-
1.
公开(公告)号:US20240303217A1
公开(公告)日:2024-09-12
申请号:US18661457
申请日:2024-05-10
申请人: Mythic, Inc.
发明人: David Fick , Malav Parikh , Paul Toth , Adam Caughron , Vimal Reddy , Erik Schlanger , Sergio Schuler , Zainab Nasreen Zaidi , Alex Dang-Tran , Raul Garibay , Bryant Sorensen
IPC分类号: G06F15/78 , G06F9/38 , G06F15/173 , G06F17/16 , H04L45/00
CPC分类号: G06F15/7825 , G06F9/3887 , G06F15/173 , G06F15/17337 , G06F15/7814 , G06F17/16 , H04L45/34 , H04L45/38
摘要: A system and method for automated data propagation and automated data processing within an integrated circuit includes an intelligence processing integrated circuit comprising at least one intelligence processing pipeline, wherein the at least one intelligence processing pipeline includes: a main data buffer that stores input data; a plurality of distinct intelligence processing tiles, wherein each distinct intelligence processing tile includes a computing circuit and a local data buffer; a token-based governance module, the token-based governance module implementing: a first token-based control data structure; a second token-based control data structure, wherein the first token-based control data structure and the second-token based control data operate in cooperation to control an automated flow of the input data and/or an automated processing of the input data through the at least one intelligence processing pipeline.
-
公开(公告)号:US11360932B2
公开(公告)日:2022-06-14
申请号:US16790240
申请日:2020-02-13
申请人: Mythic, Inc.
发明人: David Fick , Malav Parikh , Paul Toth , Adam Caughron , Vimal Reddy , Erik Schlanger , Sergio Schuler , Zainab Nasreen Zaidi , Alex Dang-Tran , Raul Garibay , Bryant Sorensen
IPC分类号: G06F15/78 , G06F15/173 , G06F17/16 , H04L45/00 , G06F9/38
摘要: A system and method for automated data propagation and automated data processing within an integrated circuit includes an intelligence processing integrated circuit comprising at least one intelligence processing pipeline, wherein the at least one intelligence processing pipeline includes: a main data buffer that stores input data; a plurality of distinct intelligence processing tiles, wherein each distinct intelligence processing tile includes a computing circuit and a local data buffer; a token-based governance module, the token-based governance module implementing: a first token-based control data structure; a second token-based control data structure, wherein the first token-based control data structure and the second-token based control data operate in cooperation to control an automated flow of the input data and/or an automated processing of the input data through the at least one intelligence processing pipeline.
-
3.
公开(公告)号:US20240311194A1
公开(公告)日:2024-09-19
申请号:US18672842
申请日:2024-05-23
申请人: Mythic, Inc.
发明人: Malav Parikh , Sergio Schuler , Vimal Reddy , Zainab Zaidi , Paul Toth , Adam Caughron , Bryant Sorensen , Alex Dang-Tran , Scott Johnson , Raul Garibay , Andrew Morten , David Fick
CPC分类号: G06F9/5027 , G06F9/4843 , G06N3/045 , G06F7/5443 , G06F7/57 , G06F9/3001 , G06F9/5061 , G06F15/7807
摘要: A system and method for a computing tile of a multi-tiled integrated circuit includes a plurality of distinct tile computing circuits, wherein each of the plurality of distinct tile computing circuits is configured to receive fixed-length instructions; a token-informed task scheduler that: tracks one or more of a plurality of distinct tokens emitted by one or more of the plurality of distinct tile computing circuits; and selects a distinct computation task of a plurality of distinct computation tasks based on the tracking; and a work queue buffer that: contains a plurality of distinct fixed-length instructions, wherein each one of the fixed-length instructions is associated with one of the plurality of distinct computation tasks; and transmits one of the plurality of distinct fixed-length instructions to one or more of the plurality of distinct tile computing circuits based on the selection of the distinct computation task by the token-informed task scheduler.
-
公开(公告)号:US20210232435A1
公开(公告)日:2021-07-29
申请号:US17231089
申请日:2021-04-15
申请人: Mythic, Inc.
发明人: Malav Parikh , Sergio Schuler , Vimal Reddy , Zainab Zaidi , Paul Toth , Adam Caughron , Bryant Sorensen , Alex Dang-Tran , Scott Johnson , Raul Garibay , Andrew Morten , David Fick
摘要: A system and method for a computing tile of a multi-tiled integrated circuit includes a plurality of distinct tile computing circuits, wherein each of the plurality of distinct tile computing circuits is configured to receive fixed-length instructions; a token-informed task scheduler that: tracks one or more of a plurality of distinct tokens emitted by one or more of the plurality of distinct tile computing circuits; and selects a distinct computation task of a plurality of distinct computation tasks based on the tracking; and a work queue buffer that: contains a plurality of distinct fixed-length instructions, wherein each one of the fixed-length instructions is associated with one of the plurality of distinct computation tasks; and transmits one of the plurality of distinct fixed-length instructions to one or more of the plurality of distinct tile computing circuits based on the selection of the distinct computation task by the token-informed task scheduler.
-
公开(公告)号:US20210157648A1
公开(公告)日:2021-05-27
申请号:US17102643
申请日:2020-11-24
申请人: Mythic, Inc.
发明人: Malav Parikh , Sergio Schuler , Vimal Reddy , Zainab Zaidi , Paul Toth , Adam Caughron , Bryant Sorensen , Alexander Dang-Tran , Scott Johnson , Raul Garibay , Andrew Morten , David Fick
摘要: A system and method for a computing tile of a multi-tiled integrated circuit includes a plurality of distinct tile computing circuits, wherein each of the plurality of distinct tile computing circuits is configured to receive fixed-length instructions; a token-informed task scheduler that: tracks one or more of a plurality of distinct tokens emitted by one or more of the plurality of distinct tile computing circuits; and selects a distinct computation task of a plurality of distinct computation tasks based on the tracking; and a work queue buffer that: contains a plurality of distinct fixed-length instructions, wherein each one of the fixed-length instructions is associated with one of the plurality of distinct computation tasks; and transmits one of the plurality of distinct fixed-length instructions to one or more of the plurality of distinct tile computing circuits based on the selection of the distinct computation task by the token-informed task scheduler.
-
公开(公告)号:US20220276983A1
公开(公告)日:2022-09-01
申请号:US17745742
申请日:2022-05-16
申请人: Mythic, Inc.
发明人: David Fick , Malav Parikh , Paul Toth , Adam Caughron , Vimal Reddy , Erik Schlanger , Sergio Schuler , Zainab Nasreen Zaidi , Alex Dang-Tran , Raul Garibay , Bryant Sorensen
IPC分类号: G06F15/78 , G06F15/173 , G06F17/16 , H04L45/00 , G06F9/38
摘要: A system and method for automated data propagation and automated data processing within an integrated circuit includes an intelligence processing integrated circuit comprising at least one intelligence processing pipeline, wherein the at least one intelligence processing pipeline includes: a main data buffer that stores input data; a plurality of distinct intelligence processing tiles, wherein each distinct intelligence processing tile includes a computing circuit and a local data buffer; a token-based governance module, the token-based governance module implementing: a first token-based control data structure; a second token-based control data structure, wherein the first token-based control data structure and the second-token based control data operate in cooperation to control an automated flow of the input data and/or an automated processing of the input data through the at least one intelligence processing pipeline.
-
公开(公告)号:US11016810B1
公开(公告)日:2021-05-25
申请号:US17102643
申请日:2020-11-24
申请人: Mythic, Inc.
发明人: Malav Parikh , Sergio Schuler , Vimal Reddy , Zainab Zaidi , Paul Toth , Adam Caughron , Bryant Sorensen , Alex Dang-Tran , Scott Johnson , Raul Garibay , Andrew Morten , David Fick
IPC分类号: G06F9/48 , G06F9/50 , G06F7/57 , G06F15/76 , G06F9/302 , G06N3/04 , G06F7/544 , G06F15/78 , G06F9/30
摘要: A system and method for a computing tile of a multi-tiled integrated circuit includes a plurality of distinct tile computing circuits, wherein each of the plurality of distinct tile computing circuits is configured to receive fixed-length instructions; a token-informed task scheduler that: tracks one or more of a plurality of distinct tokens emitted by one or more of the plurality of distinct tile computing circuits; and selects a distinct computation task of a plurality of distinct computation tasks based on the tracking; and a work queue buffer that: contains a plurality of distinct fixed-length instructions, wherein each one of the fixed-length instructions is associated with one of the plurality of distinct computation tasks; and transmits one of the plurality of distinct fixed-length instructions to one or more of the plurality of distinct tile computing circuits based on the selection of the distinct computation task by the token-informed task scheduler.
-
8.
公开(公告)号:US20200012617A1
公开(公告)日:2020-01-09
申请号:US16458917
申请日:2019-07-01
申请人: Mythic, Inc.
发明人: David Fick , Malav Parikh , Paul Toth , Adam Caughron , Vimal Reddy , Erik Schlanger , Sergio Schuler , Zainab Nasreen Zaidi , Alex Dang-Tran , Raul Garibay , Bryant Sorensen
IPC分类号: G06F15/78 , G06F15/173 , G06F17/16 , H04L12/721 , G06F9/38
摘要: Systems and methods include an integrated circuit that includes a plurality of computing tiles, wherein each of the plurality of computing tiles includes: a matrix multiply accelerator, a computing processing circuit; and a flow scoreboard module; a local data buffer, wherein the plurality of computing tiles together define an intelligence processing array; a network-on-chip system comprising: a plurality of network-on-chip routers establishing a communication network among the plurality of computing tiles, wherein each network-on-chip router is in operable communication connection with at least one of the plurality of computing tiles and a distinct network-on-chip router of the plurality of network-on-chip routers; and an off-tile buffer that is arranged in remote communication with the plurality of computing tiles, wherein the off-tile buffer stores raw input data and/or data received from an upstream process or an upstream device.
-
公开(公告)号:US10521395B1
公开(公告)日:2019-12-31
申请号:US16458917
申请日:2019-07-01
申请人: Mythic, Inc.
发明人: David Fick , Malav Parikh , Paul Toth , Adam Caughron , Vimal Reddy , Erik Schlanger , Sergio Schuler , Zainab Nasreen Zaidi , Alex Dang-Tran , Raul Garibay , Bryant Sorensen
IPC分类号: G06F15/78 , G06F15/173 , G06F9/38 , H04L12/721 , G06F17/16
摘要: Systems and methods include an integrated circuit that includes a plurality of computing tiles, wherein each of the plurality of computing tiles includes: a matrix multiply accelerator, a computing processing circuit; and a flow scoreboard module; a local data buffer, wherein the plurality of computing tiles together define an intelligence processing array; a network-on-chip system comprising: a plurality of network-on-chip routers establishing a communication network among the plurality of computing tiles, wherein each network-on-chip router is in operable communication connection with at least one of the plurality of computing tiles and a distinct network-on-chip router of the plurality of network-on-chip routers; and an off-tile buffer that is arranged in remote communication with the plurality of computing tiles, wherein the off-tile buffer stores raw input data and/or data received from an upstream process or an upstream device.
-
公开(公告)号:US12014214B2
公开(公告)日:2024-06-18
申请号:US17231089
申请日:2021-04-15
申请人: Mythic, Inc.
发明人: Malav Parikh , Sergio Schuler , Vimal Reddy , Zainab Zaidi , Paul Toth , Adam Caughron , Bryant Sorensen , Alex Dang-Tran , Scott Johnson , Raul Garibay , Andrew Morten , David Fick
CPC分类号: G06F9/5027 , G06F9/4843 , G06N3/045 , G06F7/5443 , G06F7/57 , G06F9/3001 , G06F9/5061 , G06F15/7807
摘要: A system and method for a computing tile of a multi-tiled integrated circuit includes a plurality of distinct tile computing circuits, wherein each of the plurality of distinct tile computing circuits is configured to receive fixed-length instructions; a token-informed task scheduler that: tracks one or more of a plurality of distinct tokens emitted by one or more of the plurality of distinct tile computing circuits; and selects a distinct computation task of a plurality of distinct computation tasks based on the tracking; and a work queue buffer that: contains a plurality of distinct fixed-length instructions, wherein each one of the fixed-length instructions is associated with one of the plurality of distinct computation tasks; and transmits one of the plurality of distinct fixed-length instructions to one or more of the plurality of distinct tile computing circuits based on the selection of the distinct computation task by the token-informed task scheduler.
-
-
-
-
-
-
-
-
-