公开(公告)号：US10033404B2

公开(公告)日：2018-07-24

申请号：US15639289

申请日：2017-06-30

Applicant: Intel Corporation

Inventor： Daniel F. Cutter ,  Vinodh Gopal ,  James D. Guilford

IPC: H03M7/38 ,  H03M7/30

Abstract: Technologies for efficiently compressing data with run detection include a compute device. The compute device is to produce a hash as a function of a symbol at a present position and a predefined number of symbols after the present position in an input stream, determine whether the symbol at the present position is part of a run, obtain, from a hash table, a chain of pointers to previous positions in the input stream associated with the hash, determine, as a function of whether the symbol is part of a run and to identify a matched string, a number of strings referenced by the chain of pointers to compare to a string associated with the present position in the input stream, and output, in response to an identification of a matched string, a reference to the matched string in a set of compressed output data.

公开(公告)号：US20180152201A1

公开(公告)日：2018-05-31

申请号：US15719735

申请日：2017-09-29

Applicant: Intel Corporation

Inventor： Vinodh Gopal ,  James D. Guilford ,  Kirk S. Yap ,  Daniel F. Cutter ,  Wajdi K. Feghali

IPC: H03M7/30

CPC classification number: G06F3/0641 ,  G06F3/0604 ,  G06F3/0608 ,  G06F3/0611 ,  G06F3/0613 ,  G06F3/0617 ,  G06F3/0647 ,  G06F3/065 ,  G06F3/0653 ,  G06F3/067 ,  G06F7/06 ,  G06F8/65 ,  G06F8/654 ,  G06F8/656 ,  G06F8/658 ,  G06F9/3851 ,  G06F9/3891 ,  G06F9/4401 ,  G06F9/4881 ,  G06F9/5038 ,  G06F9/505 ,  G06F9/544 ,  G06F11/0709 ,  G06F11/0751 ,  G06F11/079 ,  G06F11/1453 ,  G06F11/3006 ,  G06F11/3034 ,  G06F11/3055 ,  G06F11/3409 ,  G06F12/023 ,  G06F12/0284 ,  G06F12/0692 ,  G06F13/1652 ,  G06F15/80 ,  G06F17/30153 ,  G06F21/57 ,  G06F21/6218 ,  G06F21/73 ,  G06F21/76 ,  G06F2212/401 ,  G06F2212/402 ,  G06F2221/2107 ,  G06T1/20 ,  G06T1/60 ,  G06T9/005 ,  H01R13/4538 ,  H01R13/631 ,  H03K19/1731 ,  H03M7/3084 ,  H03M7/40 ,  H03M7/42 ,  H03M7/60 ,  H03M7/6011 ,  H03M7/6017 ,  H03M7/6029 ,  H04L9/0822 ,  H04L12/2881 ,  H04L12/4633 ,  H04L41/044 ,  H04L41/046 ,  H04L41/0816 ,  H04L41/0853 ,  H04L41/0896 ,  H04L41/12 ,  H04L41/142 ,  H04L43/04 ,  H04L43/06 ,  H04L43/08 ,  H04L43/0894 ,  H04L47/20 ,  H04L47/2441 ,  H04L49/104 ,  H04L61/2007 ,  H04L63/1425 ,  H04L67/10 ,  H04L67/1014 ,  H04L67/327 ,  H04L67/36 ,  H05K7/1452 ,  H05K7/1487

Abstract: Technologies for flexibly compressing data include a computing device having an accelerator complex that is to receive a compression job request and schedule the compression job request for one or more hardware compression resources of the accelerator complex. The accelerator complex is further to perform the compression job request with the one or more hardware compression resources in response to scheduling the compression job request and to communicate uncompressed data and compressed data with an I/O subsystem of the computing device in response to performing the compression job request. Other embodiments are described and claimed.

公开(公告)号：US20180026654A1

公开(公告)日：2018-01-25

申请号：US15395702

申请日：2016-12-30

Applicant: Intel Corporation

Inventor： Vinodh Gopal ,  James D. Guilford ,  Daniel F. Cutter ,  Kirk S. Yap

IPC: H03M7/40 ,  H03M7/30 ,  H04L29/06

CPC classification number: H04Q11/0005 ,  B25J15/0014 ,  B65G1/0492 ,  G02B6/3882 ,  G02B6/3893 ,  G02B6/3897 ,  G02B6/4292 ,  G02B6/4452 ,  G05D23/1921 ,  G05D23/2039 ,  G06F1/183 ,  G06F3/061 ,  G06F3/0611 ,  G06F3/0616 ,  G06F3/0619 ,  G06F3/0625 ,  G06F3/0631 ,  G06F3/0638 ,  G06F3/064 ,  G06F3/0647 ,  G06F3/0653 ,  G06F3/0658 ,  G06F3/0659 ,  G06F3/0664 ,  G06F3/0665 ,  G06F3/067 ,  G06F3/0673 ,  G06F3/0679 ,  G06F3/0683 ,  G06F3/0688 ,  G06F3/0689 ,  G06F8/65 ,  G06F9/4401 ,  G06F9/5016 ,  G06F9/5044 ,  G06F9/505 ,  G06F9/5072 ,  G06F9/5077 ,  G06F11/141 ,  G06F11/3414 ,  G06F12/0862 ,  G06F12/0893 ,  G06F12/10 ,  G06F12/109 ,  G06F12/1408 ,  G06F13/161 ,  G06F13/1668 ,  G06F13/1694 ,  G06F13/4022 ,  G06F13/4068 ,  G06F13/409 ,  G06F13/42 ,  G06F13/4282 ,  G06F15/8061 ,  G06F17/30949 ,  G06F2209/5019 ,  G06F2209/5022 ,  G06F2212/1008 ,  G06F2212/1024 ,  G06F2212/1041 ,  G06F2212/1044 ,  G06F2212/152 ,  G06F2212/202 ,  G06F2212/401 ,  G06F2212/402 ,  G06F2212/7207 ,  G06Q10/06 ,  G06Q10/06314 ,  G06Q10/087 ,  G06Q10/20 ,  G06Q50/04 ,  G07C5/008 ,  G08C17/02 ,  G08C2200/00 ,  G11C5/02 ,  G11C5/06 ,  G11C7/1072 ,  G11C11/56 ,  G11C14/0009 ,  H03M7/30 ,  H03M7/3084 ,  H03M7/3086 ,  H03M7/40 ,  H03M7/4031 ,  H03M7/4056 ,  H03M7/4081 ,  H03M7/6005 ,  H03M7/6023 ,  H04B10/25 ,  H04B10/2504 ,  H04L9/0643 ,  H04L9/14 ,  H04L9/3247 ,  H04L9/3263 ,  H04L12/2809 ,  H04L29/12009 ,  H04L41/024 ,  H04L41/046 ,  H04L41/0813 ,  H04L41/082 ,  H04L41/0896 ,  H04L41/12 ,  H04L41/145 ,  H04L41/147 ,  H04L41/5019 ,  H04L43/065 ,  H04L43/08 ,  H04L43/0817 ,  H04L43/0876 ,  H04L43/0894 ,  H04L43/16 ,  H04L45/02 ,  H04L45/52 ,  H04L47/24 ,  H04L47/765 ,  H04L47/782 ,  H04L47/805 ,  H04L47/82 ,  H04L47/823 ,  H04L49/15 ,  H04L49/25 ,  H04L49/357 ,  H04L49/45 ,  H04L49/555 ,  H04L67/02 ,  H04L67/10 ,  H04L67/1004 ,  H04L67/1008 ,  H04L67/1012 ,  H04L67/1014 ,  H04L67/1029 ,  H04L67/1034 ,  H04L67/1097 ,  H04L67/12 ,  H04L67/16 ,  H04L67/306 ,  H04L67/34 ,  H04L69/04 ,  H04L69/329 ,  H04Q1/04 ,  H04Q11/00 ,  H04Q11/0003 ,  H04Q11/0062 ,  H04Q11/0071 ,  H04Q2011/0037 ,  H04Q2011/0041 ,  H04Q2011/0052 ,  H04Q2011/0073 ,  H04Q2011/0079 ,  H04Q2011/0086 ,  H04Q2213/13523 ,  H04Q2213/13527 ,  H04W4/023 ,  H04W4/80 ,  H05K1/0203 ,  H05K1/181 ,  H05K5/0204 ,  H05K7/1418 ,  H05K7/1421 ,  H05K7/1422 ,  H05K7/1447 ,  H05K7/1461 ,  H05K7/1485 ,  H05K7/1487 ,  H05K7/1489 ,  H05K7/1491 ,  H05K7/1492 ,  H05K7/1498 ,  H05K7/2039 ,  H05K7/20709 ,  H05K7/20727 ,  H05K7/20736 ,  H05K7/20745 ,  H05K7/20836 ,  H05K13/0486 ,  H05K2201/066 ,  H05K2201/10121 ,  H05K2201/10159 ,  H05K2201/10189 ,  Y10S901/01

Abstract: Technologies for high-performance single-stream data compression include a computing device that updates an index data structure based on an input data stream. The input data stream is divided into multiple chunks. Each chunk has a predetermined length, such as 136 bytes, and overlaps the previous chunk by a predetermine amount, such as eight bytes. The computing device processes multiple chunks in parallel using the index data to generate multiple token streams. The tokens include literal tokens and reference tokens that refer to matching data from earlier in the input data stream. The computing device thus searches for matching data in parallel. The computing device merges the token streams to generate a single output token stream. The computing device may merge a pair of tokens from two different chunks to generate one or more synchronized tokens that are output to the output token stream. Other embodiments are described and claimed.

公开(公告)号：US20180011656A1

公开(公告)日：2018-01-11

申请号：US15663328

申请日：2017-07-28

Applicant: Intel Corporation

Inventor： James D. Guilford ,  Vinodh Gopal ,  Gilbert M. Wolrich ,  Daniel F. Cutter

IPC: G06F3/06 ,  H03M7/40

CPC classification number: G06F3/0638 ,  G06F3/0604 ,  G06F3/0608 ,  G06F3/0653 ,  G06F3/0673 ,  G06F8/52 ,  G06F12/1018 ,  G06F12/1027 ,  G06F2212/401 ,  G06F2212/68 ,  H03M7/3086 ,  H03M7/40

Abstract: A processing system is provided that includes a memory for storing an input bit stream and a processing logic, operatively coupled to the memory, to generate a first score based on: a first set of matching data related to a match between a first bit subsequence and a candidate bit subsequence within the input bit stream, and a first distance of the candidate bit subsequence from the first set of matching data. A second score is generated based on a second set of matching data related to a match between a second bit subsequence and the candidate bit subsequence, and a second distance of the candidate bit subsequence from the second set of matching data. A code to replace the first or second bit subsequence in an output bit stream is identified. Selection of the one of the bit subsequences to replace is based on a comparison of the scores.

公开(公告)号：US09825648B1

公开(公告)日：2017-11-21

申请号：US15277119

申请日：2016-09-27

Applicant: Intel Corporation

Inventor： Vinodh Gopal ,  James D. Guilford ,  Daniel F. Cutter

IPC: H03M7/34 ,  H03M7/30 ,  G06F3/06

CPC classification number: H03M7/3086 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/064 ,  G06F3/0656 ,  G06F3/0673 ,  H03M7/3068 ,  H03M7/6017

Abstract: In one embodiment, an apparatus comprises a first compression engine to receive a first compressed data block from a second compression engine that is to generate the first compressed data block by compressing a first plurality of repeated instances of data that each have a length greater than or equal to a first length. The first compression engine is further to compress a second plurality of repeated instances of data of the first compressed data block that each have a length greater than or equal to a second length, the second length being shorter than the first length, wherein each compressed repeated instance of the first and second pluralities of repeated instances comprises a location and length of a data instance that is repeated. The apparatus further comprises a memory buffer to store the compressed first and second plurality of repeated instances of data.

公开(公告)号：US20170109056A1

公开(公告)日：2017-04-20

申请号：US14886348

申请日：2015-10-19

Applicant: Intel Corporation

Inventor： Vinodh Gopal ,  James D. Guilford ,  Gilbert M. Wolrich ,  Daniel F. Cutter

IPC: G06F3/06

CPC classification number: G06F3/0608 ,  G06F3/064 ,  G06F3/0656 ,  G06F3/0661 ,  G06F3/0685 ,  G06F12/0292 ,  G06F12/0638 ,  G06F12/0684 ,  G06F12/0868 ,  G06F12/1018 ,  H03M7/3086 ,  H03M7/6011

Abstract: In an embodiment, a processor includes hardware processing cores, a cache memory, and a compression accelerator comprising a hash table memory. The compression accelerator is to: determine a hash value for input data to be compressed; read a first plurality of N location values stored in a hash table entry indexed by the hash value; perform a first set of string searches in parallel from a history buffer using the first plurality of N location values stored in the hash table entry; read a second plurality of N location values stored in a first overflow table entry indexed by a first overflow pointer included in the hash table entry; and perform a second set of string searches in parallel from the history buffer using the second plurality of N location values stored in the first overflow table entry. Other embodiments are described and claimed.

公开(公告)号：US09563579B2

公开(公告)日：2017-02-07

申请号：US13780117

申请日：2013-02-28

Applicant: Intel Corporation

Inventor： Daniel F. Cutter ,  Blaise Fanning ,  Ramadass Nagarajan ,  Ravishankar Iyer ,  Quang T. Le ,  Ravi Kolagotla ,  Ioannis T. Schoinas ,  Jose S. Niell

IPC: G06F13/00 ,  G06F9/00 ,  G06F13/16

CPC classification number: G06F13/00 ,  G06F9/00 ,  G06F13/1626 ,  Y02D10/14

Abstract: In an embodiment, a shared memory fabric is configured to receive memory requests from multiple agents, where at least some of the requests have an associated order identifier and a deadline value to indicate a maximum latency prior to completion of the memory request. Responsive to the requests, the fabric is to arbitrate between the requests based at least in part on the deadline values. Other embodiments are described and claimed.

Abstract translation: 在一个实施例中，共享存储器结构被配置为从多个代理接收存储器请求，其中至少一些请求具有相关联的顺序标识符和在存储器请求完成之前指示最大等待时间的最后期限值。 响应于请求，结构是至少部分地基于期限值来在请求之间进行仲裁。 描述和要求保护其他实施例。

公开(公告)号：US10367524B2

公开(公告)日：2019-07-30

申请号：US15496562

申请日：2017-04-25

Applicant: Intel Corporation

Inventor： Gregory B. Tucker ,  James D. Guilford ,  Daniel F. Cutter ,  Vinodh Gopal ,  Wajdi K. Feghali

IPC: G06K9/46 ,  H03M7/40

Abstract: Methods and apparatus are described by which data is compressed using semi-dynamic Huffman code generation. Embodiments generate symbol statistics over a portion of data. The symbol statistics are expanded to include all possible literals that could appear within the data. Any literal or reference added to the statistics may be given a frequency of one. The statistics are used to generate a semi-dynamic Huffman code. The entire data is then compressed using the semi-dynamic Huffman code.

公开(公告)号：US10120609B2

公开(公告)日：2018-11-06

申请号：US15720920

申请日：2017-09-29

Applicant: Intel Corporation

Inventor： James D. Guilford ,  Vinodh Gopal ,  Daniel F. Cutter

IPC: H03M7/30 ,  G06F3/06 ,  G06F17/30 ,  H03M7/40 ,  H04L12/26 ,  H04L12/813 ,  H04L12/851 ,  G06F11/07 ,  G06F11/30 ,  G06F11/34 ,  G06F7/06 ,  G06T9/00 ,  H03M7/42 ,  H04L12/28 ,  H04L12/46 ,  H04L29/12 ,  G06F13/16 ,  G06F21/62 ,  G06F21/76 ,  H03K19/173 ,  H04L9/08 ,  H04L12/933 ,  H04L29/08 ,  G06F9/38 ,  G06F9/48 ,  G06F9/50 ,  G06F12/06 ,  G06T1/20 ,  G06T1/60 ,  G06F9/54 ,  G06F8/656 ,  G06F8/658 ,  G06F8/654 ,  G06F9/4401 ,  H01R13/453 ,  H01R13/631 ,  H05K7/14 ,  G06F21/57 ,  G06F21/73 ,  G06F11/14 ,  G06F12/02 ,  H04L12/24 ,  H04L29/06 ,  G06F15/80

Abstract: A compute device to generate deterministic compressed streams receives a current string to be matched to one or more prior instances of the current string, the current string being located within an input buffer and the one or more prior instances located within a history buffer. The compute device identifies a limited subset of index memory designated for storing pointers to the prior instances, identifying a reserved slop region in the index memory, and compares the current string to a prior instance, locating the at least one prior instance using at least one pointer to the at least one prior instance. The at least one pointer is stored within the limited subset of the index memory, and the compute device also prohibits use of any pointers stored in the reserved slop region of the index memory. Other embodiments are described and claimed.

公开(公告)号：US20180159551A1

公开(公告)日：2018-06-07

申请号：US15816959

申请日：2017-11-17

Applicant: Intel Corporation

Inventor： Vinodh Gopal ,  James D. Guilford ,  Daniel F. Cutter

IPC: H03M7/30 ,  G06F3/06

CPC classification number: H03M7/3086 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/064 ,  G06F3/0656 ,  G06F3/0673 ,  H03M7/3068 ,  H03M7/6017

Abstract: In one embodiment, an apparatus comprises a first compression engine to receive a first compressed data block from a second compression engine that is to generate the first compressed data block by compressing a first plurality of repeated instances of data that each have a length greater than or equal to a first length. The first compression engine is further to compress a second plurality of repeated instances of data of the first compressed data block that each have a length greater than or equal to a second length, the second length being shorter than the first length, wherein each compressed repeated instance of the first and second pluralities of repeated instances comprises a location and length of a data instance that is repeated. The apparatus further comprises a memory buffer to store the compressed first and second plurality of repeated instances of data.