Avatar for the spiraldb user
spiraldb
fastlanes
BlogDocsChangelog

feature: Add cuda kernel generator

#112Closed
Comparing
rk/addcudakernelgenerator
(
a650781
) with
develop
(
72f6c13
)
CodSpeed Performance Gauge
+30%
Improvement
1
Untouched
35
Skipped
16

Benchmarks

52 total
for_pack_16_to_3_stack
benches/ffor.rs
CodSpeed Performance Gauge
+30%
2.3 µs1.8 µs
unfor_pack_16_from_3_stack
benches/ffor.rs
CodSpeed Performance Gauge
+1%
3 µs3 µs
unchecked_unfor_pack_16_from_3_stack
benches/ffor.rs
CodSpeed Performance Gauge
+1%
3.2 µs3.2 µs
unpack_then_add_reference_16_from_3_stack
benches/ffor.rs
CodSpeed Performance Gauge
+1%
3.7 µs3.6 µs
unchecked_unpack_then_add_reference_16_from_3_stack
benches/ffor.rs
CodSpeed Performance Gauge
+1%
3.8 µs3.8 µs
delta_u16_fused
benches/delta.rs
CodSpeed Performance Gauge
+1%
3.6 µs3.6 µs
delta_u16_unfused
benches/delta.rs
CodSpeed Performance Gauge
+1%
5.1 µs5.1 µs
delta_throughput_compress
benches/delta.rs
CodSpeed Performance Gauge
0%
804.7 µs804.7 µs
throughput_compress
benches/ffor.rs
CodSpeed Performance Gauge
0%
824.1 µs824.1 µs
pack_16_to_3_stack
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
2.2 µs2.2 µs
for_pack_16_to_3_heap
benches/ffor.rs
CodSpeed Performance Gauge
0%
1.8 µs1.8 µs
throughput_decompress
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
1.2 ms1.2 ms
throughput_decompress_separate_reference
benches/ffor.rs
CodSpeed Performance Gauge
0%
1.4 ms1.4 ms
rle_throughput_decode_32
benches/rle.rs
CodSpeed Performance Gauge
0%
4.8 ms4.8 ms
bitpacking_cmp_fused[u32]
benches/bitpacking_cmp_cod.rs
CodSpeed Performance Gauge
0%
2.8 µs2.8 µs
rle_encode_u32
benches/rle.rs
CodSpeed Performance Gauge
0%
5.6 µs5.6 µs
transpose_u16
benches/transpose.rs
CodSpeed Performance Gauge
0%
10.8 µs10.8 µs
pack_16_to_3_heap
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
1.8 µs1.8 µs
bitpacking_cmp_seq[u16]
benches/bitpacking_cmp_cod.rs
CodSpeed Performance Gauge
0%
5.3 µs5.3 µs
bitpacking_cmp_seq[u64]
benches/bitpacking_cmp_cod.rs
CodSpeed Performance Gauge
0%
5.6 µs5.6 µs
unpack_16_from_3_stack
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
2.8 µs2.8 µs
unpack_single_16_from_3
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
14.2 µs14.2 µs
throughput_compress
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
804.7 µs804.7 µs
bitpacking_cmp_unpack[u16]
benches/bitpacking_cmp_cod.rs
CodSpeed Performance Gauge
0%
2.7 µs2.7 µs
unchecked_unpack_16_from_3_stack
benches/bitpacking.rs
CodSpeed Performance Gauge
0%
3 µs3 µs

Commits

Click on a commit to change the comparison range
Base
develop
72f6c13
-21.7%
feature: Add cuda kernel generator
0650c00
4 days ago
by robert3005
+51.45%
format
a650781
4 days ago
by robert3005
© 2026 CodSpeed Technology
Home Terms Privacy Docs