摘要:
An apparatus and method for managing a translation look-aside buffer (TLB). The TLB is shared by a plurality of jobs. The method including the steps of: obtaining at least one attribute of each job of the plurality of jobs; assigning a priority level to each job according to at least one attribute of each job; and managing the related TLB entries of each job according to the priority level of each job. The present invention also provides an apparatus for managing TLB corresponding to the above method. The method and apparatus according to the present invention provide an efficient use of the shared TLB.
摘要:
A processing unit coupled to a bus for accelerating data transmission and a method for accelerating data transmission. The present invention provides a streaming data transmission mode in which a plurality of data blocks are transmitted via one handshake. The present invention employs handshake save policy, when a processing unit sends a request comprising a plurality of data blocks on a bus, a cache or memory will perform address matching to judge whether there is any hit data block. If there is any hit data block, the cache or memory only needs to reply once and then start to continuously transmit the hit data blocks it possesses. Thus, a separate handshake for each data block is no longer needed.
摘要:
An apparatus and method for managing a translation look-aside buffer (TLB). The TLB is shared by a plurality of jobs. The method including the steps of: obtaining at least one attribute of each job of the plurality of jobs; assigning a priority level to each job according to at least one attribute of each job; and managing the related TLB entries of each job according to the priority level of each job. The present invention also provides an apparatus for managing TLB corresponding to the above method. The method and apparatus according to the present invention provide an efficient use of the shared TLB.
摘要:
A processing unit coupled to a bus for accelerating data transmission and a method for accelerating data transmission. The present invention provides a streaming data transmission mode in which a plurality of data blocks are transmitted via one handshake. The present invention employs handshake save policy, when a processing unit sends a request comprising a plurality of data blocks on a bus, a cache or memory will perform address matching to judge whether there is any hit data block. If there is any hit data block, the cache or memory only needs to reply once and then start to continuously transmit the hit data blocks it possesses. Thus, a separate handshake for each data block is no longer needed.
摘要:
A request control device, request control method, and a multiprocessor cooperation architecture. The request control device is connected to a request storage module and includes a comparing means and an identifier means. The comparing means is configured to determine if an incoming first queue unit corresponds to the same message with a queue unit that has existed in the request storage module. The identifier setting means is configured to set a save identifier of the queue unit that has existed in the request storage module to indicate not to save a state associated with the message if the first queue unit corresponds to the same message with the queue unit that has existed in the request storage module. According to the technical solution of the invention, the access to the memory caused by saving/loading the states is reduced and thereby increases the processing speed of the processor.
摘要:
An embodiment of the invention provides an extremum route determining engine and method. The engine includes a memory for storing a path with a weight in a graph and an extremum route determining logic circuit. The logic circuit includes a path reading section for reading the path in the graph, a writing section for updating the weight of the read path according to a predetermined extremum requirement and writing the path whose weight is updated into the memory, and an extremum route determining section for determining an extremum route. The method includes reading a stored path in a graph, the path having a weight, updating the weight of the read path and writing the path whose weight has been updated into a memory, and determining an extremum route. An embodiment of the invention improves the processing speed of extremum route determination.
摘要:
A request control device, request control method, and a multiprocessor cooperation architecture. The request control device is connected to a request storage module and includes a comparing means and an identifier means. The comparing means is configured to determine if an incoming first queue unit corresponds to the same message with a queue unit that has existed in the request storage module. The identifier setting means is configured to set a save identifier of the queue unit that has existed in the request storage module to indicate not to save a state associated with the message if the first queue unit corresponds to the same message with the queue unit that has existed in the request storage module. According to the technical solution of the invention, the access to the memory caused by saving/loading the states is reduced and thereby increases the processing speed of the processor.
摘要:
A computer-implemented method, an accelerator hardware unit, and an article of manufacture for supporting virtual machine migration. The method includes: acquiring a task request from a task queue of an accelerator hardware unit; extracting identification information of a related virtual machine from the task request; determining whether the identification information of the related virtual machine matches the identification information of a virtual machine to be migrated, where the identification information of a virtual machine to be migrated is recorded in a virtual machine identification information table; and deleting the task request from the task queue if the extracted identification information matches the identification information of a virtual machine to be migrated.
摘要:
A computer-implemented method, an accelerator hardware unit, and an article of manufacture for supporting virtual machine migration. The method includes: acquiring a task request from a task queue of an accelerator hardware unit; extracting identification information of a related virtual machine from the task request; determining whether the identification information of the related virtual machine matches the identification information of a virtual machine to be migrated, where the identification information of a virtual machine to be migrated is recorded in a virtual machine identification information table; and deleting the task request from the task queue if the extracted identification information matches the identification information of a virtual machine to be migrated.
摘要:
This invention is an apparatus for vortex generation by combining the function of means for vortex generation with the functions of the leading-edge aerodynamic surface, the airfoil, and/or the trailing-edge aerodynamic surface.