公开(公告)号：US09792117B2

公开(公告)日：2017-10-17

申请号：US14023064

申请日：2013-09-10

Applicant: Oracle International Corporation

Inventor： Amit Ganesh ,  Shasank K. Chavan ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Michael J. Gleeson ,  Allison L. Holloway ,  Roger Macnicol

IPC: G06F15/00 ,  G06F7/38 ,  G06F9/00 ,  G06F9/44 ,  G06F9/30 ,  G06F17/30

CPC classification number: G06F9/30036 ,  G06F9/30032 ,  G06F17/30315

Abstract: A method and apparatus for efficiently processing data in various formats in a single instruction multiple data (“SIMD”) architecture is presented. Specifically, a method to unpack a fixed-width bit values in a bit stream to a fixed width byte stream in a SIMD architecture is presented. A method to unpack variable-length byte packed values in a byte stream in a SIMD architecture is presented. A method to decompress a run length encoded compressed bit-vector in a SIMD architecture is presented. A method to return the offset of each bit set to one in a bit-vector in a SIMD architecture is presented. A method to fetch bits from a bit-vector at specified offsets relative to a base in a SIMD architecture is presented. A method to compare values stored in two SIMD registers is presented.

公开(公告)号：US09430390B2

公开(公告)日：2016-08-30

申请号：US14337142

申请日：2014-07-21

Applicant: Oracle International Corporation

Inventor： Niloy Mukherjee ,  Amit Ganesh ,  Vineet Marwah ,  Jesse Kamp

IPC: G06F12/08 ,  G06F17/30 ,  G06F15/78 ,  G06F12/10 ,  G06F3/06

CPC classification number: G06F17/30315 ,  G06F3/0604 ,  G06F3/064 ,  G06F3/065 ,  G06F3/0689 ,  G06F12/0815 ,  G06F12/1018 ,  G06F15/78 ,  G06F15/8007 ,  G06F15/8076 ,  G06F15/8084 ,  G06F17/30312 ,  G06F17/30377 ,  G06F17/30477 ,  G06F17/30595 ,  G06F2003/0697 ,  G06F2212/1021 ,  G06F2212/1032 ,  G06F2212/2542 ,  G06F2212/313

Abstract: Techniques are provided for managing in-memory space and objects. In one embodiment, a set of in-memory objects are maintained within an area in volatile memory that is accessible to a database server. An in-memory object in this context includes a set of one or more in-memory segments where each respective in-memory segment includes a set of in-memory extents and each respective in-memory extent is a contiguous chunk of memory from the area in volatile memory that is accessible to the database server. The area in volatile memory is managed as a set of stripes, where each stripe is a contiguous chunk of in-memory extents. Stripe control blocks are used to locate free in-memory extents for allocation and registration with an in-memory segment.

Abstract translation: 提供了管理内存空间和对象的技术。 在一个实施例中，一组存储器内对象被维护在数据库服务器可访问的易失性存储器中的区域内。 在该上下文中的存储器内对象包括一组一个或多个内存中段，其中每个相应的内存段中包括一组存储器内区段，并且每个相应的存储器内区段是来自该区域的连续存储块 在数据库服务器可访问的易失性存储器中。 易失性存储器中的区域作为一组条带进行管理，其中每个条带是内存区段中的连续块。 条带控制块用于定位可用的存储器内区段，以便与内存段分配和注册。

公开(公告)号：US20160085781A1

公开(公告)日：2016-03-24

申请号：US14955368

申请日：2015-12-01

Applicant: Oracle International Corporation

Inventor： Lawrence J. Ellison ,  Amit Ganesh ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Shasank K. Chavan ,  Michael J. Gleeson ,  Allison L. Holloway ,  Manosiz Bhattacharyya

IPC: G06F17/30 ,  G06F9/38

CPC classification number: G06F17/30315 ,  G06F9/3887 ,  G06F17/30339 ,  G06F17/30595

Abstract: Techniques are provided for more efficiently using the bandwidth of the I/O path between a CPU and volatile memory during the performance of database operation. Relational data from a relational table is stored in volatile memory as column vectors, where each column vector contains values for a particular column of the table. A binary-comparable format may be used to represent each value within a column vector, regardless of the data type associated with the column. The column vectors may be compressed and/or encoded while in volatile memory, and decompressed/decoded on-the-fly within the CPU. Alternatively, the CPU may be designed to perform operations directly on the compressed and/or encoded column vector data. In addition, techniques are described that enable the CPU to perform vector processing operations on the column vector values.

公开(公告)号：US09292564B2

公开(公告)日：2016-03-22

申请号：US14337179

申请日：2014-07-21

Applicant: Oracle International Corporation

Inventor： Jesse Kamp ,  Amit Ganesh ,  Vineet Marwah ,  Vivekanandhan Raja ,  Tirthankar Lahiri ,  Allison L. Holloway ,  Sanket Hase ,  Shasank K. Chavan ,  Niloy Mukherjee ,  Teck Hua Lee ,  Michael J. Gleeson ,  Krishna Kunchithapadam

IPC: G06F17/30

CPC classification number: G06F17/30377 ,  G06F3/0619 ,  G06F3/065 ,  G06F3/0665 ,  G06F3/0689 ,  G06F11/2058 ,  G06F17/30315 ,  G06F17/30442 ,  G06F17/30575 ,  G06F17/30581 ,  G06F2201/80 ,  G06F2201/855

Abstract: Techniques are provided for maintaining data persistently in one format, but making that data available to a database server in more than one format. For example, one of the formats in which the data is made available for query processing is based on the on-disk format, while another of the formats in which the data is made available for query processing is independent of the on-disk format. Data that is in the format that is independent of the disk format may be maintained exclusively in volatile memory to reduce the overhead associated with keeping the data in sync with the on-disk format copies of the data.

Abstract translation: 提供的技术用于以一种格式持续保持数据，但使数据库可以以多种格式提供给数据库服务器。 例如，数据可用于查询处理的格式之一是基于磁盘格式，而数据可用于查询处理的另一种格式与磁盘格式无关。 独立于磁盘格式的格式的数据可以专门保存在易失性存储器中，以减少与保持数据与数据的磁盘格式副本同步的开销。

公开(公告)号：US20140074805A1

公开(公告)日：2014-03-13

申请号：US14079507

申请日：2013-11-13

Applicant: Oracle International Corporation

Inventor： Vikram Kapoor ,  Amit Ganesh ,  Jesse Kamp ,  Sachin Kulkarni ,  Vineet Marwah ,  Kam Shergill ,  Roger Macnicol ,  Manosiz Bhattacharyya

IPC: G06F17/30

CPC classification number: G06F16/1744 ,  G06F16/24561 ,  G06F16/902

Abstract: A database server stores compressed units in data blocks of a database. A table (or data from a plurality of rows thereof) is first compressed into a “compression unit” using any of a wide variety of compression techniques. The compression unit is then stored in one or more data block rows across one or more data blocks. As a result, a single data block row may comprise compressed data for a plurality of table rows, as encoded within the compression unit. Storage of compression units in data blocks maintains compatibility with existing data block-based databases, thus allowing the use of compression units in preexisting databases without modification to the underlying format of the database. The compression units may, for example, co-exist with uncompressed tables. Various techniques allow a database server to optimize access to data in the compression unit, so that the compression is virtually transparent to the user.

Abstract translation: 数据库服务器将压缩单位存储在数据库的数据块中。 使用各种各样的压缩技术中的任一种，首先将表（或其多行的数据）压缩为“压缩单位”。 然后，压缩单元被存储在跨越一个或多个数据块的一个或多个数据块行。 结果，单个数据块行可以包括在压缩单元内编码的多个表行的压缩数据。 数据块中的压缩单元的存储与现有的基于数据块的数据库保持兼容，从而允许在预先存在的数据库中使用压缩单元，而无需修改数据库的底层格式。 压缩单元可以例如与未压缩的表共存。 各种技术允许数据库服务器优化对压缩单元中的数据的访问，使得压缩对于用户实际上是透明的。

公开(公告)号：US20140013077A1

公开(公告)日：2014-01-09

申请号：US14023249

申请日：2013-09-10

Applicant: Oracle International Corporation

Inventor： Amit Ganesh ,  Shasank K. Chavan ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Michael J. Gleeson ,  Allison L. Holloway ,  Roger Macnicol

IPC: G06F15/80

CPC classification number: G06F15/8007 ,  G06F17/30315

Abstract: A method and apparatus for efficiently processing data in various formats in a single instruction multiple data (“SIMD”) architecture is presented. Specifically, a method to unpack a fixed-width bit values in a bit stream to a fixed width byte stream in a SIMD architecture is presented. A method to unpack variable-length byte packed values in a byte stream in a SIMD architecture is presented. A method to decompress a run length encoded compressed bit-vector in a SIMD architecture is presented. A method to return the offset of each bit set to one in a bit-vector in a SIMD architecture is presented. A method to fetch bits from a bit-vector at specified offsets relative to a base in a SIMD architecture is presented. A method to compare values stored in two SIMD registers is presented.

公开(公告)号：US20130275473A1

公开(公告)日：2013-10-17

申请号：US13916284

申请日：2013-06-12

Applicant: Oracle International Corporation

Inventor： Lawrence J. Ellison ,  Amit Ganesh ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Shasank K. Chavan ,  Michael J. Gleeson ,  Allison L. Holloway ,  Manosiz Bhattacharyya

IPC: G06F17/30

CPC classification number: G06F17/30315 ,  G06F9/3887 ,  G06F17/30339 ,  G06F17/30595

Abstract: Techniques are provided for more efficiently using the bandwidth of the I/O path between a CPU and volatile memory during the performance of database operation. Relational data from a relational table is stored in volatile memory as column vectors, where each column vector contains values for a particular column of the table. A binary-comparable format may be used to represent each value within a column vector, regardless of the data type associated with the column. The column vectors may be compressed and/or encoded while in volatile memory, and decompressed/decoded on-the-fly within the CPU. Alternatively, the CPU may be designed to perform operations directly on the compressed and/or encoded column vector data. In addition, techniques are described that enable the CPU to perform vector processing operations on the column vector values.

Abstract translation: 在执行数据库操作期间，提供了技术来更有效地使用CPU和易失性存储器之间的I / O路径的带宽。 来自关系表的关系数据作为列向量存储在易失性存储器中，其中每个列向量包含表的特定列的值。 可以使用二进制可比较的格式来表示列向量中的每个值，而不管与列相关联的数据类型如何。 列向量可以在易失性存储器中被压缩和/或编码，并且在CPU内部实时解压缩/解码。 或者，CPU可以被设计为直接对压缩和/或编码的列向量数据执行操作。 另外，描述使CPU能够对列向量值执行向量处理操作的技术。

公开(公告)号：US08521788B2

公开(公告)日：2013-08-27

申请号：US13708060

申请日：2012-12-07

Applicant: Oracle International Corporation

Inventor： Lawrence J. Ellison ,  Amit Ganesh ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Shasank K. Chavan ,  Michael J. Gleeson ,  Allison L. Holloway ,  Manosiz Bhattacharyya

IPC: G06F7/00

CPC classification number: G06F17/30315 ,  G06F9/3887 ,  G06F17/30339 ,  G06F17/30595

Abstract: Techniques are provided for more efficiently using the bandwidth of the I/O path between a CPU and volatile memory during the performance of database operation. Relational data from a relational table is stored in volatile memory as column vectors, where each column vector contains values for a particular column of the table. A binary-comparable format may be used to represent each value within a column vector, regardless of the data type associated with the column. The column vectors may be compressed and/or encoded while in volatile memory, and decompressed/decoded on-the-fly within the CPU. Alternatively, the CPU may be designed to perform operations directly on the compressed and/or encoded column vector data. In addition, techniques are described that enable the CPU to perform vector processing operations on the column vector values.

公开(公告)号：US20130151568A1

公开(公告)日：2013-06-13

申请号：US13708060

申请日：2012-12-07

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Lawrence J. Ellison ,  Amit Ganesh ,  Vineet Marwah ,  Jesse Kamp ,  Anindya C. Patthak ,  Shasank K. Chavan ,  Michael J. Gleeson ,  Allison L. Holloway ,  Manosiz Bhattacharyya

IPC: G06F17/30

CPC classification number: G06F17/30315 ,  G06F9/3887 ,  G06F17/30339 ,  G06F17/30595

Abstract: Techniques are provided for more efficiently using the bandwidth of the I/O path between a CPU and volatile memory during the performance of database operation. Relational data from a relational table is stored in volatile memory as column vectors, where each column vector contains values for a particular column of the table. A binary-comparable format may be used to represent each value within a column vector, regardless of the data type associated with the column. The column vectors may be compressed and/or encoded while in volatile memory, and decompressed/decoded on-the-fly within the CPU. Alternatively, the CPU may be designed to perform operations directly on the compressed and/or encoded column vector data. In addition, techniques are described that enable the CPU to perform vector processing operations on the column vector values.