-
公开(公告)号：US20240168739A1
公开(公告)日：2024-05-23
申请号：US18058035
申请日：2022-11-22
Applicant: Red Hat, Inc.
Inventor： Ralph Judy Bean , Simon Cobden Baird , Zoran Regvart , Cuiping Huo , Joseph James Stuart , Christophe Giuseppe Augello , Brandon Caton , Luiz Renato Ferreira Carvalho , Robert Garland Nester
CPC classification number: G06F8/4452 , G06F8/63 , G06F8/65
Abstract: A system, method, and computer readable medium receive a container image and an attestation log. The container image is built from a build pipeline and the attestation log includes information corresponding to tasks utilized by the build pipeline to build the container image. The system, method, and computer readable medium compare the information in the attestation log with policies that includes build pipeline requirements. The system, method, and computer readable medium release the container image to a destination based on the comparison indicating that tasks utilized by the build pipeline to build the container image meet the build pipeline requirements.
-
公开(公告)号：US20230315411A1
公开(公告)日：2023-10-05
申请号：US18130642
申请日：2023-04-04
Applicant: SambaNova Systems, Inc.
Inventor： Fei WANG , Weihang FAN , David Alan KOEPLINGER
IPC: G06F8/41
CPC classification number: G06F8/4452 , G06F8/433 , G06F8/452
Abstract: A method for improving throughput in a reconfigurable computing system includes detecting, in an algebraic representation of a computing task for a reconfigurable dataflow processor, an outer meta-pipeline loop, detecting an inner meta-pipeline loop nested within the outer meta-pipeline loop, and determining that the inner meta-pipeline loop and the outer meta-pipeline loop each conduct a common operation. The method also includes fusing the common operation for the inner meta-pipeline loop and the outer meta-pipeline loop into a single operation within the inner meta-pipeline loop. The instances of the common operation may be fused if the output of a first instance of the common operation is the source for a second instance of the common operation. Examples of the common operation include an accumulator operation, a re-read operation, and a temporal (chip buffer synchronized) operation such as a temporal concatenation operation and a temporal slicing operation.
-
公开(公告)号：US20230267210A1
公开(公告)日：2023-08-24
申请号：US17652218
申请日：2022-02-23
Applicant: Dell Products L.P.
Inventor： Nicole Reineke , Stephen J. Todd , Trevor Scott Conn
CPC classification number: G06F21/57 , G06F8/447 , G06F8/4452 , G06F2221/033 , G06F2221/2101
Abstract: A data confidence fabric for generating data confidence scores for a build pipeline is disclosed. Confidence scores are generated for data or jobs in a build pipeline. The scores may be combined into a final confidence score that reflects a confidence in the artifact generated by the pipeline and in the pipeline. A user or infrastructure may or may not perform the artifact based on the associated confidence score.
-
4.发明公开公开(公告)号：US20230153087A1
公开(公告)日：2023-05-18
申请号：US18097420
申请日：2023-01-16
Applicant: Kemal Ebcioglu , Emre Kultursay
Inventor： Kemal Ebcioglu , Emre Kultursay
IPC: G06F8/41 , G06F8/40 , G06F9/52 , G06F15/173 , G06F30/30 , G06F30/392
CPC classification number: G06F8/4452 , G06F8/40 , G06F9/52 , G06F15/17381 , G06F8/452 , G06F30/30 , G06F30/392 , G06F2115/10
Abstract: The invention comprises (i) a compilation method for automatically converting a single-threaded software program into an application-specific supercomputer, and (ii) the supercomputer system structure generated as a result of applying this method. The compilation method comprises: (a) Converting an arbitrary code fragment from the application into customized hardware whose execution is functionally equivalent to the software execution of the code fragment; and (b) Generating interfaces on the hardware and software parts of the application, which (i) Perform a software-to-hardware program state transfer at the entries of the code fragment; (ii) Perform a hardware-to-software program state transfer at the exits of the code fragment; and (iii) Maintain memory coherence between the software and hardware memories. If the resulting hardware design is large, it is divided into partitions such that each partition can fit into a single chip. Then, a single union chip is created which can realize any of the partitions.
-
5.发明授权公开(公告)号：US09760352B2
公开(公告)日：2017-09-12
申请号：US14799625
申请日：2015-07-15
Applicant: FUJITSU LIMITED
Inventor： Shusaku Nakashima , Toshiya Naito
CPC classification number: G06F8/443 , G06F8/4452 , G06F11/3409 , G06F11/3419 , G06F11/3466 , G06F2201/81 , G06F2201/865
Abstract: A program optimization method, executed by an arithmetic processing device, includes collecting profile information including a runtime analysis result by causing a computer to execute an original program to be optimized, calculating a calculation wait time based on the profile information, and generating a tuned-up program, when the calculation wait time is longer than a first threshold, by inserting an SIMD operation control line that performs an SIMD operation for an instruction in IF statement in the loop when an SIMD instruction ratio in the loop in the original program is lower than a second threshold.
-
Patent Agency Ranking
公开(公告)号：US20170185387A1
公开(公告)日：2017-06-29
申请号：US15325332
申请日：2014-08-28
Applicant: Hewlett Packard Enterprise Development LP
Inventor： Benjamin Orth Chandler
CPC classification number: G06F8/4452 , G06F9/38 , G06F9/4494
Abstract: A system, method, and a computer-readable storage device for sloppy feedback loop compilation are described herein. For example, a dataflow application definition can be obtained. The dataflow application definition may include a feedback loop bounding a compute block. It may then be determined that the feedback loop is to be compiled as a sloppy feedback loop. The dataflow application can then be compiled as an executable object that pipelines the compute block of the dataflow application.
-
公开(公告)号：US09628544B2
公开(公告)日：2017-04-18
申请号：US14530440
申请日：2014-10-31
Applicant: AppDynamics, Inc.
Inventor： Andrew Patrick Buteau
CPC classification number: G06F8/22 , G06F8/312 , G06F8/355 , G06F8/4452 , G06F8/71 , G06F9/52 , H04L67/02 , H04L67/2833
Abstract: The present technology adds code to a top level build configuration file of a configuration program that will gather metrics for each invocation of a build. These metrics are sent to a commonly accessible metric server for future analysis. The metrics are collected for a distributed engineering team over several machines. Compilation time metrics may then be collected for each compilation event and those metrics are analyzed by a common aggregator.
-
公开(公告)号：US09619360B2
公开(公告)日：2017-04-11
申请号：US14479455
申请日：2014-09-08
Applicant: International Business Machines Corporation
Inventor： Shivali Agarwal , Monika Gupta , Naga Praveen Kumar Katta
CPC classification number: G06F8/45 , G06F8/30 , G06F8/4452 , G06F8/452 , G06F8/72 , G06F11/3466 , G06F2201/865
Abstract: A method and system for creating a library method stub in source code form corresponding to an original library call in machine-executable form. The library method stub is created in a predefined programming language by use of a library method signature associated with the original library call, at least one idiom sentence, and a call invoking the original library call. Creating the library method stub includes composing source code of the library method stub by matching the at least one idiom sentence with idiom-stub mappings predefined for each basic idiom of at least one basic idiom. The original library call appears in sequential code. The library method signature specifies formal arguments of the original library call. The at least one idiom sentence summarizes memory operations performed by the original library call on the formal arguments. The created library method stub is stored in a database.
-
公开(公告)号：US09612811B2
公开(公告)日：2017-04-04
申请号：US14160426
申请日：2014-01-21
Applicant: NVIDIA CORPORATION
Inventor： Amit Jayant Sabne , Yuan Lin , Vinod Grover
IPC: G06F9/45
CPC classification number: G06F8/456 , G06F8/443 , G06F8/4452
Abstract: One embodiment of the present invention sets forth a method for causing thread convergence. The method includes determining that a control flow graph representing a first section of a program includes at least two non-overlapping paths that extend from a first divergent node to a candidate node. The method also includes determining that the first divergent node is not a dominator of the candidate node or that the candidate node is not a post-dominator of the first divergent node. The method further includes identifying an external node and inserting a first instruction configured to cause a predicate variable to be set to true for a first set of threads that is to execute the external node. The method additionally includes inserting into the program a second divergent node configured to cause various threads to execute or not execute a first control flow path associated with the external node.
-
公开(公告)号：US20160124721A1
公开(公告)日：2016-05-05
申请号：US14530440
申请日：2014-10-31
Applicant: AppDynamics, Inc.
Inventor： Andrew Patrick Buteau
CPC classification number: G06F8/22 , G06F8/312 , G06F8/355 , G06F8/4452 , G06F8/71 , G06F9/52 , H04L67/02 , H04L67/2833
Abstract: The present technology adds code to a top level build configuration file of a configuration program that will gather metrics for each invocation of a build. These metrics are sent to a commonly accessible metric server for future analysis. The metrics are collected for a distributed engineering team over several machines. Compilation time metrics may then be collected for each compilation event and those metrics are analyzed by a common aggregator.
Abstract translation: 本技术将代码添加到配置程序的顶级构建配置文件中，该配置程序将收集每次调用构建的度量标准。 这些指标被发送到一个常用的度量标准服务器，以便将来进行分析。 通过几台机器为分布式工程团队收集这些指标。 然后可以针对每个编译事件收集编译时间度量，并且这些度量由公共聚合器分析。
-
-
-
-
-
-
-
-
-
Search Results
243
records
(took 0.024 seconds)
