公开(公告)号：US20200233806A1

公开(公告)日：2020-07-23

申请号：US16837833

申请日：2020-04-01

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Ibrahim Hur ,  Ugonna Echeruo ,  Stijn Eyerman ,  Kristof Du Bois

IPC: G06F12/0862

Abstract: Apparatus, method, and system for enhancing data prefetching based on non-uniform memory access (NUMA) characteristics are described herein. An apparatus embodiment includes a system memory, a cache, and a prefetcher. The system memory includes multiple memory regions, at least some of which are associated with different NUMA characteristic (access latency, bandwidth, etc.) than others. Each region is associated with its own set of prefetch parameters that are set in accordance to their respective NUMA characteristics. The prefetcher monitors data accesses to the cache and generates one or more prefetch requests to fetch data from the system memory to the cache based on the monitored data accesses and the set of prefetch parameters associated with the memory region from which data is to be fetched. The set of prefetcher parameters may include prefetch distance, training-to-stable threshold, and throttle threshold.

公开(公告)号：US20200004684A1

公开(公告)日：2020-01-02

申请号：US16024527

申请日：2018-06-29

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Ibrahim Hur ,  Ugonna Echeruo ,  Stijn Eyerman ,  Kristof Du Bois

IPC: G06F12/0862

Abstract: Apparatus, method, and system for enhancing data prefetching based on non-uniform memory access (NUMA) characteristics are described herein. An apparatus embodiment includes a system memory, a cache, and a prefetcher. The system memory includes multiple memory regions, at least some of which are associated with different NUMA characteristic (access latency, bandwidth, etc.) than others. Each region is associated with its own set of prefetch parameters that are set in accordance to their respective NUMA characteristics. The prefetcher monitors data accesses to the cache and generates one or more prefetch requests to fetch data from the system memory to the cache based on the monitored data accesses and the set of prefetch parameters associated with the memory region from which data is to be fetched. The set of prefetcher parameters may include prefetch distance, training-to-stable threshold, and throttle threshold.

公开(公告)号：US10289516B2

公开(公告)日：2019-05-14

申请号：US15394271

申请日：2016-12-29

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Yves Vandriessche

IPC: G06F12/08 ,  G06F11/30 ,  G06F12/0831 ,  G06F12/084 ,  G06F12/0842 ,  G06F9/38 ,  G06F9/30 ,  G06F9/52 ,  G06F12/0804 ,  G06F12/0808

Abstract: A processor core includes a decode circuit to decode an instruction, where the instruction specifies an address to be monitored. The processor core further includes a monitor circuit, where the monitor circuit includes a data structure to store a plurality of entries for addresses that are being monitored by the monitor circuit and a triggered queue, where the monitor circuit is to enqueue an address being monitored by the monitor circuit into the triggered queue in response to a determination that a triggering event for the address being monitored by the monitor circuit occurred. The processor core further includes an execution circuit to execute the decoded instruction to add an entry for the specified address to be monitored into the data structure and ensure, using a cache coherence protocol, that a coherency status of a cache line corresponding to the specified address to be monitored is in a shared state.

公开(公告)号：US12111772B2

公开(公告)日：2024-10-08

申请号：US17133414

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Ibrahim Hur

IPC: G06F12/1027 ,  G06F9/30 ,  G06F12/0862 ,  G06F12/0891

CPC classification number: G06F12/1027 ,  G06F9/30047 ,  G06F12/0862 ,  G06F12/0891 ,  G06F2212/6024

Abstract: Techniques and mechanisms for providing information to determine whether a software prefetch instruction is to be executed. In an embodiment, one or more entries of a translation lookaside buffer (TLB) each include a respective value which indicates whether, according to one or more criteria, corresponding data has been sufficiently utilized. Insufficiently utilized data is indicated in a TLB entry with an identifier of an executed instruction to prefetch the corresponding data. An eviction of the TLB entry results in the creation of an entry in a registry of prefetch instructions. The entry in the registry includes the identifier of the executed prefetch instruction, and a value indicating a number of times that one or more future prefetch instructions are to be dropped. In another embodiment, execution of a subsequent prefetch instruction—which also corresponds to the identifier—is prevented based on the registry entry.

公开(公告)号：US12050915B2

公开(公告)日：2024-07-30

申请号：US17130592

申请日：2020-12-22

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Stijn Eyerman ,  Ibrahim Hur

IPC: G06F9/30 ,  G06F9/38 ,  G06F11/34 ,  G06F12/0811 ,  G06F12/0862

CPC classification number: G06F9/3802 ,  G06F9/30047 ,  G06F9/3818 ,  G06F11/3409 ,  G06F12/0811 ,  G06F12/0862 ,  G06F9/383 ,  G06F2212/452

Abstract: In an embodiment, a processor includes a fetch circuit to fetch instructions, the instructions including a code prefetch instruction; a decode circuit to decode the code prefetch instruction and provide the decoded code prefetch instruction to a memory circuit, the memory circuit to execute the decoded code prefetch instruction to prefetch a first set of code blocks into a first cache and to prefetch a second set of code blocks into a second cache. Other embodiments are described and claimed.

公开(公告)号：US20220283719A1

公开(公告)日：2022-09-08

申请号：US17824413

申请日：2022-05-25

Applicant: Intel Corporation

Inventor： Stijn Eyerman ,  Wim Heirman ,  Ibrahim Hur

IPC: G06F3/06

Abstract: An apparatus to facilitate generating a memory bandwidth stack for visualizing memory bandwidth utilization is disclosed. The apparatus includes processors to receive data corresponding to a memory cycle occurring during a total execution time of an application executed by the one or more processors; for the memory cycle, assign the memory cycle to a component of a bandwidth stack based on analysis of the data and in accordance with a prioritization scheme; for the component, determine a portion of the bandwidth stack to account to the component based at least in part on the assignment of the memory cycle to the component; and generate the bandwidth stack by at least representing the portion accounted to the component in the bandwidth stack.

公开(公告)号：US20220100511A1

公开(公告)日：2022-03-31

申请号：US17033770

申请日：2020-09-26

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Stijn Eyerman ,  Ibrahim Hur

IPC: G06F9/30 ,  G06F12/0804 ,  G06F12/12

Abstract: Methods and apparatus relating to one or more delayed cache writeback instructions for improved data sharing in manycore processors are described. In an embodiment, a delayed cache writeback instruction causes a cache block in a modified state in a Level 1 (L1) cache of a first core of a plurality of cores of a multi-core processor to a Modified write back (M.wb) state. The M.wb state causes the cache block to be written back to LLC upon eviction of the cache block from the L1 cache. Other embodiments are also disclosed and claimed.

公开(公告)号：US10929132B1

公开(公告)日：2021-02-23

申请号：US16579806

申请日：2019-09-23

Applicant: Intel Corporation

Inventor： Robert Pawlowski ,  Scott Hagan Schmittel ,  Joshua Fryman ,  Wim Heirman ,  Jason Howard ,  Ankit More ,  Shaden Smith ,  Scott Cline

IPC: G06F9/30 ,  G06F9/35

Abstract: Disclosed embodiments relate to systems and methods for performing instructions to access a compressed graphic list. In one example, a processor includes fetch and decode circuitry to fetch and decode the single instruction to access the compressed graphic list, and execution circuitry to execute the decoded single instruction to cause access to the compressed graphic list by: receiving, from a load store queue, at a first op-engine associated with a first data location, an indirection request, computing, via the first op-engine, a second data location associated with a second op-engine, computing, via the second op-engine, a third data location associated with a third op-engine responsive to the indirection request, and providing, via the third op-engine, a data response to the load store queue responsive to receiving data from the third data location.

公开(公告)号：US20190303294A1

公开(公告)日：2019-10-03

申请号：US15940712

申请日：2018-03-29

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Kristof Du Bois ,  Yves Vandriessche ,  Stijn Eyerman ,  Ibrahim Hur ,  Erik Hallnor

IPC: G06F12/0811 ,  G06F12/0815 ,  G06F12/0871 ,  G06F12/128

Abstract: Embodiment of this disclosure provides a mechanism to store cache lines in dedicated cache of an idle core. In one embodiment, a multi-core processor comprising a first core, a second core, a first cache, a second cache, a third cache, and a cache controller unit is provided. The cache controller is operatively coupled to at least the first cache, the second cache, and the third cache. The cache controller is to evict a first line from the first cache, wherein the first core is in an active state. Responsive to the evicting of the first line, the first line is stored in the third cache. Responsive to storing the first line, a second line is evicted from the third cache. Responsive to evicting the second line, the second line is stored in the second cache when the second core is in an idle state.

公开(公告)号：US10303609B2

公开(公告)日：2019-05-28

申请号：US15718845

申请日：2017-09-28

Applicant: Intel Corporation

Inventor： Wim Heirman ,  Kristof Du Bois ,  Yves Vandriessche ,  Stijn Eyerman ,  Ibrahim Hur

IPC: G06F12/0862

Abstract: Embodiments of apparatuses, methods, and systems for independent tuning of multiple hardware prefetchers are described. In an embodiment, an apparatus includes a processor core, a cache memory, a hardware prefetcher, and a prefetch tuner. The hardware prefetcher is to prefetch data for the processor core from a system memory to the cache memory. The prefetch tuner is to adjust a prefetch rate of the hardware prefetcher based on a fraction of late prefetches. The prefetch tuner includes a late prefetch counter to count a number of late prefetches for the hardware prefetcher, a prefetch counter to count a number of prefetches for the hardware prefetcher, and a late prefetch calculator to calculate the fraction of late prefetches based on the number of late prefetches and the number of prefetches.