Comparing
claude/avx512-decode-benchmark-wRhkZ
(13fde6b
) withdevelop
(5aa3f3d
)+5%
- Improvement
- 12
- Regression
- 3
- Untouched
- 1260
Unknown Walltime execution environment detected
Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data. For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.Benchmarks
1275 total
chunked_bool_canonical_into[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs-33%
30.3 µs45.1 µs
chunked_varbinview_into_canonical[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs-17%
176.1 µs212.2 µs
chunked_varbinview_canonical_into[(100, 100)]
vortex-array/benches/chunk_array_builder.rs-11%
273.5 µs308.4 µs
take_map[(0.1, 1.0)]
vortex-array/benches/take_patches.rs+17%
1.9 ms1.6 ms
fsst_decompress_string
vortex/benches/single_encoding_throughput.rs+14%
3.5 ms3.1 ms
decompress_fsst[(10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+14%
578.6 µs509.7 µs
chunked_canonicalize_into[(10, 10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+13%
5.9 ms5.2 ms
chunked_into_canonical[(10, 10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+13%
5.9 ms5.2 ms
decompress_fsst[(10000, 16, 8)]
encodings/fsst/benches/fsst_compress.rs+12%
631.7 µs561.9 µs
decompress_fsst[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+12%
388.4 µs347.3 µs
chunked_into_canonical[(10, 10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+12%
4 ms3.6 ms
decompress_fsst[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+12%
397.7 µs356.5 µs
chunked_canonicalize_into[(10, 10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+11%
4 ms3.6 ms
canonicalize_compare[(10000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+11%
705 µs635.3 µs
canonicalize_compare[(10000, 16, 8)]
encodings/fsst/benches/fsst_compress.rs+10%
757.8 µs688.2 µs
new_alp_prim_test_between[f32, 32768]
encodings/fastlanes/benches/compute_between.rs::alp+10%
168.9 µs153.8 µs
take_map[(0.1, 0.5)]
vortex-array/benches/take_patches.rs+9%
1,092.6 µs999.7 µs
decompress_fsst[(1000, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+9%
79.5 µs73 µs
canonicalize_compare[(10000, 4, 4)]
encodings/fsst/benches/fsst_compress.rs+9%
515.8 µs474.6 µs
canonicalize_compare[(10000, 4, 8)]
encodings/fsst/benches/fsst_compress.rs+9%
525.7 µs484.2 µs
new_bp_prim_test_between[i64, 32768]
encodings/fastlanes/benches/compute_between.rs::bitpack+8%
162.4 µs150.2 µs
chunked_into_canonical[(1000, 100, 16, 4)]
encodings/fsst/benches/fsst_compress.rs+8%
9.5 ms8.8 ms
decompress_fsst[(1000, 16, 8)]
encodings/fsst/benches/fsst_compress.rs+8%
84.7 µs78.5 µs
cuda/bitpacked_patched_u8/unpack/1%[100M]
vortex-cuda/benches/bitpacked_cuda.rs::benches::benchmark_bitunpack_with_patches::cuda+8%
410.9 µs381.2 µs
new_alp_prim_test_between[f32, 16384]
encodings/fastlanes/benches/compute_between.rs::alp+8%
106.4 µs98.9 µs
Commits
Click on a commit to change the comparison rangeBase
develop
5aa3f3d
+0.23%
Speed up VarBinView build_views single-buffer canonicalization
50b0e93
19 days ago
by joseph-isaacs+4.62%
Apply PR review feedback on varbinview construction
13fde6b
15 days ago
by joseph-isaacs