Issues
- 4
Check for CUDA errors after running benchmark
#88 opened by alliepiper - 1
Custom CUPTI metrics
#121 opened by mmcloughlin - 5
Tracking `nvbench` benchmark results
#132 opened by epompeii - 6
- 1
Async benchmarks always deadlock
#136 opened by gevtushenko - 0
- 0
- 0
- 0
Smart selection of the entropy step
#154 opened by gevtushenko - 0
Associate parameters with stopping criterion to allow stateful CLI parsing and improved diagnostics
#153 opened by alliepiper - 0
vcpkg upstream
#152 opened by endingly - 0
Consider `is_finished` customization
#147 opened by gevtushenko - 6
Bazel build rules
#120 opened by mmcloughlin - 4
How can the output metrics be interpreted
#115 opened by seanajohnston - 2
- 1
- 2
- 0
Add option for reporting min/max/median runtime
#135 opened by sleeepyjack - 1
- 3
- 0
- 0
Automatic cuda graph testing
#124 opened by luitjens - 8
Is there anyway to build offline?
#112 opened by ax7e - 1
- 0
Document jsonbin output format
#122 opened by alliepiper - 1
Implement and test NVRTC support
#119 opened by alliepiper - 0
Compact output format
#118 opened by alliepiper - 1
- 2
- 3
CUDA 11.4 can not compile
#111 opened by ax7e - 1
Use publicly visible CI runs
#110 opened by aaronmondal - 0
Use squash merging by default
#109 opened by aaronmondal - 9
- 11
- 0
[BUG] Memory allocations from flushing L2 can lead to significant delays between benchmark executions
#100 opened by jrhemstad - 9
- 3
- 3
- 2
Reasonable enum defaults don't work
#84 opened by pauleonix - 4
Add optional types to type axes
#82 opened by pauleonix - 3
Add benchmark groups/sets/tags
#81 opened by pauleonix - 0
Add hidden benchmarks
#83 opened by pauleonix - 2
- 0
[FEA] Add Global Set-Up and Tear-Down
#78 opened by karthikeyann - 1
Unused parameter warnings
#75 opened by harrism - 0
Build fails with fmt 8.1.1
#73 opened by S-o-T - 0
- 0
Export raw samples as binary blobs
#67 opened by alliepiper - 6
Add a `zip_axis` / `tuple_axis` that iterates through multiple parameter axes in lockstep
#68 opened by alliepiper - 4