公开(公告)号：US11741019B2

公开(公告)日：2023-08-29

申请号：US17471552

申请日：2021-09-10

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/10 ,  G06F12/1036 ,  G06F12/08 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109

CPC classification number: G06F12/1036 ,  G06F12/0284 ,  G06F12/0646 ,  G06F12/08 ,  G06F12/109 ,  G06F12/10 ,  G06F2212/1012 ,  G06F2212/152 ,  G06F2212/656 ,  G06F2212/657

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a plurality of processors. The method includes receiving a memory operation from a processor that references an address in a shared memory, mapping the received memory operation to at least one virtual memory pool to produce a mapping result, and providing the mapping result to the processor.

公开(公告)号：US10324860B2

公开(公告)日：2019-06-18

申请号：US15695683

申请日：2017-09-05

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/10 ,  G06F12/1036 ,  G06F12/08 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a first processor configured for unified operation with a second processor. The method includes receiving a memory operation from a processor and mapping the memory operation to one of a plurality of memory heaps. The mapping produces a mapping result. The method also includes providing the mapping result to the processor.

公开(公告)号：US20160364334A1

公开(公告)日：2016-12-15

申请号：US15246056

申请日：2016-08-24

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/0815 ,  G06F12/0804

CPC classification number: G06F12/0815 ,  G06F12/0804 ,  G06F12/0806 ,  G06F12/0835 ,  G06F12/0837 ,  G06F12/0848 ,  G06F2212/1021 ,  G06F2212/1024 ,  G06F2212/283 ,  G06F2212/608 ,  Y02D10/13

Abstract: Existing multiprocessor computing systems often have insufficient memory coherency and, consequently, are unable to efficiently utilize separate memory systems. Specifically, a CPU cannot effectively write to a block of memory and then have a GPU access that memory unless there is explicit synchronization. In addition, because the GPU is forced to statically split memory locations between itself and the CPU, existing multiprocessor computing systems are unable to efficiently utilize the separate memory systems. Embodiments described herein overcome these deficiencies by receiving a notification within the GPU that the CPU has finished processing data that is stored in coherent memory, and invalidating data in the CPU caches that the GPU has finished processing from the coherent memory. Embodiments described herein also include dynamically partitioning a GPU memory into coherent memory and local memory through use of a probe filter.

Abstract translation: 现有的多处理器计算系统通常具有不足的存储器一致性，因此不能有效地利用单独的存储器系统。 具体来说，CPU无法有效地写入内存块，然后除了有明确的同步之外，还可以对存储器进行GPU访问。 另外，由于GPU被迫静态分割其本身与CPU之间的存储器位置，所以现有的多处理器计算系统不能有效地利用单独的存储器系统。 本文所描述的实施例通过在GPU内接收到通知，CPU已经完成处理存储在相干存储器中的数据，并使CPU缓冲器中的数据无效，GPU已经从相干存储器完成处理来克服这些缺陷。 本文描述的实施例还包括通过使用探针滤波器来将GPU存储器动态地划分为相干存储器和本地存储器。

公开(公告)号：US09448930B2

公开(公告)日：2016-09-20

申请号：US14833850

申请日：2015-08-24

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/02 ,  G06F12/08 ,  G06F12/06 ,  G06F12/10

CPC classification number: G06F12/1036 ,  G06F12/0284 ,  G06F12/0646 ,  G06F12/08 ,  G06F12/10 ,  G06F12/109 ,  G06F2212/1012 ,  G06F2212/152 ,  G06F2212/656 ,  G06F2212/657

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a first processor configured for unified operation with a second processor. The method includes receiving a memory operation from a processor and mapping the memory operation to one of a plurality of memory heaps. The mapping produces a mapping result. The method also includes providing the mapping result to the processor.

公开(公告)号：US20230401159A1

公开(公告)日：2023-12-14

申请号：US18455479

申请日：2023-08-24

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/1036 ,  G06F12/08 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109

CPC classification number: G06F12/1036 ,  G06F12/08 ,  G06F12/0646 ,  G06F12/0284 ,  G06F12/109 ,  G06F12/10

Abstract: A method and system for providing memory in a computer system. The method includes receiving a memory access request for a shared memory address from a processor, mapping the received memory access request to at least one virtual memory pool to produce a mapping result, and providing the mapping result to the processor.

公开(公告)号：US09965392B2

公开(公告)日：2018-05-08

申请号：US15246056

申请日：2016-08-24

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/00 ,  G06F13/00 ,  G06F13/28 ,  G06F12/0815 ,  G06F12/0806 ,  G06F12/0831 ,  G06F12/0846 ,  G06F12/0837 ,  G06F12/0804

CPC classification number: G06F12/0815 ,  G06F12/0804 ,  G06F12/0806 ,  G06F12/0835 ,  G06F12/0837 ,  G06F12/0848 ,  G06F2212/1021 ,  G06F2212/1024 ,  G06F2212/283 ,  G06F2212/608 ,  Y02D10/13

Abstract: Existing multiprocessor computing systems often have insufficient memory coherency and, consequently, are unable to efficiently utilize separate memory systems. Specifically, a CPU cannot effectively write to a block of memory and then have a GPU access that memory unless there is explicit synchronization. In addition, because the GPU is forced to statically split memory locations between itself and the CPU, existing multiprocessor computing systems are unable to efficiently utilize the separate memory systems. Embodiments described herein overcome these deficiencies by receiving a notification within the GPU that the CPU has finished processing data that is stored in coherent memory, and invalidating data in the CPU caches that the GPU has finished processing from the coherent memory. Embodiments described herein also include dynamically partitioning a GPU memory into coherent memory and local memory through use of a probe filter.

公开(公告)号：US20210406196A1

公开(公告)日：2021-12-30

申请号：US17471552

申请日：2021-09-10

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/1036 ,  G06F12/08 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a plurality of processors. The method includes receiving a memory operation from a processor that references an address in a shared memory, mapping the received memory operation to at least one virtual memory pool to produce a mapping result, and providing the mapping result to the processor.

公开(公告)号：US11119944B2

公开(公告)日：2021-09-14

申请号：US16443385

申请日：2019-06-17

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/10 ,  G06F12/1036 ,  G06F12/08 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a plurality of processors. The method includes receiving a memory operation from a processor that receives a memory operation from a processor that references an address in a shared memory, mapping the received memory operation to at least one of a plurality of virtual memory pools to produce a mapping result, and providing the mapping result to the processor.

公开(公告)号：US20190303302A1

公开(公告)日：2019-10-03

申请号：US16443385

申请日：2019-06-17

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/1036 ,  G06F12/06 ,  G06F12/02 ,  G06F12/109 ,  G06F12/08

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a plurality of processors. The method includes receiving a memory operation from a processor that receives a memory operation from a processor that references an address in a shared memory, mapping the received memory operation to at least one of a plurality of virtual memory pools to produce a mapping result, and providing the mapping result to the processor.

公开(公告)号：US09116809B2

公开(公告)日：2015-08-25

申请号：US13724879

申请日：2012-12-21

Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

Inventor： Anthony Asaro ,  Kevin Normoyle ,  Mark Hummel

IPC: G06F12/02 ,  G06F12/08 ,  G06F12/06 ,  G06F12/10

CPC classification number: G06F12/1036 ,  G06F12/0284 ,  G06F12/0646 ,  G06F12/08 ,  G06F12/10 ,  G06F12/109 ,  G06F2212/1012 ,  G06F2212/152 ,  G06F2212/656 ,  G06F2212/657

Abstract: A method and system for allocating memory to a memory operation executed by a processor in a computer arrangement having a first processor configured for unified operation with a second processor. The method includes receiving a memory operation from a processor and mapping the memory operation to one of a plurality of memory heaps. The mapping produces a mapping result. The method also includes providing the mapping result to the processor.

Abstract translation: 一种用于将计算机装置中的处理器执行的存储器操作分配给存储器的方法和系统，所述计算机装置具有配置成与第二处理器统一操作的第一处理器 该方法包括从处理器接收存储器操作并将存储器操作映射到多个存储器堆中的一个。 映射生成映射结果。 该方法还包括向处理器提供映射结果。