公开(公告)号：US09811341B2

公开(公告)日：2017-11-07

申请号：US13995649

申请日：2011-12-29

Applicant: Kyriakos A. Stavrou ,  Enric Gibert Codina ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos E. Kotselidis ,  Fernando Latorre ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles Gimeno ,  Grigorios Magklis ,  Pedro Marcuello ,  Alejandro Martinez Vicente ,  Raul Martinez ,  Daniel Ortega ,  Demos Pavlou ,  Georgios Tournavitis ,  Polychronis Xekalakis

Inventor： Kyriakos A. Stavrou ,  Enric Gibert Codina ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos E. Kotselidis ,  Fernando Latorre ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles Gimeno ,  Grigorios Magklis ,  Pedro Marcuello ,  Alejandro Martinez Vicente ,  Raul Martinez ,  Daniel Ortega ,  Demos Pavlou ,  Georgios Tournavitis ,  Polychronis Xekalakis

IPC: G06F9/38 ,  G06F9/30 ,  G06F12/0862

CPC classification number: G06F9/3804 ,  G06F9/30047 ,  G06F9/3017 ,  G06F9/3802 ,  G06F9/3806 ,  G06F9/3848 ,  G06F12/0862 ,  G06F2212/452

Abstract: Disclosed is an apparatus and method to manage instruction cache prefetching from an instruction cache. A processor may comprise: a prefetch engine; a branch prediction engine to predict the outcome of a branch; and dynamic optimizer. The dynamic optimizer may be used to control: identifying common instruction cache misses and inserting a prefetch instruction from the prefetch engine to the instruction cache.

公开(公告)号：US20140019721A1

公开(公告)日：2014-01-16

申请号：US13995649

申请日：2011-12-29

Applicant: Kyriakos A. Stavrou ,  Enric Gibert Codina ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos E. Kotselidis ,  Fernando Latorre ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles gimeno ,  Grigorios Magklis ,  Pedro Marcuello ,  Alejandro Martinez Vicente ,  Raul Martinez ,  Daniel Ortega ,  Demos Pavlou ,  Georgios Tournavitis ,  Polychronis Xekalakis

Inventor： Kyriakos A. Stavrou ,  Enric Gibert Codina ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos E. Kotselidis ,  Fernando Latorre ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles gimeno ,  Grigorios Magklis ,  Pedro Marcuello ,  Alejandro Martinez Vicente ,  Raul Martinez ,  Daniel Ortega ,  Demos Pavlou ,  Georgios Tournavitis ,  Polychronis Xekalakis

IPC: G06F9/38

CPC classification number: G06F9/3804 ,  G06F9/30047 ,  G06F9/3017 ,  G06F9/3802 ,  G06F9/3806 ,  G06F9/3848 ,  G06F12/0862 ,  G06F2212/452

Abstract: Disclosed is an apparatus and method to manage instruction cache prefetching from an instruction cache. A processor may comprise: a prefetch engine; a branch prediction engine to predict the outcome of a branch; and dynamic optimizer. The dynamic optimizer may be used to control: indentifying common instruction cache misses and inserting a prefetch instruction from the prefetch engine to the instruction cache.

Abstract translation: 公开了一种用于从指令高速缓存管理指令高速缓存预取的装置和方法。 处理器可以包括：预取引擎; 预测分支结果的分支预测引擎; 和动态优化器。 动态优化器可用于控制：识别公共指令高速缓存未命中并将预取引擎的预取指令插入指令高速缓存。

公开(公告)号：US20150007153A1

公开(公告)日：2015-01-01

申请号：US13929360

申请日：2013-06-27

Applicant: Raul Martinez ,  Enric Gibert Codina ,  Marc Lupon ,  Kyriakos A. Stavrou

Inventor： Raul Martinez ,  Enric Gibert Codina ,  Marc Lupon ,  Kyriakos A. Stavrou

IPC: G06F9/45 ,  G06F11/14

CPC classification number: G06F8/443 ,  G06F8/4434

Abstract: Described herein are technologies for optimizing computer code. A code generator can optimize a portion of original code to create optimized code. The code generator can create a partial commit point to indicate that execution of the optimized code produces an invalid architectural state. The code generator can create recovery information recover a valid architectural state at a recovery point. The code generator can associate the partial commit point and recovery information with the optimized code.

Abstract translation: 这里描述的是用于优化计算机代码的技术。 代码生成器可以优化原始代码的一部分以创建优化的代码。 代码生成器可以创建部分提交点，以指示优化代码的执行产生无效的架构状态。 代码生成器可以创建恢复信息，以在恢复点恢复有效的体系结构状态。 代码生成器可以将部分提交点和恢复信息与优化的代码相关联。

公开(公告)号：US20140095849A1

公开(公告)日：2014-04-03

申请号：US13631402

申请日：2012-09-28

Applicant: Polychronis Xekalakis ,  Pedro Marcuello ,  Alejandro Vicente Martinez ,  Christos E. Kotselidis ,  Grigorios Magklis ,  Fernando Latorre ,  Raul Martinez ,  Josep M. Codina ,  Enric Gibert Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles ,  Daniel Ortega ,  Demos Pavlou ,  Kyriakos A. Stavrou ,  Georgios Tournavitis

Inventor： Polychronis Xekalakis ,  Pedro Marcuello ,  Alejandro Vicente Martinez ,  Christos E. Kotselidis ,  Grigorios Magklis ,  Fernando Latorre ,  Raul Martinez ,  Josep M. Codina ,  Enric Gibert Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Pedro Lopez ,  Marc Lupon ,  Carlos Madriles ,  Daniel Ortega ,  Demos Pavlou ,  Kyriakos A. Stavrou ,  Georgios Tournavitis

IPC: G06F9/38

CPC classification number: G06F9/38 ,  G06F9/30036 ,  G06F9/3848 ,  G06F9/3877 ,  G06F9/3887 ,  G06F9/3889

Abstract: A computer-readable storage medium, method and system for optimization-level aware branch prediction is described. A gear level is assigned to a set of application instructions that have been optimized. The gear level is also stored in a register of a branch prediction unit of a processor. Branch prediction is then performed by the processor based upon the gear level.

Abstract translation: 描述了用于优化级感知分支预测的计算机可读存储介质，方法和系统。 齿轮级别被分配给已优化的一组应用指令。 齿轮级也存储在处理器的分支预测单元的寄存器中。 然后由处理器基于齿轮级执行分支预测。

公开(公告)号：US20130332705A1

公开(公告)日：2013-12-12

申请号：US13993054

申请日：2011-12-29

Applicant: Raul Martinez ,  Enric Gibert Codina ,  Pedro Lopez ,  Marti Torrents Lapuerta ,  Polychronis Xekalakis ,  Georgios Tournavitis ,  Kyriakos A. Stavrou ,  Demos Pavlou ,  Daniel Ortega ,  Alejandro Martinez Vicente ,  Pedro Marcuello ,  Grigorios Magklis ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos Kotselidis ,  Fernando Latorre ,  Marc Lupon ,  Carlos Madriles

Inventor： Raul Martinez ,  Enric Gibert Codina ,  Pedro Lopez ,  Marti Torrents Lapuerta ,  Polychronis Xekalakis ,  Georgios Tournavitis ,  Kyriakos A. Stavrou ,  Demos Pavlou ,  Daniel Ortega ,  Alejandro Martinez Vicente ,  Pedro Marcuello ,  Grigorios Magklis ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos Kotselidis ,  Fernando Latorre ,  Marc Lupon ,  Carlos Madriles

IPC: G06F9/30

CPC classification number: G06F11/3037 ,  G06F11/3409 ,  G06F11/3466 ,  G06F12/0862 ,  G06F2201/86 ,  G06F2201/865 ,  G06F2201/88 ,  G06F2201/885

Abstract: A combination of hardware and software collect profile data for asynchronous events, at code region granularity. An exemplary embodiment is directed to collecting metrics for prefetching events, which are asynchronous in nature. Instructions that belong to a code region are identified using one of several alternative techniques, causing a profile bit to be set for the instruction, as a marker. Each line of a data block that is prefetched is similarly marked. Events corresponding to the profile data being collected and resulting from instructions within the code region are then identified. Each time that one of the different types of events is identified, a corresponding counter is incremented. Following execution of the instructions within the code region, the profile data accumulated in the counters are collected, and the counters are reset for use with a new code region.

Abstract translation: 硬件和软件的组合以代码区域粒度收集用于异步事件的简档数据。 示例性实施例涉及收集在本质上是异步的预取事件的度量。 使用几种替代技术之一来标识属于代码区域的指令，使得为指令设置配置文件位作为标记。 预取数据块的每一行都被类似地标记。 然后识别与正在收集并且由代码区域内的指令产生的简档数据相对应的事件。 每次识别出不同类型的事件之一时，相应的计数器将被递增。 在代码区域中执行指令之后，收集在计数器中累积的简档数据，并且重置计数器以与新的代码区域一起使用。

公开(公告)号：US20100269102A1

公开(公告)日：2010-10-21

申请号：US12624804

申请日：2009-11-24

Applicant: Fernando Latorre ,  Josep M. Codina ,  Enric Gibert Codina ,  Pedro Lopez ,  Carlos Madriles ,  Alejandro Martinez Vincente ,  Raul Martinez ,  Antonio Gonzalez

Inventor： Fernando Latorre ,  Josep M. Codina ,  Enric Gibert Codina ,  Pedro Lopez ,  Carlos Madriles ,  Alejandro Martinez Vincente ,  Raul Martinez ,  Antonio Gonzalez

IPC: G06F9/30 ,  G06F12/08 ,  G06F9/44

CPC classification number: G06F9/3842 ,  G06F8/433 ,  G06F8/452 ,  G06F8/457 ,  G06F9/3851 ,  G06F9/3861

Abstract: Systems, methods, and apparatuses for decomposing a sequential program into multiple threads, executing these threads, and reconstructing the sequential execution of the threads are described. A plurality of data cache units (DCUs) store locally retired instructions of speculatively executed threads. A merging level cache (MLC) merges data from the lines of the DCUs. An inter-core memory coherency module (ICMC) globally retire instructions of the speculatively executed threads in the MLC.

Abstract translation: 描述用于将顺序程序分解成多个线程，执行这些线程以及重建线程的顺序执行的系统，方法和装置。 多个数据高速缓存单元（DCU）存储推测执行的线程的本地退出指令。 合并级别缓存（MLC）合并来自DCU的行的数据。 核心内存一致性模块（ICMC）全局退出MLC中推测执行线程的指令。

公开(公告)号：US10013326B2

公开(公告)日：2018-07-03

申请号：US13993054

申请日：2011-12-29

Applicant: Raul Martinez ,  Enric Gibert Codina ,  Pedro Lopez ,  Marti Torrents Lapuerta ,  Polychronis Xekalakis ,  Georgios Tournavitis ,  Kyriakos A. Stavrou ,  Demos Pavlou ,  Daniel Ortega ,  Alejandro Martinez Vicente ,  Pedro Marcuello ,  Grigorios Magklis ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos Kotselidis ,  Fernando Latorre ,  Marc Lupon ,  Carlos Madriles

Inventor： Raul Martinez ,  Enric Gibert Codina ,  Pedro Lopez ,  Marti Torrents Lapuerta ,  Polychronis Xekalakis ,  Georgios Tournavitis ,  Kyriakos A. Stavrou ,  Demos Pavlou ,  Daniel Ortega ,  Alejandro Martinez Vicente ,  Pedro Marcuello ,  Grigorios Magklis ,  Josep M. Codina ,  Crispin Gomez Requena ,  Antonio Gonzalez ,  Mirem Hyuseinova ,  Christos Kotselidis ,  Fernando Latorre ,  Marc Lupon ,  Carlos Madriles

IPC: G06F11/30 ,  G06F11/34 ,  G06F12/0862

CPC classification number: G06F11/3037 ,  G06F11/3409 ,  G06F11/3466 ,  G06F12/0862 ,  G06F2201/86 ,  G06F2201/865 ,  G06F2201/88 ,  G06F2201/885

Abstract: A combination of hardware and software collect profile data for asynchronous events, at code region granularity. An exemplary embodiment is directed to collecting metrics for prefetching events, which are asynchronous in nature. Instructions that belong to a code region are identified using one of several alternative techniques, causing a profile bit to be set for the instruction, as a marker. Each line of a data block that is prefetched is similarly marked. Events corresponding to the profile data being collected and resulting from instructions within the code region are then identified. Each time that one of the different types of events is identified, a corresponding counter is incremented. Following execution of the instructions within the code region, the profile data accumulated in the counters are collected, and the counters are reset for use with a new code region.

公开(公告)号：US09940138B2

公开(公告)日：2018-04-10

申请号：US12420762

申请日：2009-04-08

Applicant: Pedro Lopez ,  Carlos Madriles ,  Alejandro Martinez ,  Raul Martinez ,  Josep M. Codina ,  Enric Gibert Codina ,  Fernando Latorre ,  Antonio Gonzalez

Inventor： Pedro Lopez ,  Carlos Madriles ,  Alejandro Martinez ,  Raul Martinez ,  Josep M. Codina ,  Enric Gibert Codina ,  Fernando Latorre ,  Antonio Gonzalez

IPC: G06F9/30 ,  G06F11/00 ,  G06F9/38 ,  G06F11/14

CPC classification number: G06F9/3863 ,  G06F9/30043 ,  G06F9/3842 ,  G06F9/3851 ,  G06F11/1402

Abstract: Methods and apparatus are disclosed for using a register checkpointing mechanism to resolve multithreading mis-speculations. Valid architectural state is recovered and execution is rolled back. Some embodiments include memory to store checkpoint data. Multiple thread units concurrently execute threads. They execute a checkpoint mask instruction to initialize memory to store active checkpoint data including register contents and a checkpoint mask indicating the validity of stored register contents. As register contents change, threads execute checkpoint write instructions to store register contents and update the checkpoint mask. Threads also execute a recovery function instruction to store a pointer to a checkpoint recovery function, and in response to mis-speculation among the threads, branch to the checkpoint recovery function. Threads then execute one or more checkpoint read instructions to copy data from a valid checkpoint storage area into the registers necessary to recover a valid architectural state, from which execution may resume.

公开(公告)号：US20160162406A1

公开(公告)日：2016-06-09

申请号：US14563839

申请日：2014-12-08

Applicant: FERNANDO LATORRE ,  Josep M. CODINA ,  Enric Gibert CODINA ,  Pedro LOPEZ ,  Carlos MADRILES ,  Alejandro Martinez VINCENTE ,  Raul MARTINEZ ,  Antonio GONZALEZ

Inventor： FERNANDO LATORRE ,  Josep M. CODINA ,  Enric Gibert CODINA ,  Pedro LOPEZ ,  Carlos MADRILES ,  Alejandro Martinez VINCENTE ,  Raul MARTINEZ ,  Antonio GONZALEZ

IPC: G06F12/08 ,  G06F9/52

CPC classification number: G06F9/528 ,  G06F9/3834 ,  G06F9/3851 ,  G06F9/3859 ,  G06F9/48 ,  G06F12/0837

Abstract: Systems, methods, and apparatuses for decomposing a sequential program into multiple threads, executing these threads, and reconstructing the sequential execution of the threads are described. A plurality of data cache units (DCUs) store locally retired instructions of speculatively executed threads. A merging level cache (MLC) merges data from the lines of the DCUs. An inter-core memory coherency module (ICMC) globally retire instructions of the speculatively executed threads in the MLC.

Abstract translation: 描述用于将顺序程序分解成多个线程，执行这些线程以及重建线程的顺序执行的系统，方法和装置。 多个数据高速缓存单元（DCU）存储推测执行的线程的本地退出指令。 合并级别缓存（MLC）合并来自DCU的行的数据。 核心内存一致性模块（ICMC）全局退出MLC中推测执行线程的指令。

公开(公告)号：US20160092235A1

公开(公告)日：2016-03-31

申请号：US14497974

申请日：2014-09-26

Applicant: REKAI GONZALEZ-ALBERQUILLA ,  TANAUSU RAMIREZ ,  JOSEP M. CODINA ,  ENRIC GIBERT CODINA

Inventor： REKAI GONZALEZ-ALBERQUILLA ,  TANAUSU RAMIREZ ,  JOSEP M. CODINA ,  ENRIC GIBERT CODINA

IPC: G06F9/38

CPC classification number: G06F9/3851 ,  G06F9/3824 ,  G06F9/3836 ,  G06F9/3855 ,  G06F9/3867 ,  G06F9/4881 ,  G06F12/1027 ,  G06F12/1036 ,  G06F2212/1024 ,  G06F2212/68 ,  G06F2212/684

Abstract: An apparatus and method are described for improved thread selection. For example, one embodiment of a processor comprises: first logic to maintain a history table comprising a plurality of entries, each entry in the table associated with an instruction and including history data indicating prior hits and/or misses to a cache level and/or a translation lookaside buffer (TLB) for that instruction; and second logic to select a particular thread for execution at a particular processor pipeline stage based on the history data.

Abstract translation: 描述了用于改进线程选择的装置和方法。 例如，处理器的一个实施例包括：维护包括多个条目的历史表的第一逻辑，表中的每个条目与指令相关联，并且包括指示先前命中和/或未命中到高速缓存级别的历史数据和/或 用于该指令的翻译后备缓冲器（TLB）; 以及基于历史数据在特定处理器流水线阶段选择特定线程以执行的第二逻辑。