Abstract: A technique for operating a high performance computing cluster includes monitoring workloads of multiple processors. The high performance computing cluster includes multiple nodes that each include two or more of the multiple processors. Workload information for the multiple processors is periodically updated in respective local job tables maintained in each of the multiple nodes. Based on the workload information in the respective local job tables, one or more threads are periodically moved to a different one of the multiple processors.

Abstract: A technique for operating a high performance computing (HPC) cluster includes monitoring communication between threads assigned to multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more of the threads are moved to a different one of the multiple processors based on the communication between the threads.

Abstract: Disclosed are a method, a system and a computer program product for automatically allocating and de-allocating resources for jobs executed or processed by one or more supercomputer systems. In one or more embodiments, a supercomputing system can process multiple jobs with respective supercomputing resources. A global resource manager can automatically allocate additional resources to a first job and de-allocate resources from a second job. In one or more embodiments, the global resource manager can provide the de-allocated resources to the first job as additional supercomputing resources. In one or more embodiments, the first job can use the additional supercomputing resources to perform data analysis at a higher resolution, and the additional resources can compensate for an amount of time the higher resolution analysis would take using originally allocated supercomputing resources.

Abstract: A data processing system includes a system memory, one or more processing cores, and a memory controller that controls access to a system memory. The memory controller includes a memory speculation mechanism that stores historical information regarding prior memory accesses. In response to a memory access request, the memory controller speculatively initiates access to the system memory based upon the historical information in the memory speculation mechanism in advance of receipt of a coherency message indicating that the memory access request is to be serviced by reference to the system memory.

Abstract: A bulk power assembly includes a bulk power distribution (BPD) subassembly and a bulk power controller and hub (BPCH) subassembly coupled to the BPD subassembly. The BPD assembly is configured to provide bulk DC power from both AC input power and DC input power. The BPD subassembly is configured to distribute the DC bulk power. The BPCH subassembly is configured to monitor and control the BPD assembly.

Abstract: A technique for operating a high performance computing (HPC) cluster includes monitoring workloads of multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more threads assigned to one or more of the multiple processors are moved to a different one of the multiple processors based on the workloads of the multiple processors.

Abstract: A technique for operating a high performance computing cluster (HPC) having multiple nodes (each of which include multiple processors) includes periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes. Respective local job tables maintained in each of the multiple nodes are updated based on the broadcast information. One or more threads are then moved from one or more of the multiple processors to a different one of the multiple processors (based on the broadcast information in the respective local job tables).

Abstract: Disclosed are a method, a system and a computer program product for dynamically allocating and/or de-allocating resources and/or partitions that provide I/O and/or active storage access services in a supercomputing system. The supercomputing system can include multiple compute nodes, high performance computing (HPC) switches coupled to the compute nodes, and active non-volatile storage devices coupled to the compute nodes. Each of the compute nodes can be configured to communicate with another compute node through at least one of the HPC switches. In one or more embodiments, each of at least two compute nodes includes a storage controller and is configured to dynamically allocate and de-allocate a storage controller partition to provide storage services to the supercomputing system, and each of at least two compute nodes includes an I/O controller and is configured to dynamically allocate and de-allocate an I/O controller partition to provide I/O services to the supercomputing system.

Abstract: A power conversion, control, and distribution system includes multiple bulk power regulator (BPR) subassemblies, a bulk power distribution (BPD) subassembly, and a bulk power controller and hub (BPCH) subassembly. The BPR subassemblies are each configured to provide regulated DC power from both AC input power and DC input power. The BPD subassembly is configured to distribute the regulated DC power. The BPCH subassembly is coupled to the multiple BPR subassemblies and the BPD subassembly. The BPCH subassembly is configured to monitor and control the BPR assemblies and the BPD assembly.

Abstract: A method and system are disclosed for saving soft state information, which is non-critical for executing a process in a processor, upon a receipt of a process interrupt by the processor. The soft state is transmitted to a memory associated with the processor via a memory interface. Preferably, the soft state is transmitted within the processor to the memory interface via a scan-chain pathway within the processor, which allows functional data pathways to remain unobstructed by the storage of the soft state. Thereafter, the stored soft state can be restored from memory when the process is again executed.

Abstract: Disclosed are a method, a system and a computer program product for automatically allocating and de-allocating resources for jobs executed or processed by one or more supercomputer systems. In one or more embodiments, a supercomputing system can process multiple jobs with respective supercomputing resources. A global resource manager can automatically allocate additional resources to a first job and de-allocate resources from a second job. In one or more embodiments, the global resource manager can provide the de-allocated resources to the first job as additional supercomputing resources. In one or more embodiments, the first job can use the additional supercomputing resources to perform data analysis at a higher resolution, and the additional resources can compensate for an amount of time the higher resolution analysis would take using originally allocated supercomputing resources.

Abstract: Disclosed are a method, a system and a computer program product for operating a cache system. The cache system can include multiple cache lines, and a first cache line of the multiple of cache lines can include multiple cache cells, and a bus coupled to the multiple cache cells. In one or more embodiments, the bus can include a switch that is operable to receive a first control signal and to split the bus into first and second portions or aggregate the bus into a whole based on the first control signal. When the bus is split, a first cache cell and a second cache cell of the multiple cache cells are coupled to respective first and second portions of the bus. Data from the first and second cache cells can be selected through respective portions of the bus and outputted through a port of the cache system.

Abstract: A power conversion, control, and distribution system includes multiple bulk power regulator (BPR) subassemblies, a bulk power distribution (BPD) subassembly, and a bulk power controller and hub (BPCH) subassembly. The BPR subassemblies are each configured to provide regulated DC power from both AC input power and DC input power. The BPD subassembly is configured to distribute the regulated DC power. The BPCH subassembly is coupled to the multiple BPR subassemblies and the BPD subassembly. The BPCH subassembly is configured to monitor and control the BPR assemblies and the BPD assembly.

Abstract: A bulk power assembly includes a bulk power distribution (BPD) subassembly and a bulk power controller and hub (BPCH) subassembly coupled to the BPD subassembly. The BPD assembly is configured to provide bulk DC power from both AC input power and DC input power. The BPD subassembly is configured to distribute the DC bulk power. The BPCH subassembly is configured to monitor and control the BPD assembly.

Abstract: Disclosed are a method, a system and a computer program product for dynamically allocating and/or de-allocating resources and/or partitions that provide I/O and/or active storage access services in a supercomputing system. The supercomputing system can include multiple compute nodes, high performance computing (HPC) switches coupled to the compute nodes, and active non-volatile storage devices coupled to the compute nodes. Each of the compute nodes can be configured to communicate with another compute node through at least one of the HPC switches. In one or more embodiments, each of at least two compute nodes includes a storage controller and is configured to dynamically allocate and de-allocate a storage controller partition to provide storage services to the supercomputing system, and each of at least two compute nodes includes an I/O controller and is configured to dynamically allocate and de-allocate an I/O controller partition to provide I/O services to the supercomputing system.

Abstract: A processor communication register (PCR) contained within a multiprocessor cluster system provides enhanced processor communication. The PCR stores information that is useful in pipelined or parallel multi-processing. Each processor cluster has exclusive rights to store to a sector within the PCR and has continuous access to read its contents. Each processor cluster updates its exclusive sector within the PCR, instantly allowing all of the other processors within the cluster network to see the change within the PCR data, and bypassing the cache subsystem. Efficiency is enhanced within the processor cluster network by providing processor communications to be immediately networked and transferred into all processors without momentarily restricting access to the information or forcing all the processors to be continually contending for the same cache line, and thereby overwhelming the interconnect and memory system with an endless stream of load, store and invalidate commands.

Abstract: A processing unit includes a processor core, an input/output (I/O) communication adapter coupled to the processor core, and a cache system coupled to the processor core and to the I/O communication adapter. The cache system including a cache array, a cache directory and a cache controller. The cache controller snoops I/O communication by the I/O communication adapter and, in response to snooping the I/O communication adapter performing an I/O data write of outgoing data in an exclusive state, invalidates corresponding data stored within the cache array.

Abstract: A technique for operating a high performance computing cluster (HPC) having multiple nodes (each of which include multiple processors) includes periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes. Respective local job tables maintained in each of the multiple nodes are updated based on the broadcast information. One or more threads are then moved from one or more of the multiple processors to a different one of the multiple processors (based on the broadcast information in the respective local job tables).

Abstract: A technique for operating a high performance computing (HPC) cluster includes monitoring communication between threads assigned to multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more of the threads are moved to a different one of the multiple processors based on the communication between the threads.

Abstract: A technique for operating a high performance computing cluster includes monitoring workloads of multiple processors. The high performance computing cluster includes multiple nodes that each include two or more of the multiple processors. Workload information for the multiple processors is periodically updated in respective local job tables maintained in each of the multiple nodes. Based on the workload information in the respective local job tables, one or more threads are periodically moved to a different one of the multiple processors.