
Allison Piper
04b70059b8
Setup clangd compile commands output.
2024-04-05 15:08:04 +00:00
Allison Piper
eb5940c64f
Add initial CI, presets, and devcontainers.
2024-04-04 21:42:43 +00:00
Georgii Evtushenko
42d99a5753
Fix MSVC ( #158 )
...
* Fix MSVC
* Revert change of source list name
2024-04-04 09:53:30 -07:00
Georgii Evtushenko
d8dced8a64
Merge pull request #151 from gevtushenko/entropy
...
Entropy-based stopping criterion
2024-01-12 23:19:25 +04:00
Georgy Evtushenko
aebbeb371b
Check if criterion options start with --
2024-01-11 11:24:59 -08:00
Georgy Evtushenko
4be0c5bdcd
API convention
2024-01-11 10:48:52 -08:00
Georgy Evtushenko
34c57965a2
Move params
2024-01-11 10:42:43 -08:00
Georgy Evtushenko
dacbee127c
Base method naming convention
2024-01-11 10:41:11 -08:00
Georgy Evtushenko
182c77e4f4
Got rid of the params description API
2024-01-10 12:30:17 -08:00
Georgy Evtushenko
bcd5c7d885
Remove extra member variable
2024-01-10 10:15:00 -08:00
Georgy Evtushenko
b59c251e3b
Making stopping criterion constructor explicit
2024-01-10 10:13:03 -08:00
Georgy Evtushenko
6b5315fc8f
Readable names
2024-01-10 10:12:19 -08:00
Georgy Evtushenko
bd23bcac31
Const version of get criterion
2024-01-10 10:09:00 -08:00
Georgy Evtushenko
dd54af3dc5
Make get params description const
2024-01-10 10:01:49 -08:00
Georgy Evtushenko
42c6bdea70
Handle empty input in mean
2024-01-10 09:52:14 -08:00
Georgy Evtushenko
f5db89cc2b
Documented potential improvement
2024-01-09 15:01:08 -08:00
Georgy Evtushenko
d079a49976
Compute mean once
2024-01-09 14:57:29 -08:00
Georgy Evtushenko
2dd4c18e2f
Criterion registration macro
2024-01-08 14:20:17 -08:00
Georgy Evtushenko
fade52fa2e
Different singleton convention
2024-01-08 14:08:12 -08:00
Georgy Evtushenko
5b6378e918
Comment on reduction of computation in is_finished()
2024-01-08 13:21:26 -08:00
Georgy Evtushenko
85ed6f007c
Rename criterion registry to criterion manager
2024-01-08 13:15:46 -08:00
Georgy Evtushenko
4d90c367f5
Showcase specifying benchmark stopping criterion
2024-01-08 13:09:27 -08:00
Georgy Evtushenko
de724a21f1
Rename get_params to get_params_description
2024-01-08 13:06:48 -08:00
Georgy Evtushenko
88cc582cea
ABC
2024-01-08 13:03:33 -08:00
Georgy Evtushenko
b789240c76
Entropy-based stopping criterion
2024-01-05 14:59:48 -08:00
Allison Vacanti
7521229872
Merge pull request #138 from andmax/fix/am/do_clone_warnings
...
fix: add final mark in do_clone methods to avoid warnings
2023-11-20 11:10:38 -05:00
Andre Maximo
e7a4ce70dc
fix: add final mark in do_clone methods to avoid warnings
2023-11-20 06:58:02 -03:00
Robert Maynard
978d81a0cb
Restore nvml being an optional dependency of nvbench ( #149 )
2023-11-16 15:20:24 -05:00
Allison Vacanti
acc8239ef7
Merge pull request #148 from robertmaynard/support_nvml_with_static_builds
...
Support static builds of nvbench with nvml enabled.
2023-11-15 09:52:35 -05:00
Robert Maynard
cbe9980304
Correct typo in nvbench/internal/nvml.cuh
...
Co-authored-by: Bradley Dice <bdice@bradleydice.com >
2023-11-14 14:23:56 -05:00
Robert Maynard
adaef09b20
Support static builds of nvbench with nvml enabled.
...
To do this we need to ensure that the nvml init handler is
both contained in the library/executable that uses nvbench.
The original implementation fails since the singleton can be dropped
since it has no usages. So instead we move to a function static
which we ensure will always be used.
2023-11-14 14:08:10 -05:00
Georgii Evtushenko
57c4d42ba5
Merge pull request #146 from gevtushenko/trials
...
No batch tag
2023-11-02 22:11:37 +04:00
Georgy Evtushenko
2ef69e9ba6
No batch exec tag
2023-11-02 11:10:27 -07:00
Robert Maynard
b8f0f6b583
Rework nvbench_git_revision logic to correct cccl build failures ( #145 )
2023-10-20 14:11:17 -04:00
Robert Maynard
e47d7ac354
write_git_revision_file must be used in same CMakeLists as consumer ( #143 )
...
* write_git_revision_file must be used in same CMakeLists as consumer
So we can't have this in the rapids-cmake init function.
* Fix whitespace damage
---------
Co-authored-by: Michael Schellenberger Costa <miscco@nvidia.com >
2023-10-19 06:52:17 +02:00
Allison Vacanti
c3a8ef6e37
Merge pull request #141 from robertmaynard/fea/support_turning_off_install_rules
...
NVBench now supports not installing itself
2023-10-18 09:47:07 -04:00
Robert Maynard
07bc58bddf
Properly generate git revision header before usage ( #142 )
...
Wasn't found due to testing using CMake 3.27+
2023-10-18 15:46:04 +02:00
