-
公开(公告)号：US12086097B2
公开(公告)日：2024-09-10
申请号：US17817593
申请日：2022-08-04
Applicant: Tesla, Inc.
Inventor： Debjit Das Sarma , Emil Talpes , Peter Joseph Bannon
IPC: G06F15/80 , G06F7/544 , G06F9/30 , G06F9/38 , G06N3/045 , G06N3/063 , G06N3/08 , G06N20/00 , G06F7/575
CPC classification number: G06F15/8053 , G06F7/5443 , G06F9/3001 , G06F9/30036 , G06F9/30043 , G06F9/3853 , G06F9/3887 , G06F9/3889 , G06N3/045 , G06N3/063 , G06N3/08 , G06N20/00 , G06F7/575 , G06F15/8023
Abstract: A microprocessor system comprises a computational array and a vector computational unit. The computational array includes a plurality of computation units. The vector computational unit is in communication with the computational array and includes a plurality of processing elements. The processing elements are configured to receive output data elements from the computational array and process in parallel the received output data elements.
-
公开(公告)号：US20240256483A1
公开(公告)日：2024-08-01
申请号：US18415052
申请日：2024-01-17
Applicant: Intel Corporation
Inventor： Altug Koker , Varghese George , Aravindh Anantaraman , Valentin Andrei , Abhishek R. Appu , Niranjan Cooray , Nicolas Galoppo Von Borries , Mike MacPherson , Subramaniam Maiyuran , ElMoustapha Ould-Ahmed-Vall , David Puffer , Vasanth Ranganathan , Joydeep Ray , Ankur N. Shah , Lakshminarayanan Striramassarma , Prasoonkumar Surti , Saurabh Tangri
IPC: G06F15/78 , G06F7/544 , G06F7/575 , G06F7/58 , G06F9/30 , G06F9/38 , G06F9/50 , G06F12/02 , G06F12/06 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/80 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06N3/08 , G06T15/06
CPC classification number: G06F15/7839 , G06F7/5443 , G06F7/575 , G06F7/588 , G06F9/3001 , G06F9/30014 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30047 , G06F9/30065 , G06F9/30079 , G06F9/3887 , G06F9/5011 , G06F9/5077 , G06F12/0215 , G06F12/0238 , G06F12/0246 , G06F12/0607 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/8046 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06F9/3802 , G06F9/3818 , G06F9/3867 , G06F2212/1008 , G06F2212/1021 , G06F2212/1044 , G06F2212/302 , G06F2212/401 , G06F2212/455 , G06F2212/60 , G06N3/08 , G06T15/06
Abstract: Embodiments are generally directed to graphics processor data access and sharing. An embodiment of an apparatus includes a circuit element to produce a result in processing of an application; a load-store unit to receive the result and generate pre-fetch information for a cache utilizing the result; and a prefetch generator to produce prefetch addresses based at least in part on the pre-fetch information; wherein the load-store unit is to receive software assistance for prefetching, and wherein generation of the pre-fetch information is based at least in part on the software assistance.
-
">
公开(公告)号：US20240220164A1
公开(公告)日：2024-07-04
申请号：US18604585
申请日：2024-03-14
Applicant: ADVANCED MICRO DEVICES, INC.
Inventor： SOORAJ PUTHOOR , MUHAMMAD AMBER HASSAAN , ASHWIN AJI , MICHAEL L. CHU , NUWAN JAYASENA
CPC classification number: G06F3/0659 , G06F3/0622 , G06F3/0631 , G06F3/0656 , G06F3/0679 , G06F7/575
Abstract: Process isolation for a PIM device through exclusive locking includes receiving, from a process, a call requesting ownership of a PIM device. The request includes one or more PIM configuration parameters. The exclusive locking technique also includes granting the process ownership of the PIM device responsive to determining that ownership is available. The PIM device is configured according to the PIM configuration parameters.
-
公开(公告)号：US12007935B2
公开(公告)日：2024-06-11
申请号：US17428523
申请日：2020-03-14
Applicant: INTEL CORPORATION
Inventor： Subramaniam Maiyuran , Shubra Marwaha , Ashutosh Garg , Supratim Pal , Jorge Parra , Chandra Gurram , Varghese George , Darin Starkey , Guei-Yuan Lueh
IPC: G06F9/30 , G06F7/544 , G06F7/575 , G06F7/58 , G06F9/38 , G06F9/50 , G06F12/02 , G06F12/06 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/78 , G06F15/80 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06N3/08 , G06T15/06
CPC classification number: G06F15/7839 , G06F7/5443 , G06F7/575 , G06F7/588 , G06F9/3001 , G06F9/30014 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30047 , G06F9/30065 , G06F9/30079 , G06F9/3887 , G06F9/5011 , G06F9/5077 , G06F12/0215 , G06F12/0238 , G06F12/0246 , G06F12/0607 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/8046 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06F9/3802 , G06F9/3818 , G06F9/3867 , G06F2212/1008 , G06F2212/1021 , G06F2212/1044 , G06F2212/302 , G06F2212/401 , G06F2212/455 , G06F2212/60 , G06N3/08 , G06T15/06
Abstract: Graphics processors and graphics processing units having dot product accumulate instructions for a hybrid floating point format are disclosed. In one embodiment, a graphics multiprocessor comprises an instruction unit to dispatch instructions and
a processing resource coupled to the instruction unit. The processing resource is configured to receive a dot product accumulate instruction from the instruction unit and to process the dot product accumulate instruction using a bfloat16 number (BF16) format.
-
公开(公告)号：US11995029B2
公开(公告)日：2024-05-28
申请号：US17428527
申请日：2020-03-14
Applicant: Intel Corporation
Inventor： Lakshminarayanan Striramassarma , Prasoonkumar Surti , Varghese George , Ben Ashbaugh , Aravindh Anantaraman , Valentin Andrei , Abhishek Appu , Nicolas Galoppo Von Borries , Altug Koker , Mike Macpherson , Subramaniam Maiyuran , Nilay Mistry , Elmoustapha Ould-Ahmed-Vall , Selvakumar Panneer , Vasanth Ranganathan , Joydeep Ray , Ankur Shah , Saurabh Tangri
IPC: G06F12/00 , G06F7/544 , G06F7/575 , G06F7/58 , G06F9/30 , G06F9/38 , G06F9/50 , G06F12/02 , G06F12/06 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/78 , G06F15/80 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06N3/08 , G06T15/06
CPC classification number: G06F15/7839 , G06F7/5443 , G06F7/575 , G06F7/588 , G06F9/3001 , G06F9/30014 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30047 , G06F9/30065 , G06F9/30079 , G06F9/3887 , G06F9/5011 , G06F9/5077 , G06F12/0215 , G06F12/0238 , G06F12/0246 , G06F12/0607 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/8046 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06F9/3802 , G06F9/3818 , G06F9/3867 , G06F2212/1008 , G06F2212/1021 , G06F2212/1044 , G06F2212/302 , G06F2212/401 , G06F2212/455 , G06F2212/60 , G06N3/08 , G06T15/06
Abstract: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.
-
公开(公告)号：US11983630B2
公开(公告)日：2024-05-14
申请号：US18156628
申请日：2023-01-19
Applicant: Tesla, Inc.
Inventor： Forrest Nelson Iandola , Harsimran Singh Sidhu , Yiqi Hou
Abstract: A neural network architecture is used that reduces the processing load of implementing the neural network. This network architecture may thus be used for reduced-bit processing devices. The architecture may limit the number of bits used for processing and reduce processing to prevent data overflow at individual calculations of the neural network. To implement this architecture, the number of bits used to represent inputs at levels of the network and the related filter masks may also be modified to ensure the number of bits of the output does not overflow the resulting capacity of the reduced-bit processor. To additionally reduce the load for such a network, the network may implement a “starconv” structure that permits the incorporation of nearby nodes in a layer to balance processing requirements and permit the network to learn from context of other nodes.
-
公开(公告)号：US11954063B2
公开(公告)日：2024-04-09
申请号：US18170900
申请日：2023-02-17
Applicant: Intel Corporation
Inventor： Subramaniam Maiyuran , Shubra Marwaha , Ashutosh Garg , Supratim Pal , Jorge Parra , Chandra Gurram , Varghese George , Darin Starkey , Guei-Yuan Lueh
IPC: G06T15/06 , G06F7/544 , G06F7/575 , G06F7/58 , G06F9/30 , G06F9/38 , G06F9/50 , G06F12/02 , G06F12/06 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/78 , G06F15/80 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06N3/08
CPC classification number: G06F15/7839 , G06F7/5443 , G06F7/575 , G06F7/588 , G06F9/3001 , G06F9/30014 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30047 , G06F9/30065 , G06F9/30079 , G06F9/3887 , G06F9/5011 , G06F9/5077 , G06F12/0215 , G06F12/0238 , G06F12/0246 , G06F12/0607 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/8046 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06F9/3802 , G06F9/3818 , G06F9/3867 , G06F2212/1008 , G06F2212/1021 , G06F2212/1044 , G06F2212/302 , G06F2212/401 , G06F2212/455 , G06F2212/60 , G06N3/08 , G06T15/06
Abstract: Described herein is a graphics processing unit (GPU) configured to receive an instruction having multiple operands, where the instruction is a single instruction multiple data (SIMD) instruction configured to use a bfloat16 (BF16) number format and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent. The GPU can process the instruction using the multiple operands, where to process the instruction includes to perform a multiply operation, perform an addition to a result of the multiply operation, and apply a rectified linear unit function to a result of the addition.
-
公开(公告)号：US11934827B2
公开(公告)日：2024-03-19
申请号：US17556291
申请日：2021-12-20
Applicant: ADVANCED MICRO DEVICES, INC.
Inventor： Sooraj Puthoor , Muhammad Amber Hassaan , Ashwin Aji , Michael L. Chu , Nuwan Jayasena
CPC classification number: G06F9/3004 , G06F7/575 , G06F9/3001 , G06F9/3856
Abstract: An apparatus that manages multi-process execution in a processing-in-memory (“PIM”) device includes a gatekeeper configured to: receive an identification of one or more registered PIM processes; receive, from a process, a memory request that includes a PIM command; if the requesting process is a registered PIM process and another registered PIM process is active on the PIM device, perform a context switch of PIM state between the registered PIM processes; and issue the PIM command of the requesting process to the PIM device.
-
公开(公告)号：US11934342B2
公开(公告)日：2024-03-19
申请号：US17429277
申请日：2020-03-14
Applicant: Intel Corporation
Inventor： Altug Koker , Varghese George , Aravindh Anantaraman , Valentin Andrei , Abhishek R. Appu , Niranjan Cooray , Nicolas Galoppo Von Borries , Mike MacPherson , Subramaniam Maiyuran , ElMoustapha Ould-Ahmed-Vall , David Puffer , Vasanth Ranganathan , Joydeep Ray , Ankur N. Shah , Lakshminarayanan Striramassarma , Prasoonkumar Surti , Saurabh Tangri
IPC: G06F15/78 , G06F7/544 , G06F7/575 , G06F7/58 , G06F9/30 , G06F9/38 , G06F9/50 , G06F12/02 , G06F12/06 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/80 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06N3/08 , G06T15/06
CPC classification number: G06F15/7839 , G06F7/5443 , G06F7/575 , G06F7/588 , G06F9/3001 , G06F9/30014 , G06F9/30036 , G06F9/3004 , G06F9/30043 , G06F9/30047 , G06F9/30065 , G06F9/30079 , G06F9/3887 , G06F9/5011 , G06F9/5077 , G06F12/0215 , G06F12/0238 , G06F12/0246 , G06F12/0607 , G06F12/0802 , G06F12/0804 , G06F12/0811 , G06F12/0862 , G06F12/0866 , G06F12/0871 , G06F12/0875 , G06F12/0882 , G06F12/0888 , G06F12/0891 , G06F12/0893 , G06F12/0895 , G06F12/0897 , G06F12/1009 , G06F12/128 , G06F15/8046 , G06F17/16 , G06F17/18 , G06T1/20 , G06T1/60 , H03M7/46 , G06F9/3802 , G06F9/3818 , G06F9/3867 , G06F2212/1008 , G06F2212/1021 , G06F2212/1044 , G06F2212/302 , G06F2212/401 , G06F2212/455 , G06F2212/60 , G06N3/08 , G06T15/06
Abstract: Embodiments are generally directed to graphics processor data access and sharing. An embodiment of an apparatus includes a circuit element to produce a result in processing of an application; a load-store unit to receive the result and generate pre-fetch information for a cache utilizing the result; and a prefetch generator to produce prefetch addresses based at least in part on the pre-fetch information; wherein the load-store unit is to receive software assistance for prefetching, and wherein generation of the pre-fetch information is based at least in part on the software assistance.
-
公开(公告)号：US20230297339A1
公开(公告)日：2023-09-21
申请号：US18013916
申请日：2021-07-05
Applicant: Semiconductor Energy Laboratory Co., Ltd.
Inventor： Yuki OKAMOTO , Minato ITO , Munehiro KOZUMA
IPC: G06F7/575 , G11C11/405 , H10B12/00
CPC classification number: G06F7/575 , G11C11/405 , H10B12/00
Abstract: A semiconductor device with a novel structure is provided. A first memory circuit portion includes a first memory circuit for retaining a plurality of pieces of first weight data. A second memory circuit portion includes a second memory circuit for retaining a plurality of pieces of second weight data. A first arithmetic circuit portion includes a first arithmetic circuit, a first switching circuit, and a third switching circuit. A second arithmetic circuit portion includes a second arithmetic circuit, a second switching circuit, and a fourth switching circuit. The first switching circuit has a function of supplying any one of the plurality of pieces of the first weight data to a first wiring. The second switching circuit has a function of supplying any one of the plurality of pieces of the second weight data to a second wiring. The third switching circuit has a function of supplying to the first arithmetic circuit the first weight data supplied to the first wiring or the second weight data supplied to the second wiring. The fourth switching circuit has a function of supplying to the second arithmetic circuit the first weight data supplied to the first wiring or the second weight data supplied to the second wiring.
