Abstract: A massively parallel computer system contains an inter-nodal communications network of node-to-node links. An automated routing strategy routes packets through one or more intermediate nodes of the network to reach a destination. Some packets are constrained to be routed through respective designated transporter nodes, the automated routing strategy determining a path from a respective source node to a respective transporter node, and from a respective transporter node to a respective destination node. Preferably, the source node chooses a routing policy from among multiple possible choices, and that policy is followed by all intermediate nodes. The use of transporter nodes allows greater flexibility in routing.

Abstract: A method for dispatching input/output access requests to a direct access storage device (DASD) is disclosed. Each of a group of I/O access requests to DASD is assigned into one of at least two I/O access request categories, namely, high priority I/O access requests and low priority I/O access requests. Each of a group of I/O slots within DASD is assigned into one of at least two I/O slot categories, namely, high priority I/O slots and low priority I/O slots. An I/O access request from a first one of the two I/O access request categories is sent to any one of the I/O slots. An I/O access request from a second one of the two I/O access request categories is sent to only a slot belonging to a subset of the two I/O slot categories.

Abstract: A storage format and methods for improving the performance of the symbol table of an encoded vector index. The symbol table comprises a hash table, entries of the hash table storing associated key values and codes for the encoded vector index. Hash table entries store an accumulated count of occurrences of prior and the current key values, which improves the efficiency of responding to a request for a key range count. A binary radix tree is used to locate entries, which comprises a plurality of nodes, corresponding to binary digits of a binary representation of a key value. Codes are assigned to key values for the encoded vector index in a distributed fashion, so there are available code values between existing code values in the code ordering, that can be assigned to new key values, alleviating the need to reorganize the code values upon an insertion.

Abstract: A method for dispatching input/output access requests to a direct access storage device (DASD) is disclosed. Each of a group of I/O access requests to DASD is assigned into one of at least two I/O access request categories, namely, high priority I/O access requests and low priority I/O access requests. Each of a group of I/O slots within DASD is assigned into one of at least two I/O slot categories, namely, high priority I/O slots and low priority I/O slots. An I/O access request from a first one of the two I/O access request categories is sent to any one of the I/O slots. An I/O access request from a second one of the two I/O access request categories is sent to only a slot belonging to a subset of the two I/O slot categories.

Abstract: A storage format and methods for improving the performance of the symbol table of an encoded vector index. The symbol table comprises a hash table, entries of the hash table storing associated key values and codes for the encoded vector index. Hash table entries store an accumulated count of occurrences of prior and the current key values, which improves the efficiency of responding to a request for a key range count. A binary radix tree is used to locate entries, which comprises a plurality of nodes, corresponding to binary digits of a binary representation of a key value. Codes are assigned to key values for the encoded vector index in a distributed fashion, so there are available code values between existing code values in the code ordering, that can be assigned to new key values, alleviating the need to reorganize the code values upon an insertion.

Abstract: A method is provided for parallel and cooperative processing of data in a system wherein a coordinator process cooperates with one or more agent processes to which portions of the data processing function is off loaded. The agent processes read and process the data and accumulate a partial result. Each agent process, responsive to statistics collected on the content of the data processed, returns a partial result of the processing to the coordinator process. These steps are repeated iteratively until the processing has been completed. In a specific application, the performance of data processing systems is improved by speeding up database group-by queries. The group-by operation processing is distributed between the host central processing unit (CPU) and the input/output (I/O) processors (IOPs). Essentially, the IOPs are sent group-by requests to be performed on a set of disk blocks (extents), along with a predicate for tuples to be selected for query.