公开(公告)号：US20210182058A1

公开(公告)日：2021-06-17

申请号：US17169232

申请日：2021-02-05

Applicant: Intel Corporation

Inventor： Himanshu Kaul ,  Mark A. Anders ,  Sanu K. Mathew ,  Anbang Yao ,  Joydeep Ray ,  Ping T. Tang ,  Michael S. Strickland ,  Xiaoming Chen ,  Tatiana Shpeisman ,  Abhishek R. Appu ,  Altug Koker ,  Kamal Sinha ,  Balaji Vembu ,  Nicolas C. Galoppo Von Borries ,  Eriko Nurvitadhi ,  Rajkishore Barik ,  Tsung-Han Lin ,  Vasanth Ranganathan ,  Sanjeev Jahagirdar

IPC: G06F9/30 ,  G06N3/04 ,  G06F9/38 ,  G06F7/483 ,  G09G5/393 ,  G06F7/544 ,  G06N3/063 ,  G06N3/08

Abstract: A processing apparatus is provided comprising a multiprocessor having a multithreaded architecture. The multiprocessor can execute at least one single instruction to perform parallel mixed precision matrix operations. In one embodiment the apparatus includes a memory interface and an array of multiprocessors coupled to the memory interface. At least one multiprocessor in the array of multiprocessors is configured to execute a fused multiply-add instruction in parallel across multiple threads.

公开(公告)号：US10983581B2

公开(公告)日：2021-04-20

申请号：US15859598

申请日：2017-12-31

Applicant: Intel Corporation

Inventor： Sanjeev Jahagirdar ,  Altug Koker ,  Yoav Harel ,  Kenneth Brand ,  Chandra Gurram ,  Eric Finley ,  Bhushan Borole ,  Carlos Nava Rodriguez

IPC: G06F1/32 ,  G06F1/324 ,  G06F1/3212 ,  G06F1/3234

Abstract: Methods and apparatus relating to techniques for resource load balancing based on usage and/or power limits are described. In an embodiment, resource load balancing logic causes a first resource of a processor to operate at a first frequency and a second resource of the processor to operate at a second frequency. Memory stores a plurality of frequency values. The resource load balancing logic also selects the first frequency and the second frequency based on the stored plurality of frequency values. Operation of the first resource at the first frequency and the second resource at the second frequency in turn causes the processor to operate under a power budget. The resource load balancing logic causes change to the first frequency and the second frequency in response to a determination that operation of the processor is different than the power budget. Other embodiments are also disclosed and claimed.

公开(公告)号：US20190295211A1

公开(公告)日：2019-09-26

申请号：US16377315

申请日：2019-04-08

Applicant: Intel Corporation

Inventor： Abhishek R. Appu ,  Altug Koker ,  John C. Weast ,  Mike B. Macpherson ,  Linda L. Hurd ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Prasoonkumar Surti ,  Chandrasekaran Sakthivel ,  Liwei Ma ,  Elmoustapha Ould-Ahmed-Vall ,  Kamal Sinha ,  Joydeep Ray ,  Balaji Vembu ,  Sanjeev Jahagirdar ,  Vasanth Ranganathan ,  Dukhwan Kim

IPC: G06T1/20 ,  G06N3/08 ,  G06N3/063 ,  G06N3/04 ,  G06F9/46

Abstract: A mechanism is described for facilitating inference coordination and processing utilization for machine learning at autonomous machines. A method of embodiments, as described herein, includes detecting, at training time, information relating to one or more tasks to be performed according to a training dataset relating to a processor including a graphics processor. The method may further include analyzing the information to determine one or more portions of hardware relating to the processor capable of supporting the one or more tasks, and configuring the hardware to pre-select the one or more portions to perform the one or more tasks, while other portions of the hardware remain available for other tasks.

公开(公告)号：US20170017297A1

公开(公告)日：2017-01-19

申请号：US15280057

申请日：2016-09-29

Applicant: Intel Corporation

Inventor： Sanjeev Jahagirdar ,  Varghese George ,  John B. Conrad ,  Robert Milstrey ,  Stephen A. Fischer ,  Alon Naveh ,  Shai Rotem

IPC: G06F1/32 ,  G06F9/44

CPC classification number: G06F1/3287 ,  G06F1/3203 ,  G06F1/324 ,  G06F1/3243 ,  G06F1/3246 ,  G06F1/3275 ,  G06F1/3293 ,  G06F1/3296 ,  G06F9/4418 ,  G06F11/1441 ,  G06F12/084 ,  G06F12/0875 ,  G06F2212/281 ,  G06F2212/305 ,  G06F2212/314 ,  G11C7/1072 ,  Y02B70/123 ,  Y02B70/126 ,  Y02B70/32 ,  Y02D10/152 ,  Y02D10/172 ,  Y02D50/20 ,  Y02P80/11 ,  Y10T307/305 ,  Y10T307/406 ,  Y10T307/582 ,  Y10T307/826

Abstract: Embodiments of the invention relate to a method and apparatus for a zero voltage processor sleep state. A processor may include a dedicated cache memory. A voltage regulator may be coupled to the processor to provide an operating voltage to the processor. During a transition to a zero voltage power management state for the processor, the operational voltage applied to the processor by the voltage regulator may be reduced to approximately zero and the state variables associated with the processor may be saved to the dedicated cache memory.

Abstract translation: 本发明的实施例涉及一种用于零电压处理器睡眠状态的方法和装置。 处理器可以包括专用高速缓存存储器。 电压调节器可以耦合到处理器以向处理器提供工作电压。 在处理器转换到零电压电源管理状态期间，电压调节器施加到处理器的工作电压可以减小到大约零，并且与处理器相关联的状态变量可以被保存到专用高速缓冲存储器。

公开(公告)号：US09081575B2

公开(公告)日：2015-07-14

申请号：US14254422

申请日：2014-04-16

Applicant: Intel Corporation

Inventor： Jose Allarey ,  Sanjeev Jahagirdar

IPC: G06F1/32 ,  G06F11/14 ,  G06F12/08 ,  G11C7/10

CPC classification number: G06F1/3287 ,  G06F1/3203 ,  G06F1/324 ,  G06F1/3243 ,  G06F1/3246 ,  G06F1/3275 ,  G06F1/3293 ,  G06F1/3296 ,  G06F9/4418 ,  G06F11/1441 ,  G06F12/084 ,  G06F12/0875 ,  G06F2212/281 ,  G06F2212/305 ,  G06F2212/314 ,  G11C7/1072 ,  Y02B70/123 ,  Y02B70/126 ,  Y02B70/32 ,  Y02D10/152 ,  Y02D10/172 ,  Y02D50/20 ,  Y02P80/11 ,  Y10T307/305 ,  Y10T307/406 ,  Y10T307/582 ,  Y10T307/826

Abstract: Embodiments of the invention relate to a method and apparatus for a zero voltage processor sleep state. A voltage regulator may be coupled to a processor to provide an operating voltage to the processor. During a transition to a zero voltage power management state for the processor, the operational voltage applied to the processor by the voltage regulator may be reduced to approximately zero while an external voltage is continuously applied to a portion of the processor to save state variables of the processor during the zero voltage management power state.

Abstract translation: 本发明的实施例涉及一种用于零电压处理器睡眠状态的方法和装置。 电压调节器可以耦合到处理器以向处理器提供工作电压。 在向处理器转换到零电压电源管理状态期间，由电压调节器施加到处理器的工作电压可以减小到大约为零，同时外部电压被持续地施加到处理器的一部分以保存处理器的状态变量 处理器在零电压管理电源状态。

公开(公告)号：US12182035B2

公开(公告)日：2024-12-31

申请号：US17428529

申请日：2020-03-14

Applicant: Intel Corporation

Inventor： Altug Koker ,  Joydeep Ray ,  Elmoustapha Ould-Ahmed-Vall ,  Abhishek Appu ,  Aravindh Anantaraman ,  Valentin Andrei ,  Durgaprasad Bilagi ,  Varghese George ,  Brent Insko ,  Sanjeev Jahagirdar ,  Scott Janus ,  Pattabhiraman K ,  SungYe Kim ,  Subramaniam Maiyuran ,  Vasanth Ranganathan ,  Lakshminarayanan Striramassarma ,  Xinmin Tian

IPC: G06F12/00 ,  G06F12/0875 ,  G06F12/0891 ,  G06F12/123 ,  G06T1/60

Abstract: Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received.

公开(公告)号：US12112398B2

公开(公告)日：2024-10-08

申请号：US18470652

申请日：2023-09-20

Applicant: Intel Corporation

Inventor： Naveen Matam ,  Lance Cheney ,  Eric Finley ,  Varghese George ,  Sanjeev Jahagirdar ,  Altug Koker ,  Josh Mastronarde ,  Iqbal Rajwani ,  Lakshminarayanan Striramassarma ,  Melaku Teshome ,  Vikranth Vemulapalli ,  Binoj Xavier

IPC: G06T1/20 ,  G06F13/40

CPC classification number: G06T1/20 ,  G06F13/4027

Abstract: Embodiments described herein provide techniques to disaggregate an architecture of a system on a chip integrated circuit into multiple distinct chiplets that can be packaged onto a common chassis. In one embodiment, a graphics processing unit or parallel processor is composed from diverse silicon chiplets that are separately manufactured. A chiplet is an at least partially and distinctly packaged integrated circuit that includes distinct units of logic that can be assembled with other chiplets into a larger package. A diverse set of chiplets with different IP core logic can be assembled into a single device.

公开(公告)号：US20240005443A1

公开(公告)日：2024-01-04

申请号：US18455128

申请日：2023-08-24

Applicant: Intel Corporation

Inventor： Naveen Matam ,  Lance Cheney ,  Eric Finley ,  Varghese George ,  Sanjeev Jahagirdar ,  Altug Koker ,  Josh Mastronarde ,  Iqbal Rajwani ,  Lakshminarayanan Striramassarma ,  Melaku Teshome ,  Vikranth Vemulapalli ,  Binoj Xavier

IPC: G06T1/20 ,  G06F13/40

CPC classification number: G06T1/20 ,  G06F13/4027

Abstract: Embodiments described herein provide techniques to disaggregate an architecture of a system on a chip integrated circuit into multiple distinct chiplets that can be packaged onto a common chassis. In one embodiment, a graphics processing unit or parallel processor is composed from diverse silicon chiplets that are separately manufactured. A chiplet is an at least partially and distinctly packaged integrated circuit that includes distinct units of logic that can be assembled with other chiplets into a larger package. A diverse set of chiplets with different IP core logic can be assembled into a single device.

公开(公告)号：US11861761B2

公开(公告)日：2024-01-02

申请号：US17095590

申请日：2020-11-11

Applicant: Intel Corporation

Inventor： Subramaniam Maiyuran ,  Durgaprasad Bilagi ,  Joydeep Ray ,  Scott Janus ,  Sanjeev Jahagirdar ,  Brent Insko ,  Lidong Xu ,  Abhishek R. Appu ,  James Holland ,  Vasanth Ranganathan ,  Nikos Kaburlasos ,  Altug Koker ,  Xinmin Tian ,  Guei-Yuan Lueh ,  Changliang Wang

IPC: G06T1/60 ,  G06T1/20 ,  G06F12/0802 ,  G06N5/04

CPC classification number: G06T1/60 ,  G06F12/0802 ,  G06N5/04 ,  G06T1/20 ,  G06F2212/251

Abstract: Embodiments described herein are generally directed to improvements relating to power, latency, bandwidth and/or performance issues relating to GPU processing/caching. According to one embodiment, a system includes a producer intellectual property (IP) (e.g., a media IP), a compute core (e.g., a GPU or an AI-specific core of the GPU), a streaming buffer logically interposed between the producer IP and the compute core. The producer IP is operable to consume data from memory and output results to the streaming buffer. The compute core is operable to perform AI inference processing based on data consumed from the streaming buffer and output AI inference processing results to the memory.

公开(公告)号：US20230260075A1

公开(公告)日：2023-08-17

申请号：US18305904

申请日：2023-04-24

Applicant: Intel Corporation

Inventor： Subramaniam Maiyuran ,  Durgaprasad Bilagi ,  Joydeep Ray ,  Scott Janus ,  Sanjeev Jahagirdar ,  Brent Insko ,  Lidong Xu ,  Abhishek R. Appu ,  James Holland ,  Vasanth Ranganathan ,  Nikos Kaburlasos ,  Altug Koker ,  Xinmin Tian ,  Guei-Yuan Lueh ,  Changliang Wang

IPC: G06T1/60 ,  G06T1/20 ,  G06F12/0802 ,  G06N5/04

CPC classification number: G06T1/60 ,  G06T1/20 ,  G06F12/0802 ,  G06N5/04 ,  G06F2212/251

Abstract: Embodiments described herein are generally directed to improvements relating to power, latency, bandwidth and/or performance issues relating to GPU processing/caching. According to one embodiment, a state of multiple intellectual property (IP) cores that have access to a common cache via a central fabric is observed. Responsive to the observed state being indicative of performance of a standalone workload by a first IP core of the multiple IP cores, the common cache is treated as a local cache of the first IP core by powering off the central fabric and causing the first IP core to access the common cache via a low power access path between the first IP core and the common cache that is outside of the central fabric.