SweepANN:用于药物发现的GPU加速大K近似向量搜索
SweepANN: A GPU-Accelerated Large-K Approximate Vector Search for Drug Discovery
AI总结:
SweepANN是GPU加速的大K近似向量搜索方法,用于药物发现,在5亿分子库上,4块Blackwell GPU处理2.6万余口袋的平均召回率达99.6%,比同类方案快数倍且内存占用更低。
摘要:
DrugCLIP将小分子和蛋白质口袋置于同一空间,通过向量邻近性将全基因组药物发现转化为大K检索。针对包含5亿多个分子的库,预先固定了超过2万个口袋,每个口袋保留K=50万个候选分子,占集合的0.1%,而近似最近邻(ANN)基准中通常仅保留100个候选。未命中的候选永远不会被测试,因此相对于精确搜索,平均召回率必须达到99%。大尺寸的候选使得倒排文件(IVF)需要探测每个包含结果的列表,而图搜索则需要跟踪K个或更多候选,因此计算成本随K增长。在我们的CPU和GPU上,这两种索引家族均无法在不丧失其相对于扫描的大部分优势的情况下达到目标。SweepANN将压缩向量跨GPU分区,并扫描每个驻留分区,通过一次读取整个查询批次,用一次矩阵乘法对每个块进行评分。多个方案执行每个查询的K个答案的依赖于K的选择和合并,每个方案在压缩评分下返回精确的Top-K。窗口方案从采样块中保留每个查询的最佳K作为种子,仅将高于每个种子的最低分数的行(在GPU间共享一次)输入缓冲区。四块Blackwell GPU(RTX PRO 6000)在约61秒内(不包括库加载)处理全部26562个口袋,相对于精确FP32搜索的平均召回率为99.6%。DrugCLIP在其自身的实验中使用8块A100 GPU需约24小时。在5亿行数据上,窗口方案在相同内存下比SweepANN的分组方案快1.41倍。在2500万至5亿行数据以及K为1万至50万的范围内,所有达到召回目标的GPU IVF配置的驻留时间均为SweepANN的8.2至24倍。在DEEP1B的10亿向量跨8块GPU上,相对于SweepANN对未压缩FP32行的精确全评分扫描,窗口方案在K=10万和50万时分别将驻留时间缩短5.4倍和3.2倍,同时将每GPU峰值内存分别降低6.0倍和5.3倍,平均召回率分别损失1.0和0.7个百分点。
英文摘要:
DrugCLIP places small molecules and protein pockets in one space, turning genome-wide drug discovery into large-K retrieval by vector proximity. A campaign fixes over 20K pockets in advance for one library of over 500M molecules. Each pocket keeps K = 500K candidates, 0.1% of the collection, versus 100 in ANN benchmarks. Missed hits never get tested, so mean recall must reach 99% relative to exact search. Large answers make IVF probe every list holding a result and graph search track K or more candidates, so costs grow with K. On our CPUs and GPUs, neither index family reaches the target without losing most of its edge over scanning. SweepANN partitions compressed vectors across GPUs and scans each resident partition. One matrix multiplication scores each block for a whole query batch, reading it once. Several plans perform the K-dependent selection and merging of each query's K answers, each returning an exact top-K under compressed scoring. The window plan retains each query's best K from sampled blocks as its seed, and only rows above each seed's minimum score, shared once across GPUs, enter the buffers. Four Blackwell GPUs (RTX PRO 6000) answer all 26,562 pockets with a resident time of about 61 seconds, excluding library loading, and 99.6% mean recall relative to exact FP32 search. DrugCLIP reports roughly 24 hours with eight A100 GPUs in its own campaign. On 500M rows, the window plan runs 1.41x faster than SweepANN's grouped plan in the same memory. Across 25M-500M rows and K of 10K-500K, all GPU IVF configurations meeting the recall target take 8.2-24x SweepANN's resident time. On DEEP1B's 1B vectors across eight GPUs, against SweepANN's exact full-score scan of uncompressed FP32 rows, the window plan cuts resident time by 5.4x and 3.2x at K = 100K and 500K. It also cuts per-GPU peak memory by 6.0x and 5.3x, losing 1.0 and 0.7 mean-recall points.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。