NVIDIA/nvbench
1
0
Fork 0
mirror of https://github.com/NVIDIA/nvbench.git synced 2026-04-19 22:38:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Show zip versus linear iteration

Browse Source
This commit is contained in:
Robert Maynard
2022-03-01 09:11:40 -05:00
parent c3c86e1f26
commit 91c8f43d15
1 changed files with 17 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
examples/custom_iteration_spaces.cu
View File

@@ -60,16 +60,27 @@ void copy_sweep_grid_shape(nvbench::state &state)
num_values);
});
}
//==============================================================================
// Tied iteration space allows you to iterate two or more axes at the same
// time allowing for sparse exploration of the search space. Can also be used
// to test the diagonal of a square matrix
//
void naive_copy_sweep_grid_shape(nvbench::state &state)
{
copy_sweep_grid_shape(state);
}
void tied_copy_sweep_grid_shape(nvbench::state &state)
{
copy_sweep_grid_shape(state);
}
//==============================================================================
// Naive iteration of both the BlockSize and NumBlocks axis.
// Will generate the full cross product of the two axis for a total of
// 16 invocations of copy_sweep_grid_shape.
NVBENCH_BENCH(naive_copy_sweep_grid_shape)
// Full combinatorial of Every power of two from 64->1024:
.add_int64_axis("BlockSize", {32, 64, 128, 256})
.add_int64_axis("NumBlocks", {1024, 512, 256, 128});
//==============================================================================
// Zipped iteration of BlockSize and Numblocks axes.
// Will generate only 4 invocations of copy_sweep_grid_shape
NVBENCH_BENCH(tied_copy_sweep_grid_shape)
// Every power of two from 64->1024:
.add_zip_axes(nvbench::int64_axis{"BlockSize", {32, 64, 128, 256}},