wip[cuda]: datafusion backed GPU scan
#6246Comparing
ji/df-cuda-scan
(fdd9e5e
) withdevelop
(941edaa
)-33%
- Regression
- 1
- Untouched
- 1137
- Skipped
- 1265
- Archived
- 119
Benchmarks
2522 total
chunked_bool_into_canonical[(1000, 10)]
vortex-array/benches/chunk_array_builder.rs-33%
43 µs64.2 µs
true_count_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+6%
1.1 µs1 µs
decompress[u8, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+5%
10.1 µs9.7 µs
slice_vortex_buffer[16384]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
1.4 µs1.3 µs
slice_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
1.4 µs1.3 µs
slice_vortex_buffer[65536]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
1.4 µs1.3 µs
slice_vortex_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
1.4 µs1.3 µs
slice_vortex_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
1.4 µs1.3 µs
binary_search_std
vortex-array/benches/search_sorted.rs+4%
741.4 ns712.2 ns
decode_primitives[u8, (1000, 2)]
vortex-array/benches/dict_compress.rs+4%
19.2 µs18.5 µs
decompress[u8, (1000, 16)]
encodings/runend/benches/run_end_compress.rs+4%
12 µs11.5 µs
decompress[u16, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+3%
11.4 µs11 µs
decompress[u8, (10000, 1024)]
encodings/runend/benches/run_end_compress.rs+3%
15.2 µs14.8 µs
decompress[u64, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+3%
13.5 µs13.2 µs
bitwise_and_arrow_buffer[1024]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
3.3 µs3.2 µs
decompress[u8, (10000, 256)]
encodings/runend/benches/run_end_compress.rs+3%
16.6 µs16.2 µs
decompress[u8, (1000, 4)]
encodings/runend/benches/run_end_compress.rs+3%
17.4 µs17 µs
decompress[u16, (1000, 16)]
encodings/runend/benches/run_end_compress.rs+2%
14.4 µs14 µs
bitwise_and_arrow_buffer[2048]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
3.9 µs3.8 µs
value_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.3 µs1.3 µs
decompress[u64, (1000, 16)]
encodings/runend/benches/run_end_compress.rs+2%
17 µs16.6 µs
push_n_vortex_buffer[u16, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
2.7 µs2.6 µs
set_indices_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+2%
1.3 µs1.3 µs
decompress[u32, (1000, 256)]
encodings/runend/benches/run_end_compress.rs+2%
12 µs11.8 µs
push_n_vortex_buffer[u64, 128]
vortex-buffer/benches/vortex_buffer.rs+2%
2.9 µs2.8 µs
Commits
Click on a commit to change the comparison rangeBase
develop
941edaa
-33.03%
wip
fdd9e5e
15 hours ago
by joseph-isaacs