Comparing
ad/fallback
(c5a1ed5
) withdevelop
(1c8667c
)-10%
- Regression
- 1
- Untouched
- 1015
- Skipped
- 1522
Benchmarks
2538 total
map_each[BufferMut<i32>, 128]
vortex-buffer/benches/vortex_buffer.rs-10%
770.6 ns858.1 ns
binary_search_std
vortex-array/benches/search_sorted.rs+6%
553.6 ns524.4 ns
binary_search_vortex
vortex-array/benches/search_sorted.rs+4%
807.2 ns778.1 ns
set_indices_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.2 µs1.2 µs
take_map[(0.1, 0.5)]
vortex-array/benches/take_patches.rs+2%
2.1 ms2 ms
transpose_scalar
encodings/fastlanes/benches/bit_transpose.rs+2%
1.8 µs1.8 µs
take_map[(0.01, 0.5)]
vortex-array/benches/take_patches.rs+1%
1.3 ms1.3 ms
old_alp_prim_test_between[f64, 2048]
encodings/fastlanes/benches/compute_between.rs::alp+1%
145.2 µs143.7 µs
push_n_vortex_buffer[u32, 128]
vortex-buffer/benches/vortex_buffer.rs+1%
2.9 µs2.9 µs
new_raw_prim_test_between[f32, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+1%
37.4 µs37.1 µs
take_map[(0.01, 0.05)]
vortex-array/benches/take_patches.rs+1%
200.4 µs198.7 µs
case_when_simple[1000]
vortex-array/benches/expr/case_when_bench.rs+1%
113.2 µs112.2 µs
take_map[(0.1, 0.05)]
vortex-array/benches/take_patches.rs+1%
764.3 µs758.9 µs
old_bp_prim_test_between[i16, 2048]
encodings/fastlanes/benches/compute_between.rs::bitpack+1%
127.4 µs126.6 µs
append_buffer_arrow_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
4.4 µs4.4 µs
old_raw_prim_test_between[f32, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+1%
120.4 µs119.7 µs
chunked_canonicalize_into[(10, 10000, 64, 4)]
encodings/fsst/benches/fsst_compress.rs+1%
28.5 ms28.4 ms
bitwise_and_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
5.1 µs5.1 µs
bitwise_or_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+1%
5.2 µs5.1 µs
new_raw_prim_test_between[u32, 2048]
encodings/fastlanes/benches/compute_between.rs::primitive+1%
36.7 µs36.5 µs
old_alp_prim_test_between[f32, 2048]
encodings/fastlanes/benches/compute_between.rs::alp+1%
141.5 µs140.8 µs
push_n_vortex_buffer[u32, 1024]
vortex-buffer/benches/vortex_buffer.rs+1%
5.4 µs5.4 µs
push_n_vortex_buffer[u32, 2048]
vortex-buffer/benches/vortex_buffer.rs0%
7.2 µs7.2 µs
decompress[runend_for_bp_u32]
vortex/benches/common_encoding_tree_throughput.rs0%
247.5 µs246.7 µs
old_raw_prim_test_between[u64, 16384]
encodings/fastlanes/benches/compute_between.rs::primitive0%
289.5 µs288.5 µs
Commits
Click on a commit to change the comparison rangeBase
develop
1c8667c
-10.2%
feat(cuda): hybrid dispatch for fused GPU decompression
c5a1ed5
3 days ago
by 0ax1