gpu compatible write strategy, move compact strategy to use btrblocks with zstd and pco
#6322Comparing
os/gpu-strategy
(f4f3811
) withdevelop
(0b003d3
)+33%
- Improvement
- 1
- Untouched
- 1137
- Skipped
- 1265
Benchmarks
2403 total
chunked_bool_into_canonical[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+33%
87.2 µs65.6 µs
true_count_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+7%
917.8 ns859.4 ns
true_count_arrow_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+6%
980.3 ns921.9 ns
take_map[(0.05, 1.0)]
vortex-array/benches/take_patches.rs+6%
3.2 ms3.1 ms
true_count_arrow_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+5%
1.1 µs1.1 µs
new_raw_prim_test_between[i64, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+3%
26.3 µs25.6 µs
value_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
1.1 µs1.1 µs
append_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.5 µs1.4 µs
take_map[(0.1, 0.5)]
vortex-array/benches/take_patches.rs+2%
2.2 ms2.1 ms
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+2%
31.5 µs30.9 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%
3.5 µs3.5 µs
chunked_dict_primitive_canonical_into[f32, (1000, 100, 10)]
vortex-array/benches/chunked_dict_builder.rs+1%
94.8 µs93.5 µs
chunked_dict_primitive_canonical_into[f64, (1000, 100, 100)]
vortex-array/benches/chunked_dict_builder.rs+1%
1.2 ms1.2 ms
bitwise_and_arrow_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
3.3 µs3.3 µs
chunked_dict_primitive_canonical_into[f32, (1000, 10, 10)]
vortex-array/benches/chunked_dict_builder.rs+1%
93 µs92.3 µs
bitwise_and_arrow_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
3.8 µs3.8 µs
take_map[(0.05, 0.05)]
vortex-array/benches/take_patches.rs+1%
474.1 µs470.6 µs
take_map[(0.05, 0.1)]
vortex-array/benches/take_patches.rs+1%
611.9 µs607.8 µs
take_10_stratified
encodings/fastlanes/benches/bitpacking_take.rs+1%
23.9 µs23.8 µs
decompress_rd[f64, 10000]
encodings/alp/benches/alp_compress.rs+1%
248.8 µs247.3 µs
take_struct_sequential_indices
vortex-array/benches/take_struct.rs+1%
90.9 µs90.4 µs
true_count_arrow_buffer[65536]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
11.7 µs11.6 µs
take_map[(0.01, 0.05)]
vortex-array/benches/take_patches.rs0%
209.3 µs208.4 µs
old_bp_prim_test_between[i32, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack0%
141.8 µs141.2 µs
Commits
Click on a commit to change the comparison rangeBase
develop
0b003d3
-33.04%
gpu compatible write strategy
09d6906
3 days ago
by onursatici+65.96%
taplo
143b084
2 days ago
by onursatici+1.75%
Merge branch 'develop' into os/gpu-strategy
3b1e9af
2 days ago
by onursatici-1.63%
don't use custom compressor
73c05cf
2 days ago
by onursatici-33.02%
zstd
735233c
2 days ago
by onursatici+33.02%
taplo
b1eb106
2 days ago
by onursatici-0.12%
Merge branch 'develop' into os/gpu-strategy
f4f3811
2 days ago
by onursatici