ji/tree-enc-throughput - Branch - vortex-data/vortex

chore[vx]: more decompression throughput benchmarks

#5067Merged

Comparing

ji/tree-enc-throughput

(

b3c8beb

) with

develop

(

3fcccdb

)

Untouched: 553

Archived: 773

Benchmarks

1326 total

take_map[(0.005, 1.0)]

vortex-array/benches/take_patches.rs

+1%

1.4 ms1.4 ms

fsst_decompress_string

vortex/benches/single_encoding_throughput.rs

+1%

38.2 ms38 ms

zstd_compress_string

vortex/benches/single_encoding_throughput.rs

1.4 s1.4 s

pcodec_compress_f64

vortex/benches/single_encoding_throughput.rs

100.8 ms100.5 ms

take_map[(0.1, 0.5)]

vortex-array/benches/take_patches.rs

1.3 ms1.3 ms

patched_take_10k_contiguous_patches

encodings/fastlanes/benches/bitpacking_take.rs

1.5 ms1.5 ms

runend_compress_u32

vortex/benches/single_encoding_throughput.rs

50.8 ms50.7 ms

take_map[(0.005, 0.05)]

vortex-array/benches/take_patches.rs

112.7 µs112.6 µs

take_map[(0.01, 0.5)]

vortex-array/benches/take_patches.rs

765 µs764.7 µs

patched_take_10k_contiguous_not_patches

encodings/fastlanes/benches/bitpacking_take.rs

735.8 µs735.4 µs

patched_take_10k_random

encodings/fastlanes/benches/bitpacking_take.rs

1.5 ms1.5 ms

compress_fsst[(1000, 64, 8)]

encodings/fsst/benches/fsst_compress.rs

529.7 µs529.6 µs

patched_take_10k_adversarial

encodings/fastlanes/benches/bitpacking_take.rs

1.4 ms1.4 ms

take_map[(0.01, 1.0)]

vortex-array/benches/take_patches.rs

1.5 ms1.5 ms

new_bp_prim_test_between[i32, 2048]

encodings/fastlanes/benches/compute_between.rs::bitpack

39.2 µs39.2 µs

new_alp_prim_test_between[f64, 2048]

encodings/fastlanes/benches/compute_between.rs::alp

53.1 µs53.1 µs

new_bp_prim_test_between[i64, 2048]

encodings/fastlanes/benches/compute_between.rs::bitpack

43.9 µs43.9 µs

chunked_varbinview_opt_canonical_into[(100, 100)]

vortex-array/benches/chunk_array_builder.rs

312.4 µs312.3 µs

compress_fsst[(10000, 16, 8)]

encodings/fsst/benches/fsst_compress.rs

2 ms2 ms

take_indices[(100000, 256)]

encodings/runend/benches/run_end_compress.rs

41.8 µs41.8 µs

compress_fsst[(10000, 64, 8)]

encodings/fsst/benches/fsst_compress.rs

4.9 ms4.9 ms

take_map[(0.005, 0.1)]

vortex-array/benches/take_patches.rs

182.4 µs182.4 µs

patched_take_10_contiguous

encodings/fastlanes/benches/bitpacking_take.rs

31.3 µs31.3 µs

take_indices[(1000, 4)]

encodings/runend/benches/run_end_compress.rs

31.6 µs31.6 µs

chunked_bool_canonical_into[(1000, 10)]

vortex-array/benches/chunk_array_builder.rs

48.3 µs48.3 µs

Commits

Click on a commit to change the comparison range

Base

develop

3fcccdb

chore[vx]: more decompression throughput benchmarks

3b865b0

7 months ago

by joseph-isaacs

chore[vx]: more decompression throughput benchmarks

b3c8beb

7 months ago

by joseph-isaacs

Home Terms Privacy Docs