-
公开(公告)号：US11288095B2
公开(公告)日：2022-03-29
申请号：US16588872
申请日：2019-09-30
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Matthew D. Sinclair , Bradford M. Beckmann , David A. Wood
Abstract: A technique for synchronizing workgroups is provided. The techniques comprise detecting that one or more non-executing workgroups are ready to execute, placing the one or more non-executing workgroups into one or more ready queues based on the synchronization status of the one or more workgroups, detecting that computing resources are available for execution of one or more ready workgroups, and scheduling for execution one or more ready workgroups from the one or more ready queues in an order that is based on the relative priority of the ready queues.
-
公开(公告)号：US11150899B2
公开(公告)日：2021-10-19
申请号：US15948795
申请日：2018-04-09
Applicant: Advanced Micro Devices, Inc.
Inventor： Anthony T. Gutierrez , Sergey Blagodurov , Scott A. Moe , Xianwei Zhang , Jieming Yin , Matthew D. Sinclair
Abstract: An electronic device includes a controller functional block and a computational functional block. During operation, while the computational functional block executes a test portion of a workload at at least one precision level, the controller functional block monitors a behavior of the computational functional block. Based on the behavior of the computational functional block while executing the test portion of the workload at the at least one precision level, the controller functional block selects a given precision level from among a set of two or more precision levels at which the computational functional block is to execute a remaining portion of the workload. The controller functional block then configures the computational block to execute the remaining portion of the workload at the given precision level.
-
公开(公告)号：US20210096909A1
公开(公告)日：2021-04-01
申请号：US16588872
申请日：2019-09-30
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Matthew D. Sinclair , Bradford M. Beckmann , David A. Wood
Abstract: A technique for synchronizing workgroups is provided. The techniques comprise detecting that one or more non-executing workgroups are ready to execute, placing the one or more non-executing workgroups into one or more ready queues based on the synchronization status of the one or more workgroups, detecting that computing resources are available for execution of one or more ready workgroups, and scheduling for execution one or more ready workgroups from the one or more ready queues in an order that is based on the relative priority of the ready queues.
-
公开(公告)号：US20240045718A1
公开(公告)日：2024-02-08
申请号：US18488794
申请日：2023-10-17
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Marcus Nathaniel Chow , Matthew D. Sinclair , Bradford M. Beckmann , David A. Wood
CPC classification number: G06F9/4881 , G06F9/545 , G06F9/3838
Abstract: Techniques for executing workgroups are provided. The techniques include executing, for a first workgroup of a first kernel dispatch, a workgroup dependency instruction that includes an indication to prioritize execution of a second workgroup of a second kernel dispatch, and in response to the workgroup dependency instruction, dispatching the second workgroup of the second kernel dispatch prior to dispatching a third workgroup of the second kernel dispatch, wherein no workgroup dependency instruction including an indication to prioritize execution of the third workgroup has been executed.
-
公开(公告)号：US20200379820A1
公开(公告)日：2020-12-03
申请号：US16425881
申请日：2019-05-29
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Sergey Blagodurov , Anthony T. Gutierrez , Matthew D. Sinclair , David A. Wood , Bradford M. Beckmann
Abstract: A technique for synchronizing workgroups is provided. Multiple workgroups execute a wait instruction that specifies a condition variable and a condition. A workgroup scheduler stops execution of a workgroup that executes a wait instruction and an advanced controller begins monitoring the condition variable. In response to the advanced controller detecting that the condition is met, the workgroup scheduler determines whether there is a high contention scenario, which occurs when the wait instruction is part of a mutual exclusion synchronization primitive and is detected by determining that there is a low number of updates to the condition variable prior to detecting that the condition has been met. In a high contention scenario, the workgroup scheduler wakes up one workgroup and schedules another workgroup to be woken up at a time in the future. In a non-contention scenario, more than one workgroup can be woken up at the same time.
-
公开(公告)号：US11809902B2
公开(公告)日：2023-11-07
申请号：US17031424
申请日：2020-09-24
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Marcus Nathaniel Chow , Matthew D. Sinclair , Bradford M. Beckmann , David A. Wood
CPC classification number: G06F9/4881 , G06F9/3838 , G06F9/545
Abstract: Techniques for executing workgroups are provided. The techniques include executing, for a first workgroup of a first kernel dispatch, a workgroup dependency instruction that includes an indication to prioritize execution of a second workgroup of a second kernel dispatch, and in response to the workgroup dependency instruction, dispatching the second workgroup of the second kernel dispatch prior to dispatching a third workgroup of the second kernel dispatch, wherein no workgroup dependency instruction including an indication to prioritize execution of the third workgroup has been executed.
-
公开(公告)号：US20220091880A1
公开(公告)日：2022-03-24
申请号：US17031424
申请日：2020-09-24
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Marcus Nathaniel Chow , Matthew D. Sinclair , Bradford M. Beckmann , David A. Wood
Abstract: Techniques for executing workgroups are provided. The techniques include executing, for a first workgroup of a first kernel dispatch, a workgroup dependency instruction that includes an indication to prioritize execution of a second workgroup of a second kernel dispatch, and in response to the workgroup dependency instruction, dispatching the second workgroup of the second kernel dispatch prior to dispatching a third workgroup of the second kernel dispatch, wherein no workgroup dependency instruction including an indication to prioritize execution of the third workgroup has been executed.
-
公开(公告)号：US12190174B2
公开(公告)日：2025-01-07
申请号：US16425881
申请日：2019-05-29
Applicant: Advanced Micro Devices, Inc.
Inventor： Alexandru Dutu , Sergey Blagodurov , Anthony T. Gutierrez , Matthew D. Sinclair , David A. Wood , Bradford M. Beckmann
Abstract: A technique for synchronizing workgroups is provided. Multiple workgroups execute a wait instruction that specifies a condition variable and a condition. A workgroup scheduler stops execution of a workgroup that executes a wait instruction and an advanced controller begins monitoring the condition variable. In response to the advanced controller detecting that the condition is met, the workgroup scheduler determines whether there is a high contention scenario, which occurs when the wait instruction is part of a mutual exclusion synchronization primitive and is detected by determining that there is a low number of updates to the condition variable prior to detecting that the condition has been met. In a high contention scenario, the workgroup scheduler wakes up one workgroup and schedules another workgroup to be woken up at a time in the future. In a non-contention scenario, more than one workgroup can be woken up at the same time.
-
公开(公告)号：US20190310864A1
公开(公告)日：2019-10-10
申请号：US15948795
申请日：2018-04-09
Applicant: Advanced Micro Devices, Inc.
Inventor： Anthony T. Gutierrez , Sergey Blagodurov , Scott A. Moe , Xianwei Zhang , Jieming Yin , Matthew D. Sinclair
Abstract: An electronic device includes a controller functional block and a computational functional block. During operation, while the computational functional block executes a test portion of a workload at at least one precision level, the controller functional block monitors a behavior of the computational functional block. Based on the behavior of the computational functional block while executing the test portion of the workload at the at least one precision level, the controller functional block selects a given precision level from among a set of two or more precision levels at which the computational functional block is to execute a remaining portion of the workload. The controller functional block then configures the computational block to execute the remaining portion of the workload at the given precision level.
