parquet bench + cuda changes to scan clickbench
#6739Comparing
os/parquet-bench
(4be081e
) withos/gpu-scan-bench
(f08430d
)-10%
- Improvement
- 3
- Regression
- 3
- Untouched
- 948
- Skipped
- 1466
Benchmarks
2420 total
map_each[BufferMut<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs-10%
770.6 ns858.1 ns
patched_take_200k_dispersed
encodings/fastlanes/benches/bitpacking_take.rs-10%
5.1 ms5.6 ms
true_count_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs-10%
1 µs1.2 µs
chunked_opt_bool_canonical_into[(10, 1000)]
vortex-array/benches/chunk_array_builder.rs+16%
1.6 ms1.4 ms
bench_many_nulls[0.9]
vortex-array/benches/dict_unreferenced_mask.rs+14%
547.5 µs481.6 µs
bench_many_nulls[0.5]
vortex-array/benches/dict_unreferenced_mask.rs+11%
379.5 µs342.8 µs
chunked_bool_canonical_into[(10, 1000)]
vortex-array/benches/chunk_array_builder.rs+9%
1.4 ms1.2 ms
encode_varbin[(1000, 8)]
vortex-array/benches/dict_compress.rs+7%
224.8 µs209.4 µs
encode_varbin[(1000, 2)]
vortex-array/benches/dict_compress.rs+7%
221.5 µs206.3 µs
encode_varbin[(1000, 4)]
vortex-array/benches/dict_compress.rs+7%
223.2 µs208 µs
chunked_bool_canonical_into[(100, 100)]
vortex-array/benches/chunk_array_builder.rs+7%
168 µs156.8 µs
bench_dict_mask[(0.1, 0.9)]
vortex-array/benches/dict_mask.rs+7%
1.9 ms1.7 ms
bench_dict_mask[(0.01, 0.9)]
vortex-array/benches/dict_mask.rs+7%
1.9 ms1.7 ms
encode_varbin[(1000, 32)]
vortex-array/benches/dict_compress.rs+7%
234.3 µs219.5 µs
bench_dict_mask[(0.5, 0.9)]
vortex-array/benches/dict_mask.rs+7%
1.9 ms1.7 ms
binary_search_vortex
vortex-array/benches/search_sorted.rs+7%
938.9 ns880.6 ns
chunked_opt_bool_into_canonical[(10, 1000)]
vortex-array/benches/chunk_array_builder.rs+7%
1.7 ms1.6 ms
bitwise_not_vortex_buffer_mut[128]
vortex-buffer/benches/vortex_bitbuffer.rs+6%
501.1 ns471.9 ns
bench_dict_mask[(0.01, 0.5)]
vortex-array/benches/dict_mask.rs+6%
2.1 ms1.9 ms
bench_dict_mask[(0.1, 0.5)]
vortex-array/benches/dict_mask.rs+6%
2.1 ms1.9 ms
bench_dict_mask[(0.5, 0.5)]
vortex-array/benches/dict_mask.rs+6%
2.1 ms1.9 ms
bench_dict_mask[(0.9, 0.1)]
vortex-array/benches/dict_mask.rs+6%
2.3 ms2.1 ms
bench_dict_mask[(0.9, 0.01)]
vortex-array/benches/dict_mask.rs+6%
2.3 ms2.2 ms
bench_dict_mask[(0.01, 0.01)]
vortex-array/benches/dict_mask.rs+5%
2.3 ms2.2 ms
bench_dict_mask[(0.1, 0.01)]
vortex-array/benches/dict_mask.rs+5%
2.3 ms2.2 ms
Commits
Click on a commit to change the comparison rangeBase
os/gpu-scan-bench
f08430d
-10.2%
use a cuda context per batch and add buffered
c237031
5 days ago
by onursatici0%
data-gen can create vortex-cuda for benchmarks
eb12dd9
5 days ago
by onursatici0%
s3fs to uv
4be081e
4 days ago
by onursatici