Avatar for the vortex-data user
vortex-data
vortex
BlogDocsChangelog

feature: Add fastlanes bit unpacking cuda kernels

#6145Merged
Comparing
rk/cudabitpacking
(
960ce72
) with
develop
(
68130ce
)
CodSpeed Performance Gauge
-83%
Improvement
7
Regression
10
Untouched
1133
Skipped
1233
Archived
101

Benchmarks

1233 total
null_count_run_end[(100000, 256, 0.5)]
encodings/runend/benches/run_end_null_count.rs
Skipped
12.9 KB*
pco_canonical[(10000, 1.0)]
encodings/pco/benches/pco.rs
Skipped
128 B*
decompress[u64, (100000, 1024)]
encodings/runend/benches/run_end_compress.rs
Skipped
776.2 KB*
pco_canonical[(50000, 1.0)]
encodings/pco/benches/pco.rs
Skipped
128 B*
null_count_run_end[(10000, 1024, 0.5)]
encodings/runend/benches/run_end_null_count.rs
Skipped
1.8 KB*
null_count_run_end[(10000, 16, 0.1)]
encodings/runend/benches/run_end_null_count.rs
Skipped
1.9 KB*
take_indices[(10000, 256, 0.03)]
encodings/runend/benches/run_end_filter.rs
Skipped
5.7 KB*
decompress[u64, (1000000, 256)]
encodings/runend/benches/run_end_compress.rs
Skipped
7.6 MB*
pco_canonical[(100000, 0.5)]
encodings/pco/benches/pco.rs
Skipped
128 B*
take_indices[(1000, 4, 0.03)]
encodings/runend/benches/run_end_filter.rs
Skipped
1.4 KB*
decompress[u16, (1000, 256)]
encodings/runend/benches/run_end_compress.rs
Skipped
1.7 KB*
filter_runend[(10000, 4, 0.01)]
encodings/runend/benches/run_end_filter.rs
Skipped
23.1 KB*
take_indices[(10000, 1024)]
encodings/runend/benches/run_end_compress.rs
Skipped
1.9 KB*
take_indices[(1000, 16)]
encodings/runend/benches/run_end_compress.rs
Skipped
2.1 KB*
filter_runend[(10000, 256, 0.01)]
encodings/runend/benches/run_end_filter.rs
Skipped
1 KB*
filter_runend[(1000, 16, 0.03)]
encodings/runend/benches/run_end_filter.rs
Skipped
1.3 KB*
decompress[u64, (10000, 16)]
encodings/runend/benches/run_end_compress.rs
Skipped
78.3 KB*
take_indices[(10000, 256)]
encodings/runend/benches/run_end_compress.rs
Skipped
2 KB*
null_count_run_end[(100000, 256, 0.1)]
encodings/runend/benches/run_end_null_count.rs
Skipped
12.9 KB*
null_count_run_end[(10000, 256, 0.5)]
encodings/runend/benches/run_end_null_count.rs
Skipped
1.9 KB*
take_indices[(100000, 4)]
encodings/runend/benches/run_end_compress.rs
Skipped
99.5 KB*
decompress[u8, (10000, 4)]
encodings/runend/benches/run_end_compress.rs
Skipped
10 KB*
filter_runend[(1000, 4, 0.005)]
encodings/runend/benches/run_end_filter.rs
Skipped
2.9 KB*
filter_runend[(1000, 256, 0.005)]
encodings/runend/benches/run_end_filter.rs
Skipped
776 B*
null_count_run_end[(10000, 16, 0.5)]
encodings/runend/benches/run_end_null_count.rs
Skipped
1.9 KB*

Commits

Click on a commit to change the comparison range
Base
develop
68130ce
+0.01%
less
65d7812
29 days ago
by robert3005
-0.01%
more
fd528d6
29 days ago
by robert3005
-84%
less
dc8c8b7
29 days ago
by robert3005
+62.46%
fixes
3ed9b0c
29 days ago
by robert3005
-3.72%
unnecessary
6235337
29 days ago
by robert3005
+25.28%
more
4bda5ba
28 days ago
by robert3005
-0.07%
license
999cdc6
28 days ago
by robert3005
+0.13%
compiles
51017b2
28 days ago
by robert3005
-82.93%
override
960ce72
28 days ago
by robert3005
© 2026 CodSpeed Technology
Home Terms Privacy Docs