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
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
Allison Vacanti
8ae58981ca
Add docs for launch and cuda_stream.
2022-02-11 13:25:41 -05:00
Allison Vacanti
da2ec38cdb
Exclude some bits from clang-format.
2022-02-11 13:20:05 -05:00
Yunsong Wang
fde2e408de
Add stream benchmark example
2022-02-07 13:09:35 -05:00
Yunsong Wang
6159d9c6cb
Minor correction in unit test
2022-02-06 20:19:21 -05:00
Yunsong Wang
e05bf002f7
Use unique_ptr + custom deleter to simplify destroy logic
2022-02-06 20:14:41 -05:00
Yunsong Wang
e7c29c1c1b
Update docs
2022-02-06 19:34:57 -05:00
Yunsong Wang
a2a12c689c
Update docs/benchmarks.md
...
Co-authored-by: Jake Hemstad <jhemstad@nvidia.com >
2022-02-06 19:31:20 -05:00
Yunsong Wang
33a896f99e
Update copyright year
2022-02-04 17:25:50 -05:00
Yunsong Wang
76cbbcc8f9
Update benchmarks.md
2022-02-04 17:20:40 -05:00
Yunsong Wang
470beda9f0
Add nvbench::state stream tests
2022-02-04 16:55:29 -05:00
Yunsong Wang
439ffec1c8
Minor correction
2022-02-04 16:35:55 -05:00
Yunsong Wang
86708ec793
Fix a stream destroy bug
2022-02-04 16:03:52 -05:00
Yunsong Wang
14eab0774a
Update measure_* classes to construct launch from the state cuda stream
2022-02-04 14:16:43 -05:00
Yunsong Wang
c510a0e78c
Update launch to hold a const ref of nvbenc::cuda_stream
2022-02-04 13:56:02 -05:00
Yunsong Wang
8aea3e467e
Add a cuda stream member to nvbench::state
2022-02-04 13:51:30 -05:00
Yunsong Wang
15f2e92fdf
Add owning and non-owning semantics to nvbench::cuda_stream
2022-02-04 13:26:00 -05:00
Allison Vacanti
b1b6d73afa
Merge pull request #74 from S-o-T/fix_for_fmt8
...
Add missing formatter
2022-01-28 11:48:26 -05:00
Mark Shachkov
c9b1bdaf00
Cast axis_type to string prior to formatting
2022-01-28 10:11:21 +03:00
