International Business Machines Corporation

Peter M Held

Wolfgang Gellerich

Martin Schwidefsky

Chung-Lung K Shum

Gerrit Koch

Christoph Raisch

A method for managing tasks in a computer system comprising a processor and a memory, the method includes performing a first task by the processor, the first task comprising task-relating branch instructions and task-independent branch instructions and executing the branch prediction method, the execution resulting in task-relating branch prediction data in the branch prediction history table. In response to determining that the first task is to be interrupted or terminated, the method includes storing the task-relating branch prediction data of the first task in the task structure of the first task. In response to determining that a second task is to be continued, the method includes reading task-relating branch prediction data of the second task from the task structure of the second task and storing the task-relating branch prediction data of the second task in the branch prediction history table.

Method for maintaining a branch prediction history table

Examples of techniques for branch prediction for indirect branch instructions are described herein. An aspect includes detecting a first register setting instruction in an instruction pipeline of a processor, wherein the first register setting instruction stores a target instruction address in a first register of the processor. Another aspect includes looking up the first register setting instruction in a first table. Another aspect includes, based on there being a hit for the first register setting instruction in the first table, determining instruction address data corresponding to a first indirect branch instruction that is associated with the first register setting instruction in a first entry in the first table. Another aspect includes updating a branch prediction for the first indirect branch instruction in a branch prediction logic of the processor based on the target instruction address.

Branch prediction for indirect branch instructions

A method includes storing a first address of a first instruction executed by a processor core in a first table, where the first instruction writes a value into a register for utilization in addressing memory. The method stores the first address of the first instruction executed by the processor core in a second table with multiple entries, where a register value loaded into the register is utilized as a second address by a second instruction executed by the processor core to access a main memory. The method determines whether an instruction address associated with an instruction executed by the processor core is present in the second table, where the instruction address is the second address. Responsive to determining the instruction address is present in the second table, the method prefetches data from the main memory, where the register value is utilized as the second address in the main memory.

Data prefetching that stores memory addresses in a first table and responsive to the occurrence of loads corresponding to the memory addresses stores the memory addresses in a second table

Embodiments here relate to managing a cache by exploiting a cache line hierarchy is provided. Managing the cache includes reading cache references of a first task from a cache reference save area of a first task data structure in response to a context switch. Further, managing the cache includes prefetching and restoring cache lines of the first task to the cache based on the cache references. Note that the cache lines can be predetermined from a plurality of cache lines associated with the first task during an extraction operation with respect to the first task and the cache line hierarchy.

Quality of cache management in a computer

A method for managing tasks in a computer system comprising a processor and a memory, the method includes performing a first task by the processor, the first task comprising task-relating branch instructions and task-independent branch instructions and executing the branch prediction method, the execution resulting in task-relating branch prediction data in the branch prediction history table. In response to determining that the first task is to be interrupted or terminated, the method includes storing the task-relating branch prediction data of the first task in the task structure of the first task. In response to determining that a second task is to be continued, the method includes reading task-relating branch prediction data of the second task from the task structure of the second task, storing the task-relating branch prediction data of the second task in the branch prediction history table, and ensuring that task-independent branch prediction data is maintained.

Growing community of inventors

Renningen, Germany

Peter M Held