claude/great-edison-jrGY0 - Branch - vortex-data/vortex

perf: aggregate min/max

#8061

Comparing

claude/great-edison-jrGY0

(

8b98b5d

) with

develop

(

ae19fe7

)

+15%

Improvement: 7

Regression: 1

Untouched: 1243

New: 6

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

1257 total

pack_return_dtype[100]

vortex-array/benches/expr/large_struct_pack.rs

67.3 µs67.2 µs

push_vortex_buffer[2048]

vortex-buffer/benches/vortex_buffer.rs

16.4 µs16.4 µs

take_fsl_random[64, 100]

vortex-array/benches/take_fsl.rs

119.9 µs119.7 µs

new_raw_prim_test_between[i64, 32768]

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

168.4 µs168.1 µs

bench_many_nulls[0.01]

vortex-array/benches/dict_unreferenced_mask.rs

49.2 µs49.1 µs

chunked_dict_fsst_into_canonical[(1000, 10, 10)]

encodings/fsst/benches/chunked_dict_fsst_builder.rs

1.5 ms1.5 ms

case_when_simple[1000]

vortex-array/benches/expr/case_when_bench.rs

83.8 µs83.7 µs

decompress_alp[f64, (10000, 0.1, 1.0)]

encodings/alp/benches/alp_compress.rs

71.2 µs71 µs

decompress_alp[f64, (10000, 0.1, 0.95)]

encodings/alp/benches/alp_compress.rs

71.6 µs71.5 µs

take_filter_primitive_large_random_mask_random_indices[(2500, 25000)]

vortex-array/benches/take_filter.rs

330.4 µs329.9 µs

decompress_rd[f32, (10000, 0.01)]

encodings/alp/benches/alp_compress.rs

83.6 µs83.4 µs

chunked_dict_primitive_canonical_into[f32, (1000, 1000, 10)]

vortex-array/benches/chunked_dict_builder.rs

100.9 µs100.7 µs

decode_primitives[i64, (1000, 4)]

vortex-array/benches/dict_compress.rs

19.2 µs19.2 µs

new_bp_prim_test_between[i64, 32768]

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

222.4 µs222.1 µs

cast_execute[(65536, 1, 0.01)]

encodings/fastlanes/benches/cast_bitpacked.rs

190.8 µs190.5 µs

push_n_vortex_buffer[u16, 16384]

vortex-buffer/benches/vortex_buffer.rs

18.5 µs18.5 µs

new_raw_prim_test_between[u64, 32768]

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

169 µs168.7 µs

cuda/bitpacked_u16/unpack/5bw[100M]

vortex-cuda/benches/bitpacked_cuda.rs::benches::benchmark_bitunpack::cuda

558 µs557.2 µs

decompress_rd[f32, (10000, 0.1)]

encodings/alp/benches/alp_compress.rs

83.6 µs83.5 µs

chunked_dict_primitive_canonical_into[f32, (1000, 100, 10)]

vortex-array/benches/chunked_dict_builder.rs

86.3 µs86.1 µs

rebuild_naive

encodings/zstd/benches/listview_rebuild.rs

142.2 µs142 µs

new_raw_prim_test_between[f64, 32768]

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

176.1 µs175.9 µs

cuda/dict/u64_values_u8_codes[100M]

vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict::cuda

2 ms2 ms

take_10k_random

encodings/fastlanes/benches/bitpacking_take.rs

238 µs237.7 µs

case_when_without_else[10000]

vortex-array/benches/expr/case_when_bench.rs

129.4 µs129.2 µs

Commits

Click on a commit to change the comparison range

Base

develop

ae19fe7

+28.11%

Vectorize integer min/max for all-valid arrays

e9a31ad

6 hours ago

by claude

-28.26%

Simplify aggregate max benchmark to one bench per type

ac47a14

5 hours ago

by claude

+32.2%

Reduce aggregate max benchmark array length to 100k

08abd6a

5 hours ago

by claude

-17.21%

Vectorize integer sum via chunked widening accumulator

8b98b5d

26 minutes ago

by claude

Home Terms Privacy Docs