39 results about "Re-order buffer" patented technology

These and other aspects of the present invention will be better described with reference to the Detailed Description and the accompanying figures. A method and apparatus for out-of-order processing of packets using linked lists is described. In one embodiment, the method includes receiving packets in a global order, the packets being designated for different ones of a plurality of reorder contexts. The method also includes storing information regarding each of the packets in a shared reorder buffer. The method also includes for each of the plurality of reorder contexts, maintaining a reorder context linked list that records the order in which those of the packets that were designated for that reorder context and that are currently stored in the shared reorder buffer were received relative to the global order. The method also includes completing processing of at least certain of the packets out of the global order and retiring the packets from the shared reorder buffer out of the global order for at least certain of the packets.

A method and a system for operating a plurality of processors that each includes an execution pipeline for processing dependence chains, the method comprising: configuring the plurality of processors to execute the dependence chains on execution pipelines; implementing a Super Re-Order Buffer (SuperROB) in which received instructions are re-ordered after out-of-order execution when at least one of the plurality of processors is in an Instruction Level Parallelism (ILP) mode and at least one of the plurality of processors has a Thread Level Parallelism (TLP) core; detecting an imbalance in a dispatch of instructions of a first dependence chain compared to a dispatch of instructions of a second dependence chain with respect to dependence chain priority; determining a source of the imbalance; and activating the ILP mode when the source of the imbalance has been determined.

A method for HARQ reordering in Enhanced Uplink Dedicated Channel of WCDMA system includes following steps: locating the soft combination buffer in the Node B and the reordering buffer in the SRNC; locating the HARQ entity in the Node B; locating the reordering queue distribution entity, the reordering entity and the disassembly entity in the SRNC. This invention adopts the separation technology of the soft combination buffer and the reordering buffer, the separation model can not only ensure the diversity gain, but also reduce the receiving delay and save the buffer space. Three mechanisms (timer mechanism, window mechanism and SBI mechanism) are proposed to prevent the blocking of the reordering buffer, which degrades the blocking to the least level, improves the receiving efficiency and the system performance. Aiming at the SBI mechanism, the invention proposes the new DCH data frame structure on the Iub interface and the Iur interface.

Reducing power consumption in a multi-slice computer processor that includes a re-order buffer and an architected register file, including: designating an entry in the re-order buffer as being invalid and unwritten; assigning a pending instruction to the entry in the re-order buffer; responsive to assigning the pending instruction to the entry in the re-order buffer, designating the entry as being valid; writing data generated by executing the pending instruction into the re-order buffer; and responsive to writing data generated by executing the pending instruction into the re-order buffer, designating the entry as being written.

A processor includes a logic for stateless capture of data linear addresses (DLA) during precise event based sampling (PEBS) for an out-of-order execution engine. The engine may include a PEBS unit with logic to increment a counter each time an instance of a designated micro-op is retired a reorder buffer, capture output DLA referenced by an instance of the micro-op that executes after the counter overflows, set a captured bit associated with a reorder buffer identifier for the instance of the micro-op, and store a PEBS record in a debug storage when the instance of the micro-op is retired from the reorder buffer. The designated micro-op references a DLA of a memory accessible to the processor.

Aspects relate to arbitrating access to an interconnect among multiple ports. For example, input ports receive requests for access to identified destination ports and buffer these in one or more FIFOs. A picker associated with respective FIFO(s) begins an empty arbitration packet that includes a location for each output port and fills one or more locations in the packet, such as based on a prioritization scheme. Each packet is passed in a ring to another picker, which performs a fill that does not conflict with previously filled locations in that packet. Each picker has an opportunity to place requests in each of the packets. Results of the arbitration are dispatched to reorder buffers associated with respective output ports and used to schedule the interconnect. Each arbitration cycle thus produces a set of control information for an interconnect to be used in subsequent data transfer steps.

A re-order buffer memory in a real-time application such as e.g., an imager. Initially, input data is written into the re-order buffer using a first addressing mode, which causes the data to be stored in a line-by-line manner. Prior to receiving the last line of input data, the stored data is read-out in blocks of data that spans multiples lines in the buffer. This frees up space in the re-order buffer. Subsequently received input data is written into the re-order buffer using a second addressing mode, which stores the newly received data in vertical segments of the re-order buffer whose stored data has already been read-out. Writing / reading of the re-order buffer alternates between the first and second addressing modes. Using this technique, a single buffer may be used to input new data while existing data is being read-out.

A processor may include a reorder buffer, reservation stations, and execution units. The reorder buffer may be a circular buffer with a head pointer and a tail pointer, configured to assign indexes to instructions. Reservation stations may be configured to host instructions with the assigned indexes, while waiting to be issued to the execution units. Responsive to exception event, reservation stations may be configured to flush instructions that are younger, in program order, than the instruction executed with exception. Execution units may provide the reorder buffer index EX of the instruction executed with exception. The reorder buffer may provide the reorder buffer index TP stored in the tail pointer. Reservation stations may be configured to flush instructions with assigned indexes in the wrapped-around increasing interval from the index EX to the index TP.

Reducing power consumption in a multi-slice computer processor that includes a re-order buffer and an architected register file, including: designating an entry in the re-order buffer as being invalid and unwritten; assigning a pending instruction to the entry in the re-order buffer; responsive to assigning the pending instruction to the entry in the re-order buffer, designating the entry as being valid; writing data generated by executing the pending instruction into the re-order buffer; and responsive to writing data generated by executing the pending instruction into the re-order buffer, designating the entry as being written.

A technique for restoring a register renaming map is described. In one example, a restore table with multiple storage locations holds a copy of the register renaming map whenever a flow risk instruction is passed to the reorder buffer. When all storage locations are full, further instructions are still passed to the reorder buffer, but no copy of the mapping is kept. A storage location then becomes available when the process risk instruction associated with that storage location is executed. A state of a register rename map for unrecorded flow-risk instructions passed to the reorder buffer when the plurality of memory locations are full is generated and stored in the available locations. The state of the register renaming map is generated using a restore table entry for a previous flow-risk instruction and a reorder buffer value for an intermediate instruction between the previous flow-risk instruction and the Between the above undocumented process risk instructions. The restore table can be used to restore the mapping if an unexpected change occurs in the instruction flow.