Comparing
ad/cuda-vector-ops
(979292b
) withdevelop
(953c00c
)0%
- Untouched
- 1204
- Skipped
- 1179
- Archived
- 125
Benchmarks
2508 total
true_count_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+6%
1,005.3 ns946.9 ns
true_count_arrow_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+6%
1.1 µs1 µs
true_count_arrow_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+5%
1.3 µs1.2 µs
binary_search_std
vortex-array/benches/search_sorted.rs+4%
741.4 ns712.2 ns
binary_search_vortex
vortex-array/benches/search_sorted.rs+4%
817.2 ns788.1 ns
map_each[BufferMut<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs+4%
858.1 ns828.9 ns
value_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
1.1 µs1.1 µs
canonical_into_non_nullable[(10000, 1, 0.0)]
encodings/fastlanes/benches/canonicalize_bench.rs+3%
36 µs35.1 µs
old_bp_prim_test_between[i32, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+3%
458.1 µs446.9 µs
take_map[(0.005, 0.5)]
vortex-array/benches/take_patches.rs+2%
1.4 ms1.4 ms
canonical_into_non_nullable[(10000, 1, 0.01)]
encodings/fastlanes/benches/canonicalize_bench.rs+2%
41.2 µs40.4 µs
append_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.4 µs1.4 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+2%
33.4 µs32.7 µs
null_count_run_end[(10000, 1024, 0.01)]
encodings/runend/benches/run_end_null_count.rs+2%
3.2 µs3.1 µs
null_count_run_end[(10000, 256, 0.01)]
encodings/runend/benches/run_end_null_count.rs+2%
3.2 µs3.2 µs
null_count_run_end[(100000, 1024, 0.01)]
encodings/runend/benches/run_end_null_count.rs+2%
3.2 µs3.2 µs
old_bp_prim_test_between[i32, 16384]
encodings/fastlanes/benches/compute_between.rs::bitpack+2%
298 µs292.7 µs
take_map[(0.005, 0.05)]
vortex-array/benches/take_patches.rs+2%
198.5 µs195 µs
iter_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.7 µs1.7 µs
true_count_arrow_buffer[16384]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
3.6 µs3.6 µs
decompress[u8, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+2%
9.2 µs9.1 µs
canonical_into_non_nullable[(10000, 1, 0.1)]
encodings/fastlanes/benches/canonicalize_bench.rs+2%
56.6 µs55.7 µs
canonical_into_nullable[(10000, 1, 0.0)]
encodings/fastlanes/benches/canonicalize_bench.rs+2%
66 µs65 µs
decompress[u8, (1000, 16)]
encodings/runend/benches/run_end_compress.rs+1%
10.5 µs10.3 µs
decompress[u16, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+1%
10.5 µs10.4 µs
Commits
Click on a commit to change the comparison rangeBase
develop
953c00c
+0.03%
perf: CUDA FoR loop unrolling
979292b
1 month ago
by 0ax1