Memory shuffle engine for efficient work execution in a parallel computing system

    公开(公告)号:US10324730B2

    公开(公告)日:2019-06-18

    申请号:US15285472

    申请日:2016-10-04

    Applicant: MediaTek Inc.

    Abstract: A computing device performs parallel computations using a set of thread processing units and a memory shuffle engine. The memory shuffle engine includes a register array to store an array of data elements retrieved from a memory buffer, and an array of input selectors. According to a first control signal, each input selector transfers at least a first data element from a corresponding subset of the register array, which is coupled to the input selector via input lines, to one or more corresponding thread processing units. According to a second control signal, each input selector transfers at least a second data element from another subset of the register array, which is coupled to another input selector via other input lines, to the one or more corresponding thread processing units.

    HETEROGENEOUS COMPUTING SYSTEM WITH A SHARED COMPUTING UNIT AND SEPARATE MEMORY CONTROLS

    公开(公告)号:US20170262291A1

    公开(公告)日:2017-09-14

    申请号:US15065447

    申请日:2016-03-09

    Applicant: MediaTek Inc.

    CPC classification number: G06F9/50 G06F9/3877

    Abstract: A heterogeneous computing system described herein includes a parallel processing module shared among a set of heterogeneous processors. The processors have different processor types, and each processor includes an internal memory unit to store its current context. The parallel processing module includes multiple execution units. A switch module is coupled to the processors and the parallel processing module. The switch module is operative to select, according to a control signal, one of the processors to use the parallel processing module for executing an instruction with multiple data entries in parallel.

    Efficient work execution in a parallel computing system

    公开(公告)号:US11175920B2

    公开(公告)日:2021-11-16

    申请号:US16395193

    申请日:2019-04-25

    Applicant: MediaTek Inc.

    Abstract: A computing device operative to perform parallel computations. The computing device includes a controller unit to assign workgroups to a set of batches. Each batch includes a program counter shared by M workgroups assigned to the batch, where M is a positive integer determined according to a configurable batch setting. Each batch further includes a set of thread processing units operative to execute, in parallel, a subset of work items in each of the M workgroups. Each batch further includes a spilling memory to store intermediate data of the M workgroups when one or more workgroups in the M workgroups encounters a synchronization barrier.

    Graphics-processing method of a graphics-processing unit and graphics-processing apparatus

    公开(公告)号:US09836869B2

    公开(公告)日:2017-12-05

    申请号:US15075050

    申请日:2016-03-18

    Applicant: MediaTek Inc.

    CPC classification number: G06T15/005 G06T11/40

    Abstract: A graphics-processing method and a graphics-processing apparatus are provided. The graphics-processing method includes the steps of computing a vertex position of a vertex in a binning phase to obtain a first position data; generating a first signal according to a first condition, wherein when the first signal corresponds to a first value, the first position data is stored into a memory unit, and when the first signal corresponds to a second value, the vertex position of the vertex in a rendering phase is computed to obtain a second position data; computing a vertex varying of the vertex in the binning phase or the rendering phase; and rendering in the rendering phase according to either the first position data or the second position data.

    EFFICIENT WORK EXECUTION IN A PARALLEL COMPUTING SYSTEM

    公开(公告)号:US20170277567A1

    公开(公告)日:2017-09-28

    申请号:US15285472

    申请日:2016-10-04

    Applicant: MediaTek Inc.

    Abstract: A computing device performs parallel computations using a set of thread processing units and a memory shuffle engine. The memory shuffle engine includes a register array to store an array of data elements retrieved from a memory buffer, and an array of input selectors. According to a first control signal, each input selector transfers at least a first data element from a corresponding subset of the register array, which is coupled to the input selector via input lines, to one or more corresponding thread processing units. According to a second control signal, each input selector transfers at least a second data element from another subset of the register array, which is coupled to another input selector via other input lines, to the one or more corresponding thread processing units.

    ADAPTIVE EXECUTION ENGINE FOR CONVOLUTION COMPUTING SYSTEMS

    公开(公告)号:US20180173676A1

    公开(公告)日:2018-06-21

    申请号:US15787897

    申请日:2017-10-19

    Applicant: MediaTek Inc.

    CPC classification number: G06F17/15 G06F17/16 G06N3/0454 G06N3/063

    Abstract: A system performs convolution computing in either a matrix mode or a filter mode. An analysis module generates a mode select signal to select the matrix mode or the filter mode based on results of analyzing convolution characteristics. The results include at least a comparison of resource utilization between the matrix mode and the filter mode. A convolution module includes processing elements, each of which further includes arithmetic computing circuitry. The convolution module is configured according to the matrix mode for performing matrix multiplications converted from convolution computations, and is configured according to the filter mode for performing the convolution computations.

    GRAPHICS PROCESSING METHOD AND GRAPHICS PROCESSING APPARATUS
    9.
    发明申请
    GRAPHICS PROCESSING METHOD AND GRAPHICS PROCESSING APPARATUS 有权
    图形处理方法和图形处理装置

    公开(公告)号:US20150332495A1

    公开(公告)日:2015-11-19

    申请号:US14675759

    申请日:2015-04-01

    Applicant: MEDIATEK INC.

    CPC classification number: G06T15/005 G06T11/40

    Abstract: A graphics processing method and an associated graphics processing apparatus are provided, where the graphics processing method is applied to the graphics processing apparatus, the graphics processing apparatus may be positioned within an electronic device, and the graphics processing apparatus may comprise at least one portion of the electronic device. The graphics processing method includes the steps of: calculating vertex positions of a primitive in a binning phase; determining, according to specific information, whether to compute vertex varyings of the primitive in the binning phase or in a rendering phase so as to provide a determination result; computing the vertex varyings in the binning phase or in the rendering phase according to the determination result; and rendering the primitive according to the vertex positions and the vertex varyings in the rendering phase.

    Abstract translation: 提供了图形处理方法和相关联的图形处理装置,其中将图形处理方法应用于图形处理装置,图形处理装置可以位于电子装置内,并且图形处理装置可以包括至少一部分 电子设备。 图形处理方法包括以下步骤:计算合并阶段中原语的顶点位置; 根据具体信息确定是否计算合并阶段或渲染阶段中的原语的顶点变化,以便提供确定结果; 根据确定结果计算合并阶段或渲染阶段中的顶点变化; 并根据渲染阶段中的顶点位置和顶点变化渲染图元。

    Adaptive execution engine for convolution computing systems

    公开(公告)号:US10394929B2

    公开(公告)日:2019-08-27

    申请号:US15787897

    申请日:2017-10-19

    Applicant: MediaTek Inc.

    Abstract: A system performs convolution computing in either a matrix mode or a filter mode. An analysis module generates a mode select signal to select the matrix mode or the filter mode based on results of analyzing convolution characteristics. The results include at least a comparison of resource utilization between the matrix mode and the filter mode. A convolution module includes processing elements, each of which further includes arithmetic computing circuitry. The convolution module is configured according to the matrix mode for performing matrix multiplications converted from convolution computations, and is configured according to the filter mode for performing the convolution computations.

Patent Agency Ranking