Arbitrating among portions of multiple transactions and transmitting a winning portion over one of a multiplicity of virtual channels associated with an interconnect on a clock cycle-by-clock cycle basis. By repeatedly performing the above each clock cycle, winning portions are interleaved and transmitted over the multiplicity of virtual channels over multiple clock cycles respectively.

Arbitrating among portions of multiple transactions and transmitting a winning portion over one of a multiplicity of virtual channels associated with an interconnect on a clock cycle-by-clock cycle basis. By repeatedly performing the above each clock cycle, winning portions are interleaved and transmitted over the multiplicity of virtual channels over multiple clock cycles respectively.

Arbitrating among portions of multiple transactions and transmitting a winning portion over one of a multiplicity of virtual channels associated with an interconnect on a clock cycle-by-clock cycle basis. By repeatedly performing the above each clock cycle, winning portions are interleaved and transmitted over the multiplicity of virtual channels over multiple clock cycles respectively.

A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

A method, system, and computer program product are described for a machine selecting a selected adapter among two or more adapters that perform a same function. The method includes generating a request, at the machine, for the function, and calculating a time indicator associated with each of the two or more adapters based on a respective adapter queue time factor (QTF) associated with each of the two or more adapters, the adapter QTF associated with each of the two or more adapters being a computed value. The method also includes selecting the selected adapter and submitting one or more requests to the selected adapter of the two or more adapters to perform the function based on a comparison of the time indicator associated with each of the two or more adapters.

A processing unit connected via a system fabric to multiple processing units calls a first single command in a bus protocol that allows sampling over the system fabric of the capability of snoopers distributed across the processing units to handle an interrupt. The processing unit, in response to detecting at least one first selection of snoopers with capability to handle the interrupt, calling a second single command in the bus protocol to poll the first selection of snoopers over the system fabric for an availability status. The processing unit, in response to detecting at least one second selection of snoopers respond with the available status indicating an availability to handle the interrupt, assigning a single snooper from among the second selection of snoopers to handle the interrupt by calling a third single command in the bus protocol.

A processing unit connected via a system fabric to multiple processing units calls a first single command in a bus protocol that allows sampling over the system fabric of the capability of snoopers distributed across the processing units to handle an interrupt. The processing unit, in response to detecting at least one first selection of snoopers with capability to handle the interrupt, calling a second single command in the bus protocol to poll the first selection of snoopers over the system fabric for an availability status. The processing unit, in response to detecting at least one second selection of snoopers respond with the available status indicating an availability to handle the interrupt, assigning a single snooper from among the second selection of snoopers to handle the interrupt by calling a third single command in the bus protocol.

In one embodiment of the invention, a system architecture for bus masters and bus arbiters are provided to support routing and failover. The system comprises large pools of bus masters, a plurality of sets can be configured to control a plurality of slave devices wherein each set contains a collection of bus masters attached to central arbiter driving one of the system buses. Each set controls a group(s) of slave device that are primarily controlled by the bus master(s) within the set. Hence, a system can therefore include of a plurality of sets and can control a group of slave devices.

In one embodiment of the invention, a system architecture for bus masters and bus arbiters are provided to support routing and failover. The system comprises large pools of bus masters, a plurality of sets can be configured to control a plurality of slave devices wherein each set contains a collection of bus masters attached to central arbiter driving one of the system buses. Each set controls a group(s) of slave device that are primarily controlled by the bus master(s) within the set. Hence, a system can therefore include of a plurality of sets and can control a group of slave devices.

A method for self-moderating bus arbitration for access to a common bus is provided. The method may include receiving, by a bus arbiter, a request from a master device, wherein the received request includes a priority value set by the master device. The method may also include identifying the priority value from the received transaction request. The method may then include determining an insertion point within a priority table based on comparing the identified priority value to a table entry priority value associated with each table entry within the priority table. The method may further include inserting a new entry into the priority table based on the determined insertion point. The method may also include identifying a highest priority entry within the priority table. The method may then include serving the identified highest priority entry.