Add cast pushdown optimization for bit-packed integer widening
#8046Comparing
claude/cast-bitpacked-pushdown-VNtVh
(6603c3f
) withdevelop
(c54ce7e
)-2%
- Improvement
- 2
- Regression
- 1
- Untouched
- 1234
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
1237 total
fast_lt_out_of_range[4, 65536]
encodings/fastlanes/benches/bitpack_compare.rs-22%
204.3 µs262.4 µs
baseline_eq[16, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+11%
287.6 µs259.5 µs
baseline_lt[16, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+10%
302.7 µs274.7 µs
cuda/alp_for_bp_6bw_f32/dispatch_f32[100M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::cuda+5%
1.1 ms1.1 ms
take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+3%
26.3 µs25.5 µs
decode_primitives[f32, (1000, 512)]
vortex-array/benches/dict_compress.rs+3%
18.8 µs18.3 µs
chunked_dict_fsst_canonical_into[(1000, 100, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14 ms13.6 ms
chunked_dict_fsst_into_canonical[(1000, 100, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14.1 ms13.7 ms
chunked_dict_fsst_canonical_into[(1000, 10, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
13.9 ms13.6 ms
chunked_dict_fsst_canonical_into[(1000, 1000, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+3%
14.9 ms14.5 ms
new_bp_prim_test_between[i16, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+3%
49.6 µs48.4 µs
cuda/runend/i32_runlen_10[100M]
vortex-cuda/benches/runend_cuda.rs::benches::benchmark_runend::cuda+2%
1.4 ms1.4 ms
baseline_eq[4, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+2%
243.7 µs238.1 µs
chunked_dict_fsst_into_canonical[(1000, 1000, 100)]
encodings/fsst/benches/chunked_dict_fsst_builder.rs+2%
14.9 ms14.6 ms
new_raw_prim_test_between[f32, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+2%
34.5 µs33.7 µs
baseline_lt[4, 65536]
encodings/fastlanes/benches/bitpack_compare.rs+2%
257.7 µs252.1 µs
new_raw_prim_test_between[u32, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+2%
34.1 µs33.4 µs
new_bp_prim_test_between[i64, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+2%
62.3 µs61 µs
new_raw_prim_test_between[i64, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+2%
37.5 µs36.8 µs
new_alp_prim_test_between[f64, 2048]
encodings/fastlanes/benches/compute_between.rs::alp+2%
71.4 µs70 µs
new_raw_prim_test_between[u64, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+2%
37.5 µs36.8 µs
new_bp_prim_test_between[i32, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+2%
54 µs53 µs
push_n_vortex_buffer[u16, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
1.6 µs1.6 µs
new_alp_prim_test_between[f32, 2048]
encodings/fastlanes/benches/compute_between.rs::alp+2%
62.8 µs61.8 µs
new_raw_prim_test_between[f64, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+2%
37.9 µs37.3 µs
Commits
Click on a commit to change the comparison rangeBase
develop
c54ce7e
-0.92%
Add cast-on-decompression pushdown for bit-packed arrays
a97240a
10 hours ago
by claude+0.99%
Wire bit-packed cast pushdown into CastKernel for widening int casts
267524d
9 hours ago
by claude+8.88%
Fix clippy lints and refresh public-api.lock for cast pushdown
2010fd3
8 hours ago
by claude+10.84%
u
b0d1f54
7 hours ago
by joseph-isaacs-35.96%
u
921b04b
6 hours ago
by joseph-isaacs+35.97%
u
69d7270
6 hours ago
by joseph-isaacs-0.01%
Deduplicate patch application in bit-packed cast pushdown
dde5949
3 hours ago
by claude-21.46%
Test bit-packed widening cast through the real engine path
6603c3f
1 hour ago
by claude