International Business Machines Corporation

Zhong Liang Wang

Michael K Gschwind

Alexander Erik Mericas

Venkat Rajeev Indukuru

Timothy John Slegel

Christian Jacobi

Chung-Lung K Shum

Balaram Sinharoy

Giles R Frazier

Vijay Sundaresan

Ronald P Hall

Mauricio J Serrano

Peter Wiebe Burka

Mark Graham Stoodley

Richard William Doing

Nikola Grcevski

Joran S C Siu

Charles Brian Hall

Kevin James Langman

Improving execution of application program instructions by receiving code having a security classification, determining that the code is untrusted according to the security classification and inserting instructions for a cache flush associated with executing the code.

Controlling processor instruction execution

Affinity domain based garbage collection is facilitated for a non-uniform memory access (NUMA) computing environment. The affinity domain that a memory region is allocated is determined. Based on a processor of the NUMA computing environment having a matching affinity domain to the affinity domain in the memory region, the processor performs garbage collection processing on the memory region. The processor is one processor of a plurality of processors of the NUMA computing environment. In a global garbage collection work queue embodiment, the processor initially determines that it has a matching affinity domain to the affinity domain of the memory region to be processed. In a multiple garbage collection work queue implementation, memory regions are enqueued on a designated work queue for the affinity domain to which the memory region is allocated. The locality domain-based garbage collection processing presented may be implemented at one or more system architectural levels.

Affinity domain-based garbage collection

Embodiments relate to lightweight interrupts for condition checking. An aspect includes determining, by a condition checker in a computer system, that a condition occurs for an application executing on the computer system. Another aspect includes, based on determining that the condition occurs for the application, determining whether lightweight interrupts are enabled. Yet another aspect includes based on determining that lightweight interrupts are enabled, issuing a lightweight interrupt to the application and handling the instruction by the application.

Lightweight interrupts for condition checking

A method and data processing system for managing running of instructions in a program. A processor of the data processing system receives a monitoring instruction of a monitoring unit. The processor determines if at least one secondary thread of a set of secondary threads is available for use as an assist thread. The processor selects the at least one secondary thread from the set of secondary threads to become the assist thread in response to a determination that the at least one secondary thread of the set of secondary threads is available for use as an assist thread. The processor changes profiling of running of instructions in the program from the main thread to the assist thread.

Hardware assist thread for dynamic performance profiling

An information handling system includes a memory, a processor, and an instruction tracking unit. The processor executes program code and, while the program code executes, the instruction tracking unit decodes a multi-purpose no-op instruction within the program code. In turn, the instruction tracking unit sends an interrupt to the processor, which invokes a profiling module to collect and store profiling data in a profiling buffer.

General purpose emit for use in value profiling

A method that provides for dynamic loop transfer for a method having a first set of instructions being executed by an interpreter is provided. An execution stack includes slots for storing a value of each local variable known to each subroutine while the subroutine is active. The method comprises suspending execution at a point for which a current execution state can be captured from the execution stack; assigning the value in each slot of the execution stack to a corresponding slot of an array of values; scanning the first set of instructions to identify a data type for local variable that is not known in the current execution state and shares a slot in the execution stack with a local variable that is known; and generating a second set of instructions for the method coded to be initially executed to declare each local variable that is known in the current execution state and each local variable for which a data type was identified, assign each declared variable with the value assigned to the slot in the array that corresponds to the slot of the execution stack in which the value of the variable is stored during execution of the first set of instructions, and branch to a target point in the second set of instructions that corresponds to the point at which execution was suspended.

Method and system for dynamic loop transfer by populating split variables

A method and apparatus to guarantee type safety in multithreaded programs, and to guarantee initialization safety in well-behaved multithreaded programs. A plurality of bytecodes representing a program are received and examined to identify bytecodes defining object creation operations and object initialization operations. Upon execution of the plurality of bytecodes, memory barrier operations are performed subsequent to the performance of both the object creation operations and the object initialization operations. This guarantees type safety, and further guarantees initialization safety if the program is well-behaved. Optimization algorithms may also be applied in the compilation of bytecodes to improve performance.

Apparatus to guarantee type and initialization safety in multithreaded programs

A method for lock reservation using cooperative multithreading is provided. The method includes analyzing code containing async points to support cooperative multithreading. The method also includes identifying a class of code as a candidate for reservation via determining locking properties within the code as a function of locations of async points within the code, and generating reserving code that reserves the shared object when code performing the reservation is considered hot code. The method further includes performing runtime monitoring of reservation performance to detect a contention level for the shared object, and removing the reservation when the runtime monitoring determines that a low level of contention exists. A method for lightweight single reader reserved locks is also provided, including identifying a candidate for reservation containing a read-only locking sequence, conditionally marling the sequence, and generating code using an artificial dependency to control execution order of out-of-line code.

Lock reservation using cooperative multithreading and lightweight single reader reserved locks

A reference to data in program code is resolved during execution of the program code. A request to resolve the reference is classified based on a state of the referenced data and a source of the request. A transitional resolution for the reference is provided if the referenced data state indicates no accessible definition and resolution of the reference is allowed according to the request classification. A full resolution for the reference is provided if the referenced data state indicates an accessible definition according to the request classification. The request is removed only if the reference resolution is a full resolution.

Growing community of inventors

Markham, Canada

Zhong Liang Wang