cuVS 基准测试#

conda create --name cuvs_benchmarks
conda activate cuvs_benchmarks

# to install GPU package:
conda install -c rapidsai -c conda-forge -c nvidia cuvs-ann-bench=<rapids_version> cuda-version=11.8*

# to install CPU package for usage in CPU-only systems:
conda install -c rapidsai -c conda-forge  cuvs-bench-cpu

docker pull rapidsai/cuvs-bench:24.10a-cuda12.0-py3.10 #substitute cuvs-bench for the exact desired container.

usage: get_dataset.py [-h] [--name NAME] [--dataset-path DATASET_PATH] [--normalize]

options:
  -h, --help            show this help message and exit
  --dataset DATASET     dataset to download (default: glove-100-angular)
  --dataset-path DATASET_PATH
                        path to download dataset (default: ${RAPIDS_DATASET_ROOT_DIR})
  --normalize           normalize cosine distance to inner product (default: False)

usage: __main__.py [-h] [--subset-size SUBSET_SIZE] [-k COUNT] [-bs BATCH_SIZE] [--dataset-configuration DATASET_CONFIGURATION] [--configuration CONFIGURATION] [--dataset DATASET]
                   [--dataset-path DATASET_PATH] [--build] [--search] [--algorithms ALGORITHMS] [--groups GROUPS] [--algo-groups ALGO_GROUPS] [-f] [-m SEARCH_MODE]

options:
  -h, --help            show this help message and exit
  --subset-size SUBSET_SIZE
                        the number of subset rows of the dataset to build the index (default: None)
  -k COUNT, --count COUNT
                        the number of nearest neighbors to search for (default: 10)
  -bs BATCH_SIZE, --batch-size BATCH_SIZE
                        number of query vectors to use in each query trial (default: 10000)
  --dataset-configuration DATASET_CONFIGURATION
                        path to YAML configuration file for datasets (default: None)
  --configuration CONFIGURATION
                        path to YAML configuration file or directory for algorithms Any run groups found in the specified file/directory will automatically override groups of the same name
                        present in the default configurations, including `base` (default: None)
  --dataset DATASET     name of dataset (default: glove-100-inner)
  --dataset-path DATASET_PATH
                        path to dataset folder, by default will look in RAPIDS_DATASET_ROOT_DIR if defined, otherwise a datasets subdirectory from the calling directory (default:
                        os.getcwd()/datasets/)
  --build
  --search
  --algorithms ALGORITHMS
                        run only comma separated list of named algorithms. If parameters `groups` and `algo-groups` are both undefined, then group `base` is run by default (default: None)
  --groups GROUPS       run only comma separated groups of parameters (default: base)
  --algo-groups ALGO_GROUPS
                        add comma separated <algorithm>.<group> to run. Example usage: "--algo-groups=cuvs_cagra.large,hnswlib.large" (default: None)
  -f, --force           re-run algorithms even if their results already exist (default: False)
  -m SEARCH_MODE, --search-mode SEARCH_MODE
                        run search in 'latency' (measure individual batches) or 'throughput' (pipeline batches and measure end-to-end) mode (default: throughput)
  -t SEARCH_THREADS, --search-threads SEARCH_THREADS
                        specify the number threads to use for throughput benchmark. Single value or a pair of min and max separated by ':'. Example --search-threads=1:4. Power of 2 values between 'min' and 'max' will be used. If only 'min' is
                        specified, then a single test is run with 'min' threads. By default min=1, max=<num hyper threads>. (default: None)
  -r, --dry-run         dry-run mode will convert the yaml config for the specified algorithms and datasets to the json format that's consumed by the lower-level c++ binaries and then print the command to run execute the benchmarks but
                        will not actually execute the command. (default: False)

usage: data_export.py [-h] [--dataset DATASET] [--dataset-path DATASET_PATH]

options:
  -h, --help            show this help message and exit
  --dataset DATASET     dataset to download (default: glove-100-inner)
  --dataset-path DATASET_PATH
                        path to dataset folder (default: ${RAPIDS_DATASET_ROOT_DIR})

usage:  [-h] [--dataset DATASET] [--dataset-path DATASET_PATH] [--output-filepath OUTPUT_FILEPATH] [--algorithms ALGORITHMS] [--groups GROUPS] [--algo-groups ALGO_GROUPS]
        [-k COUNT] [-bs BATCH_SIZE] [--build] [--search] [--x-scale X_SCALE] [--y-scale {linear,log,symlog,logit}] [--x-start X_START] [--mode {throughput,latency}]
        [--time-unit {s,ms,us}] [--raw]

options:
  -h, --help            show this help message and exit
  --dataset DATASET     dataset to plot (default: glove-100-inner)
  --dataset-path DATASET_PATH
                        path to dataset folder (default: /home/coder/cuvs/datasets/)
  --output-filepath OUTPUT_FILEPATH
                        directory for PNG to be saved (default: /home/coder/cuvs)
  --algorithms ALGORITHMS
                        plot only comma separated list of named algorithms. If parameters `groups` and `algo-groups are both undefined, then group `base` is plot by default
                        (default: None)
  --groups GROUPS       plot only comma separated groups of parameters (default: base)
  --algo-groups ALGO_GROUPS, --algo-groups ALGO_GROUPS
                        add comma separated <algorithm>.<group> to plot. Example usage: "--algo-groups=cuvs_cagra.large,hnswlib.large" (default: None)
  -k COUNT, --count COUNT
                        the number of nearest neighbors to search for (default: 10)
  -bs BATCH_SIZE, --batch-size BATCH_SIZE
                        number of query vectors to use in each query trial (default: 10000)
  --build
  --search
  --x-scale X_SCALE     Scale to use when drawing the X-axis. Typically linear, logit or a2 (default: linear)
  --y-scale {linear,log,symlog,logit}
                        Scale to use when drawing the Y-axis (default: linear)
  --x-start X_START     Recall values to start the x-axis from (default: 0.8)
  --mode {throughput,latency}
                        search mode whose Pareto frontier is used on the y-axis (default: throughput)
  --time-unit {s,ms,us}
                        time unit to plot when mode is latency (default: ms)
  --raw                 Show raw results (not just Pareto frontier) of mode arg (default: False)

# (1) prepare dataset.
python -m cuvs_bench.get_dataset --dataset deep-image-96-angular --normalize

# (2) build and search index
python -m cuvs_bench.run --dataset deep-image-96-inner --algorithms cuvs_cagra --batch-size 10 -k 10

# (3) export data
python -m cuvs_bench.data_export --dataset deep-image-96-inner

# (4) plot results
python -m cuvs_bench.plot --dataset deep-image-96-inner

mkdir -p datasets/deep-1B
# (1) prepare dataset
# download manually "Ground Truth" file of "Yandex DEEP"
# suppose the file name is deep_new_groundtruth.public.10K.bin
python -m cuvs_bench.split_groundtruth --groundtruth datasets/deep-1B/deep_new_groundtruth.public.10K.bin
# two files 'groundtruth.neighbors.ibin' and 'groundtruth.distances.fbin' should be produced

# (2) build and search index
python -m cuvs_bench.run --dataset deep-1B --algorithms cuvs_cagra --batch-size 10 -k 10

# (3) export data
python -m cuvs_bench.data_export --dataset deep-1B

# (4) plot results
python -m cuvs_bench.plot --dataset deep-1B