Commit Graph

545 Commits

Author SHA1 Message Date
Allison Vacanti
083fdc2fc1 Merge pull request #133 from robertmaynard/bug/handle_conda_env_static_fmt
Handle use case where we are in a conda env but with a static fmt lib
2023-05-31 13:56:56 -04:00
Robert Maynard
b8b5d2904b Handle use case where we are in a conda env but with a static fmt lib 2023-05-31 10:51:40 -04:00
Allison Vacanti
702ab05751 Merge pull request #127 from robertmaynard/use_public_fmt_in_conda
Propagate fmt requirement in conda envs
2023-05-16 12:20:57 -04:00
Georgy Evtushenko
263f9eca98 Merge pull request #131 from senior-zero/enh-main/github/json-device-list
Add list-devices option
2023-04-13 23:04:59 +04:00
Georgy Evtushenko
5785d002e5 Add jsonlist-devices option 2023-04-13 23:04:05 +04:00
Georgy Evtushenko
9d6a60ef82 Merge pull request #130 from senior-zero/enh-main/github/json-list
Introduce machine-readable version of --list
2023-04-10 19:59:25 +04:00
Georgy Evtushenko
12a164f763 Introduce jsonlist 2023-04-10 15:45:12 +04:00
Georgy Evtushenko
fe6f7da36a Throw on unsupported behavior 2023-04-10 15:02:26 +04:00
Georgy Evtushenko
794557acbd List should print only axis lists 2023-04-10 14:55:40 +04:00
Georgy Evtushenko
51a9342b8a Fix examples 2023-04-10 14:53:32 +04:00
Robert Maynard
16c9b0210f Propagate fmt requirement in conda envs
When we are inside a conda env the linker will be set to
`ld.bfd` which will try to resolve all undefined symbols at time.

Since we could be using a shared library version of fmt we need
it on the final link line of consumers
2023-02-17 14:34:34 -05:00
Allison Vacanti
e477bb3862 Merge pull request #108 from aaronmondal/fix-clang-filesystem
Fix filesystem detection for clang
2023-02-01 11:19:16 -05:00
Aaron Siddhartha Mondal
4d25de1377 Remove empty line 2023-02-01 14:20:48 +01:00
Aaron Siddhartha Mondal
05743e5e61 Restore previous include order 2023-02-01 14:18:12 +01:00
Allison Vacanti
9dfe96526c Merge pull request #116 from senior-zero/fix-histogram
Adopt histogram script to new format
2023-01-30 11:48:08 -05:00
Allison Vacanti
f2c47c3854 Merge pull request #114 from robertmaynard/update_to_fmt_9.1
Update nvbench default fmt to be built to be 9.1.0
2023-01-04 10:05:02 -05:00
Georgy Evtushenko
1eb0c49222 Adopt histogram script to new format 2022-12-22 17:12:22 +04:00
Robert Maynard
b8739b6fe6 Update nvbench default fmt to be built to be 9.1.0
The formatting of `{}` can be incorrect under 7.X when given
doubles and compiled with the latest conda toolchain. While both
fmt 8 and 9 don't show this issue move to the latest version
to leverage all the improvements in fmt 9.

Fixes #103
2022-12-16 15:04:49 -05:00
Aaron Siddhartha Mondal
d2f47110dc Fix filesystem detection for clang
Clang defines __GNUC__ but does not use experimental/filesystem.
2022-11-24 10:22:31 +01:00
Jake Hemstad
1cce3988e2 Merge pull request #102 from vyasr/feature/fmt_9
fmt::memory_buffer is no longer an iterator.
2022-11-08 13:47:37 -06:00
Vyas Ramasubramani
a5ffad1e8d Downgrade fmt version again. 2022-11-08 11:13:45 -08:00
Vyas Ramasubramani
06c3cd26e1 Query the underlying type. 2022-11-04 10:05:40 -07:00
Vyas Ramasubramani
ae6ede15d6 Fix warning. 2022-11-03 13:59:17 -07:00
Vyas Ramasubramani
a3b729bca8 fmt::memory_buffer is no longer an iterator. 2022-11-03 10:04:02 -07:00
Georgy Evtushenko
2ce4e425ee Merge pull request #98 from miscco/format_includes
Improve formatting of includes
2022-08-31 13:43:03 +04:00
Michael Schellenberger Costa
2b2d78b5c0 Improve formatting of includes 2022-08-31 11:39:29 +02:00
Georgy Evtushenko
1a13a2e724 Merge pull request #96 from senior-zero/fix-main/github/format
Fix formatting
2022-08-23 02:38:26 +04:00
Georgy Evtushenko
eb4d1b2d5f Add git blame ignore revs 2022-08-23 02:36:28 +04:00
clang-format
8f1152d4a2 Auto format 2022-08-23 02:34:35 +04:00
Georgy Evtushenko
87ce9ee576 Increase line limit 2022-08-18 19:35:22 +04:00
Allison Vacanti
61d862f845 Merge pull request #94 from robertmaynard/update_rapids-cmake
Update to latest version of rapids
2022-08-10 12:52:28 -04:00
Robert Maynard
8919728d32 Update to latest version of rapids
Also ensure that we don't clobber any existing rapids.cmake file
2022-08-08 13:24:29 -04:00
Allison Vacanti
9630a081e6 Merge pull request #93 from hahnjo/local-json
Allow using local nlohmann_json installation
2022-08-05 13:14:23 -04:00
Jonas Hahnfeld
449cd4e275 Allow using local nlohmann_json installation
Use the nlohmann_json::nlohmann_json if available, otherwise fall
back to add the downloaded headers.

Closes #19
2022-08-05 09:57:56 +02:00
Allison Vacanti
761ded142a Merge pull request #89 from PointKernel/patch-1
Fix a typo in README.md
2022-06-06 12:48:59 -04:00
Yunsong Wang
46a2dc2856 Update README.md 2022-06-06 08:59:32 -04:00
Allison Vacanti
12d13bdc5e Merge pull request #85 from pauleonix/main
Add --disable-blocking-kernel and --profile options.
2022-04-26 13:23:58 -04:00
pauleonix
79912d7b5f Fix no_block_tags
Co-authored-by: Allison Vacanti <alliepiper16@gmail.com>
2022-04-26 13:44:19 +02:00
Paul Große-Bley
2b5662ea4a Rename [get|set|m]_no_block to [get|set|m]_disable_blocking_kernel in public APIs 2022-04-26 13:40:46 +02:00
Paul Große-Bley
7f51ead595 Add --disable-blocking-kernel and --profile options. 2022-04-08 20:03:44 +02:00
Allison Vacanti
9eed5ab9c3 Merge pull request #79 from PointKernel/fix-config-count-bug
Fix a bug in config count unit test: count number of devices as well
2022-02-18 16:54:49 -05:00
Allison Vacanti
9d655fc48e Improve diagnostic when failing to lock old cards' clocks.
The issue is that the APIs we currently use don't support older
hardware. Users can still lookup the desired frequency for their
HW and manually lock clocks with nvidia-smi.
2022-02-15 14:38:19 -05:00
Allison Vacanti
9d0b2230bc Use SM version instead of PTX version when reporting HW capabilities. 2022-02-15 14:36:40 -05:00
Yunsong Wang
af4c35d78b Fix a bug in config count unit test: count number of devices as well 2022-02-11 18:24:58 -05:00
Allison Vacanti
48d94259b4 Fix typo in new docs. 2022-02-11 14:01:49 -05:00
Allison Vacanti
6c2c53ed4a Reduce time spent smoketesting examples. 2022-02-11 13:54:40 -05:00
Allison Vacanti
19961206e2 Run tests in parallel. 2022-02-11 13:54:22 -05:00
Allison Vacanti
38cecd5f76 Merge pull request #76 from PointKernel/add-implicit-stream-support
Add implicit stream benchmarking support
2022-02-11 13:38:06 -05:00
Allison Vacanti
039d455727 Move documentation on streams to new subsection.
Also update to use `nvbench::make_cuda_stream_view`.
2022-02-11 13:29:06 -05:00
Allison Vacanti
3b41387637 Add nvbench::make_cuda_stream_view(cudaStream_t). 2022-02-11 13:26:33 -05:00