12 results about "Workgroup" patented technology

Policy-based genomic digital data sharing facilitates a variety of sharing scenarios, including public access, tenant-to-tenant sharing, workgroup sharing, and access by external service providers. Genomic digital data can be published to the platform and controlled by access tokens that are generated based on access policies. The policies can support conditions that are evaluated at execution time and effectively place control of access to information in hands of the owning tenant. Sharing conditions can be easily specified to support various use cases, relieving administrators from excessive access control configuration.

The present disclosure provides a data processing method and device, electronic equipment and computer readable storage medium, the method comprising: sending reduction request information to a reduction processing unit by a computing unit, the reduction request information comprising reduction mark information and reduction data attribute information; determining a target workgroup from the computing unit according to the reduction mark information by the reduction processing unit, reading reduction data from the to-be-processed data of the data storage unit corresponding to the target workgroup according to the reduction data attribute information, and performing reduction processing on the read reduction data to obtain a reduction result. Through the above technical solution, the data can be read from different types of storage during the reduction operation, resulting in low efficiency of data reduction.

Cloud provider accounts can be integrated into a software-as-a-service platform. Configuration options can be provided to support various levels of granularity so that different cloud provider accounts can be provided to different tenants, workgroups, users, applications, and the like. From a user perspective, the fact that data is being stored at a cloud provider account can be transparent in that the same features and authentication process can be supported across different cloud provider types. In practice, limited temporary derived credentials can be generated from underlying credentials to provide fine-grained control of access to cloud provider account resources while avoiding administrative overhead.

A processing unit and method for multiplying a sparse matrix (W) and a dense matrix (X)to determine an output matrix (Y). An execution module executes threads of a workgroup, the threads are allocated

1. Name of the product in this design: Circuit board with heat sink. 2. Purpose of this design: As a working component in a data processing server, specifically a circuit board with a heat sink. 3. The key design feature of this product is its shape. 4. The picture or photo that best illustrates the key design points: Design 1 3D diagram 1. 5. Design 1 is designated as the basic design.

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.

An accelerator unit (AU) includes a compute unit configured to execute a first workgroup of a first kernel and a set of compute unit resources allocated to the first workgroup. Concurrently with the compute unit executing the first workgroup, a scheduling circuitry of the AU receives a resource termination hint indicating that the first workgroup is going to end the use of portions of compute unit resources allocated to the first workgroup. In response to this resource termination hint, the scheduling circuitry provisionally allocates these portions of compute unit resources to a second workgroup of a second kernel and begins execution of a portion of the second workgroup. After the first workgroup releases the portions of compute unit resources, the scheduling circuitry fully allocates the portions of compute unit resources to the second workgroup and executes a remainer of the second workgroup.

A method, system, and computer-readable medium for executing a task is disclosed. The method includes receiving input data and computing instructions, launching a workgroup including wavefronts to execute the task, wherein the launching causes the wavefronts to process the input data by sharing intermediate results and resources, and adjusting the operation based on characteristics of the wavefronts. The characteristics include data dependencies, computational load, memory usage, and execution timing requirements. The wavefronts execute the task in stages, where each stage processes portions of input data and data generated by other wavefronts.

A mehtod of multiply a sparse matrix and a dense matrix to determine an output matrix, wherein a processing unit includes: an execution module configured to execute threads of a workgroup, wherein t

The present disclosure provides an instruction execution method, device, electronic equipment and computer readable storage medium, the method comprises: sending at least one first operation instruction in a work group instruction kernel to a sub-function processing unit through an instruction scheduler; executing a sub-task corresponding to the first operation instruction through the sub-function processing unit, and sending a task completion signal to the instruction scheduler if the sub-function processing unit has executed the sub-task; performing instruction synchronization on the work group instruction kernel through the instruction scheduler, which includes releasing the control of the work group instruction kernel if the instruction scheduler receives the task completion signal corresponding to all the first operation instructions and determines that the work group instruction kernel is in a suspended state; and executing a target operation instruction through the instruction scheduler, which avoids the problem of needing to use more barrier instructions to meet the execution requirements when executing complex parallel processing tasks, thereby improving the execution efficiency of the task.