NVIDIA/nvbench
1
0
Fork 0
mirror of https://github.com/NVIDIA/nvbench.git synced 2026-04-20 06:48:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1 from PointKernel/doc-update

Browse Source 
Minor corrections in doc
This commit is contained in:
Allison Vacanti
2021-03-11 18:32:00 -05:00
committed by GitHub
parent ca8e2d6391 a097e6d90d
commit 1e5f858d99
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/benchmarks.md
View File

@@ -91,7 +91,7 @@ NVBENCH_BENCH(benchmark).add_int64_power_of_two_axis("NumInputs",
{4, 6, 8, 10, 12});
// Or, as shown in a later section:
NVBENCH_BENCH(benchmark).add_int64_power_of_two_axis("NumInputs",
nvbench::range(4, 12, 2});
nvbench::range(4, 12, 2));
```
## Float64 Axes
@@ -254,7 +254,7 @@ void my_benchmark(nvbench::state& state, nvbench::type_list<T, U>)
/* ... */
};
// Skip benchmarks are compile time -- for example, always skip when T == U
// Skip benchmarks at compile time -- for example, always skip when T == U
// (Note that the `type_list` argument defines the same type twice).
template <typename SameType>
void my_benchmark(nvbench::state& state,
@@ -280,7 +280,7 @@ Execution tags may be passed to `state.exec` when these assumptions are not
true:
- `nvbench::exec_tag::sync` tells NVBench that the kernel launcher will
synchronize internally, and
synchronize internally.
- `nvbench::exec_tag::timer` requests a timer object that can be used to
restrict the timed region.