公开(公告)号：US20150039852A1

公开(公告)日：2015-02-05

申请号：US13956356

申请日：2013-08-01

Applicant: Oracle International Corporation

Inventor： Rajkumar Sen ,  Sam Idicula ,  Nipun Agarwal

IPC: G06F9/30

CPC classification number: G06F17/3033 ,  G06F9/30021 ,  G06F9/30032 ,  G06F9/30036 ,  G06F17/30466

Abstract: Techniques for performing database operations using vectorized instructions are provided. In one technique, data compaction is performed using vectorized instructions to identify a shuffle mask based on matching bits and update an output array based on the shuffle mask and an input array. In a related technique, a hash table probe involves using vectorized instructions to determine whether each key in one or more hash buckets matches a particular input key.

Abstract translation: 提供了使用向量化指令执行数据库操作的技术。 在一种技术中，使用向量化指令执行数据压缩，以基于匹配比特来识别洗牌掩码，并且基于随机播放掩码和输入阵列更新输出阵列。 在相关技术中，散列表探测器涉及使用向量化指令来确定一个或多个散列桶中的每个密钥是否与特定输入密钥匹配。

公开(公告)号：US08849871B2

公开(公告)日：2014-09-30

申请号：US13645030

申请日：2012-10-04

Applicant: Oracle International Corporation

Inventor： Sam Idicula ,  Sabina Petride ,  Nipun Agarwal ,  Eric Sedlar

IPC: G06F7/00 ,  G06F17/30

CPC classification number: G06F17/30289 ,  G06F17/30498 ,  G06F17/30598

Abstract: A system and method for allocating join processing between and RDBMS and an assisting cluster. In one embodiment, the method estimates a cost of performing the join completely in the RDBMS and the cost of performing the join with the assistance of a cluster coupled to the RDBMS. The cost of performing the join with the assistance of the cluster includes estimating a cost of a broadcast join or a partition join depending on the sizes of the tables. Additional costs are incurred when there is a blocking operation, which prevents the cluster from being able to process portions of the join. The RDBMS also maintains transactional consistency when the cluster performs some or all of the join processing.

Abstract translation: 用于在RDBMS和辅助群集之间分配连接处理的系统和方法。 在一个实施例中，该方法估计在RDBMS中完全执行连接的成本以及在耦合到RDBMS的集群的协助下执行连接的成本。 在集群的帮助下执行连接的成本包括根据表的大小来估计广播联接或分区连接的成本。 当有阻塞操作时会产生额外的成本，从而防止集群处理部分连接。 当集群执行部分或全部连接处理时，RDBMS还维护事务一致性。

公开(公告)号：US11790242B2

公开(公告)日：2023-10-17

申请号：US16166039

申请日：2018-10-19

Applicant: Oracle International Corporation

Inventor： Sandeep Agrawal ,  Venkatanathan Varadarajan ,  Sam Idicula ,  Nipun Agarwal

IPC: G06N3/126 ,  G06N20/00

CPC classification number: G06N3/126 ,  G06N20/00

Abstract: Techniques are described for generating and applying mini-machine learning variants of machine learning algorithms to save computational resources in tuning and selection of machine learning algorithms. In an embodiment, at least one of the hyper-parameter values for a reference variant is modified to a new hyper-parameter value thereby generating a new variant of machine learning algorithm from the reference variant of machine learning algorithm. A performance score is determined for the new variant of machine learning algorithm using a training dataset, the performance score representing the accuracy of the new machine learning model for the training dataset. By performing training of the new variant of machine learning algorithm with the training data set, a cost metric of the new variant of machine learning algorithm is measured by measuring usage the used computing resources for the training. Based on the cost metric of the new variant of machine learning algorithm and comparing the performance score for the new and reference variants, the system determines whether the modified reference machine algorithm is the mini-machine learning algorithm that is computationally less costly than the reference variant of machine learning algorithm but closely tracks the accuracy thereof.

公开(公告)号：US11615265B2

公开(公告)日：2023-03-28

申请号：US16547312

申请日：2019-08-21

Applicant: Oracle International Corporation

Inventor： Tomas Karnagel ,  Sam Idicula ,  Hesam Fathi Moghadam ,  Nipun Agarwal

IPC: G06F16/00 ,  G06K9/62 ,  G06N20/00

Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer ranks features of datasets of a training corpus. For each dataset and for each landmark percentage, a target ML model is configured to receive only a highest ranking landmark percentage of features, and a landmark accuracy achieved by training the ML model with the dataset is measured. Based on the landmark accuracies and meta-features values of the dataset, a respective training tuple is generated for each dataset. Based on all of the training tuples, a regressor is trained to predict an optimal amount of features for training the target ML model.

公开(公告)号：US11567937B2

公开(公告)日：2023-01-31

申请号：US17318972

申请日：2021-05-12

Applicant: Oracle International Corporation

Inventor： Sam Idicula ,  Tomas Karnagel ,  Jian Wen ,  Seema Sundara ,  Nipun Agarwal ,  Mayur Bency

IPC: G06F16/2453 ,  G06N20/00 ,  G06F16/21 ,  G06N20/20

Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters. The optimal set of configuration parameter values is automatically applied for the given workload.

公开(公告)号：US20210312014A1

公开(公告)日：2021-10-07

申请号：US17349817

申请日：2021-06-16

Applicant: Oracle International Corporation

Inventor： Gaurav Chadha ,  Sam Idicula ,  Sandeep Agrawal ,  Nipun Agarwal

IPC: G06F17/16 ,  G06F7/523 ,  G06F17/12

Abstract: Techniques are described herein for performing efficient matrix multiplication in architectures with scratchpad memories or associative caches using asymmetric allocation of space for the different matrices. The system receives a left matrix and a right matrix. In an embodiment, the system allocates, in a scratchpad memory, asymmetric memory space for tiles for each of the two matrices as well as a dot product matrix. The system proceeds with then performing dot product matrix multiplication involving the tiles of the left and the right matrices, storing resulting dot product values in corresponding allocated dot product matrix tiles. The system then proceeds to write the stored dot product values from the scratchpad memory into main memory.

公开(公告)号：US11120368B2

公开(公告)日：2021-09-14

申请号：US16137719

申请日：2018-09-21

Applicant: Oracle International Corporation

Inventor： Venkatanathan Varadarajan ,  Sam Idicula ,  Sandeep Agrawal ,  Nipun Agarwal

IPC: G06F3/00 ,  G06N20/00 ,  G06F9/48 ,  G06N3/08 ,  G06N3/04 ,  G06N5/00 ,  G06N7/00 ,  G06N20/20 ,  G06N20/10 ,  G06N3/12

Abstract: Herein are techniques for automatic tuning of hyperparameters of machine learning algorithms. System throughput is maximized by horizontally scaling and asynchronously dispatching the configuration, training, and testing of an algorithm. In an embodiment, a computer stores a best cost achieved by executing a target model based on best values of the target algorithm's hyperparameters. The best values and their cost are updated by epochs that asynchronously execute. Each epoch has asynchronous costing tasks that explore a distinct hyperparameter. Each costing task has a sample of exploratory values that differs from the best values along the distinct hyperparameter. The asynchronous costing tasks of a same epoch have different values for the distinct hyperparameter, which accomplishes an exploration. In an embodiment, an excessive update of best values or best cost creates a major epoch for exploration in a subspace that is more or less unrelated to other epochs, thereby avoiding local optima.

公开(公告)号：US11061902B2

公开(公告)日：2021-07-13

申请号：US16298837

申请日：2019-03-11

Applicant: Oracle International Corporation

Inventor： Sam Idicula ,  Tomas Karnagel ,  Jian Wen ,  Seema Sundara ,  Nipun Agarwal ,  Mayur Bency

IPC: G06F16/2453 ,  G06N20/00 ,  G06F16/21 ,  G06N20/20

Abstract: Embodiments implement a prediction-driven, rather than a trial-driven, approach to automate database configuration parameter tuning for a database workload. This approach uses machine learning (ML) models to test performance metrics resulting from application of particular database parameters to a database workload, and does not require live trials on the DBMS managing the workload. Specifically, automatic configuration (AC) ML models are trained, using a training corpus that includes information from workloads being run by DBMSs, to predict performance metrics based on workload features and configuration parameter values. The trained AC-ML models predict performance metrics resulting from applying particular configuration parameter values to a given database workload being automatically tuned. Based on correlating changes to configuration parameter values with changes in predicted performance metrics, an optimization algorithm is used to converge to an optimal set of configuration parameters. The optimal set of configuration parameter values is automatically applied for the given workload.

公开(公告)号：US10706055B2

公开(公告)日：2020-07-07

申请号：US15092483

申请日：2016-04-06

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Gong Zhang ,  Sam Idicula ,  Michael Duller ,  Nitin Kunal

IPC: G06F7/00 ,  G06F16/2455 ,  G06F7/16

Abstract: Techniques are described for executing an analytical query with a top-N clause. In an embodiment, a stream of tuples are received by each of the processing units from a data source identified in the query. The processing unit uses a portion of a received tuple to identify the partition that the tuple is assigned to. For each partition, the processing unit maintains a top-N data store that stores an N number of received tuples that match the criteria of top N tuples according to the query. The received tuple is compared to the N number of tuples to determine whether to store the received tuple and discard an already stored tuple, or to discard the received tuple. After all the tuples have been similarly processed by the processing units, all the top-N data stores for each partition are merged, yielding the top N number of tuples for each partition to return as a result of the query.

公开(公告)号：US10685021B2

公开(公告)日：2020-06-16

申请号：US15791696

申请日：2017-10-24

Applicant: Oracle International Corporation

Inventor： Pit Fender ,  Sam Idicula ,  Nipun Agarwal ,  Benjamin Schlegel

IPC: G06F16/00 ,  G06F16/2453 ,  G06F8/41

Abstract: Techniques are described herein for introducing transcode operators into a generated operator tree during query processing. Setting up the transcode operators with correct encoding type at runtime is performed by inferring correct encoding type information during compile time. The inference of the correct encoding type information occurs in three phases during compile time: the first phase involves collecting, consolidating, and propagating the encoding-type information of input columns up the expression tree. The second phase involves pushing the encoding-type information down the tree for nodes in the expression tree that do not yet have any encoding-type assigned. The third phase involves determining which inputs to the current relational operator need to be pre-processed by a transcode operator.