Abstract: A computer implemented method, data processing system, computer usable program code, and apparatus are provided for enhancing boot time of a computer system. Initial program load firmware is initialized on a plurality of service processors. The plurality of service processors performs independent non-redundant initialization tasks concurrently as other independent non-redundant initialization tasks are performed by another service processor. Once the initialization tasks are completed, control is switched to a primary service processor within the plurality of service processors and runtime firmware is loaded by the primary service processor.

Abstract: A method, apparatus, and computer instructions for self-diagnosing remote I/O enclosures with enhanced FRU callouts. When a failure is detected on a RIO drawer, a data processing system uses the bulk power controller to provide an alternate path, rather than using the existing RIO links, to access registers on the I/O drawers. The system logs onto the bulk power controller, which provides a communications path between the data processing system and the RIO drawer. The communications path allows the data processing system to read all of the registers on the I/O drawer. The register information in the I/O drawer is then analyzed to diagnose the I/O failure. Based on the register information, the data processing system identifies a field replacement unit to repair the I/O failure.

Abstract: A method, system, and computer product for aiding in the debugging of an I/O failure. When an I/O failure is detected on a RIO drawer, a data processing system uses the bulk power controller to provide an alternate path, rather than using the existing RIO links, to access registers on the I/O drawers. The system logs onto the bulk power controller, which provides a communications path between the data processing system and the RIO drawer. The communications path allows the data processing system to read the chip registers on the I/O drawer. The data processing system captures I/O failure information in the I/O drawer using the communications path, wherein the I/O failure information is used to debug the I/O failure.

Abstract: A non-invasive method, system, and computer product for monitoring I/O performance without using the RIO bus. When executing a performance benchmark run in a remote I/O drawer, the system logs into a bulk power controller, wherein the bulk power controller provides a communications path between the data processing system and the I/O drawer, and wherein the communications path allows the data processing system to access chip register information on the I/O drawer without using a RIO link. Using the communications path, the system may monitor I/O performance and obtain chip register information. The system may further increase performance by using software to detect a load imbalance. Through the communications path, the software is able to dynamically balance the load by changing the chip register settings to allow the initialization registers to handle the load more efficiently.

Abstract: A JTAG bus cross point switching device that is commanded by the same bus which it configures. In a preferred embodiment a JTAG chain includes a cross point switching device that is capable of adding, omitting, or rearranging devices on a JTAG bus. The switching device itself is controlled by commands on the JTAG bus which it configures.