Scalar truncation is implemented over scalar values instead of scalars and can operate in place
#6414Comparing
rk/inplacetruncation
(4c5edf7
) withdevelop
(aa55054
)+35%
- Improvement
- 5
- Untouched
- 1130
- Skipped
- 1268
Benchmarks
2403 total
take_map[(0.1, 1.0)]
vortex-array/benches/take_patches.rs+35%
4.7 ms3.5 ms
take_map[(0.1, 0.5)]
vortex-array/benches/take_patches.rs+35%
2.8 ms2.1 ms
take_map[(0.05, 0.1)]
vortex-array/benches/take_patches.rs+33%
792 µs594.2 µs
take_map[(0.05, 1.0)]
vortex-array/benches/take_patches.rs+31%
4.1 ms3.1 ms
take_map[(0.1, 0.1)]
vortex-array/benches/take_patches.rs+21%
1,118.8 µs926.8 µs
take_map[(0.05, 0.5)]
vortex-array/benches/take_patches.rs+9%
1.8 ms1.7 ms
take_map[(0.1, 0.05)]
vortex-array/benches/take_patches.rs+6%
825.1 µs775.8 µs
take_map[(0.05, 0.05)]
vortex-array/benches/take_patches.rs+5%
479.4 µs455.5 µs
new_raw_prim_test_between[i64, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+3%
27.2 µs26.4 µs
true_count_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
1 µs1 µs
decode_varbinview[(1000, 32)]
vortex-array/benches/dict_compress.rs+3%
34.5 µs33.6 µs
train_compressor[(10000, 64, 4)]
encodings/fsst/benches/fsst_compress.rs+3%
4.7 ms4.6 ms
true_count_vortex_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
1.2 µs1.1 µs
train_compressor[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+2%
4.9 ms4.8 ms
train_compressor[(10000, 64, 8)]
encodings/fsst/benches/fsst_compress.rs+2%
4.7 ms4.6 ms
take_map[(0.005, 1.0)]
vortex-array/benches/take_patches.rs+2%
2.5 ms2.4 ms
true_count_vortex_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.3 µs1.3 µs
train_compressor[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+2%
5.2 ms5.1 ms
chunked_bool_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs+2%
67.3 µs66 µs
bitwise_or_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
4.7 µs4.6 µs
bitwise_and_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
4.7 µs4.6 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+2%
37.9 µs37.2 µs
iter_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.6 µs1.6 µs
take_map[(0.01, 0.05)]
vortex-array/benches/take_patches.rs+2%
202.8 µs199.2 µs
take_map[(0.01, 0.1)]
vortex-array/benches/take_patches.rs+2%
322.5 µs317 µs
Commits
Click on a commit to change the comparison rangeBase
develop
aa55054
+34.63%
comments
4c5edf7
17 hours ago
by robert3005