vortex-data
vortex
BlogDocsChangelog

GitHub Actions run

16 hours ago f2db37e ad/zstd-cuda pull_request

Compare

Base
Search a run

Head
feat: Zstd CUDA nvCOMP decompression
#6136
ad/zstd-cuda
16 hours ago
Wall TimeCPU SimulationMemory

Compare
Suggested base runs:
2559 total
decompress_kernel[1M]
vortex-cuda/benches/zstd_cuda.rs::benches::benchmark_zstd_cuda_decompress::ZSTD_cuda
388.6 µs
u32_FoR[10M]
vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u32
183.4 µs
u32_values_u8_codes[10M]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict_cuda::Dict_cuda_u32_u8
132.4 µs
u64_values_u8_codes[10M]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict_cuda::Dict_cuda_u64_u8
220.7 µs
u16_FoR[10M]
vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u16
7.9 µs
u32_values_u16_codes[10M]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict_cuda::Dict_cuda_u32_u16
153.4 µs
u64_values_u32_codes[10M]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict_cuda::Dict_cuda_u64_u32
279.5 µs
decompress_kernel[100M]
vortex-cuda/benches/zstd_cuda.rs::benches::benchmark_zstd_cuda_decompress::ZSTD_cuda
18.2 ms
u8_FoR[10M]
vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u8
9.2 µs
decompress_kernel[10M]
vortex-cuda/benches/zstd_cuda.rs::benches::benchmark_zstd_cuda_decompress::ZSTD_cuda
2 ms
u64_FoR[10M]
vortex-cuda/benches/for_cuda.rs::benches::benchmark_for_cuda::FoR_cuda_u64
349.9 µs
decompress_bitpacking_late_filter[i32, 0.05]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
374.5 µs
decompress_bitpacking_late_filter[i32, 0.03]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
337 µs
decompress_bitpacking_late_filter[i32, 0.01]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
298.9 µs
decompress_bitpacking_early_filter[i16, 0.005]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
80 µs
decompress_bitpacking_early_filter[i16, 0.01]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
112.3 µs
decompress_bitpacking_early_filter[i16, 0.0105]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
114.2 µs
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs
29.3 µs
decompress_bitpacking_late_filter[i32, 0.02]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
318.4 µs
decompress_bitpacking_late_filter[i32, 0.04]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
355.8 µs
patched_take_10k_adversarial
encodings/fastlanes/benches/bitpacking_take.rs
2 ms
patched_take_10_stratified
encodings/fastlanes/benches/bitpacking_take.rs
28 µs
decompress_bitpacking_late_filter[i64, 0.02]
encodings/fastlanes/benches/bitpacking_decompress_selection.rs
520.3 µs
patched_take_10k_contiguous_patches
encodings/fastlanes/benches/bitpacking_take.rs
2.1 ms
patched_take_10k_contiguous_not_patches
encodings/fastlanes/benches/bitpacking_take.rs
1.2 ms
© 2026 CodSpeed Technology
Home Terms Privacy Docs