Rework `Scheme` estimation in compressor
#7230Comparing
ct/compress-estimation
(ba4dd26
) withdevelop
(fcfd443
)0%
- Untouched
- 1106
- Skipped
- 1522
Benchmarks
2628 total
map_each[BufferMut<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs+7%
465.8 ns436.7 ns
binary_search_std
vortex-array/benches/search_sorted.rs+6%
515.3 ns486.1 ns
decode_primitives[u8, (1000, 2)]
vortex-array/benches/dict_compress.rs+4%
23.8 µs23 µs
decode_primitives[u8, (10000, 32)]
vortex-array/benches/dict_compress.rs+2%
60.3 µs58.9 µs
decode_primitives[u8, (10000, 4)]
vortex-array/benches/dict_compress.rs+2%
60.2 µs58.9 µs
decode_primitives[u8, (10000, 8)]
vortex-array/benches/dict_compress.rs+2%
60.2 µs58.9 µs
decode_primitives[i64, (1000, 2)]
vortex-array/benches/dict_compress.rs+2%
26.7 µs26.2 µs
decode_primitives[f32, (1000, 32)]
vortex-array/benches/dict_compress.rs+2%
24 µs23.6 µs
transpose_scalar
encodings/fastlanes/benches/bit_transpose.rs+2%
1.7 µs1.7 µs
push_n_vortex_buffer[u32, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
1.8 µs1.7 µs
decode_primitives[f32, (1000, 4)]
vortex-array/benches/dict_compress.rs+2%
24.3 µs23.9 µs
untranspose_bmi2
encodings/fastlanes/benches/bit_transpose.rs::x86+2%
1.8 µs1.8 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+2%
40.5 µs39.9 µs
decode_varbin[(1000, 32)]
vortex-array/benches/dict_compress.rs+1%
34.4 µs34 µs
map_each[BufferMut<i32>, 1024]
vortex-buffer/benches/vortex_buffer.rs+1%
2.2 µs2.2 µs
encode_primitives[i64, (10000, 512)]
vortex-array/benches/dict_compress.rs+1%
566.5 µs559.5 µs
decode_varbin[(1000, 4)]
vortex-array/benches/dict_compress.rs+1%
34.2 µs33.8 µs
take_struct_sequential_indices
vortex-array/benches/take_struct.rs+1%
58.5 µs57.9 µs
take_map[(0.1, 1.0)]
vortex-array/benches/take_patches.rs+1%
1.6 ms1.6 ms
decode_varbin[(1000, 8)]
vortex-array/benches/dict_compress.rs+1%
34.2 µs33.9 µs
decode_varbin[(1000, 2)]
vortex-array/benches/dict_compress.rs+1%
34.2 µs33.8 µs
train_compressor[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+1%
4.2 ms4.1 ms
decode_primitives[f32, (1000, 8)]
vortex-array/benches/dict_compress.rs+1%
23.8 µs23.6 µs
push_n_vortex_buffer[u16, 1024]
vortex-buffer/benches/vortex_buffer.rs+1%
3.5 µs3.5 µs
from_iter[Buffer<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs+1%
3.7 µs3.7 µs
Commits
Click on a commit to change the comparison rangeBase
develop
fcfd443
+0.03%
rework schemes AGAIN
ba4dd26
22 hours ago
by connortsui20