Abstract: A load request is received to retrieve a piece of data from a location in memory and the load request follows one or more store requests in a set of instructions to store a piece of data in the location in memory. One or more possible locations in a cache for a piece of data corresponding to the location in memory is determined. Each possible location of the one or more possible locations in the cache is determined. It is then determined if at least one location of the one or more possible locations contains data to be stored in the location in memory. Data in one location of the at least one location is loaded, the data in the one location is from a store request of the one or more store requests and the store request is closest in the set of instructions to the load request.

Abstract: A load request is received to retrieve a piece of data from a location in memory and the load request follows one or more store requests in a set of instructions to store a piece of data in the location in memory. One or more possible locations in a cache for a piece of data corresponding to the location in memory is determined. Each possible location of the one or more possible locations in the cache is determined. It is then determined if at least one location of the one or more possible locations contains data to be stored in the location in memory. Data in one location of the at least one location is loaded, the data in the one location is from a store request of the one or more store requests and the store request is closest in the set of instructions to the load request.

Abstract: Embodiments relate to a method, system and computer program product for storing a system-absolute address (SAA) in a first level look-aside buffer (TLB). In one embodiment, the system includes a central processor including the TLB and general purpose registers (GPRS). The TLB is configured for storing the SAA. The central processor is configured for issuing a load system-absolute address (LSAA) instruction. The system includes a translation unit that is in communication with the TLB of the central processor. The system is configured to perform a method including determining, based on the LSAA instruction being issued, whether the SAA is stored in the TLB. The method includes sending a translation request to the translation unit from the central processor based on the SAA not being stored in the TLB. The method includes determining the SAA by the translation unit based on receiving the translation request.

Abstract: A mechanism for simultaneous multithreading is provided. Responsive to performing a store instruction for a given thread of threads on a processor core and responsive to the core having ownership of a cache line in a cache, an entry of the store instruction is placed in a given store queue belonging to the given thread. The entry for the store instruction has a starting memory address and an ending memory address on the cache line. The starting memory addresses through ending memory addresses of load queues of the threads are compared on a byte-per-byte basis against the starting through ending memory address of the store instruction. Responsive to one memory address byte in the starting through ending memory addresses in the load queues overlapping with a memory address byte in the starting through ending memory address of the store instruction, the threads having the one memory address byte is flushed.

Abstract: A mechanism for simultaneous multithreading is provided. Responsive to performing a store instruction for a given thread of threads on a processor core and responsive to the core having ownership of a cache line in a cache, an entry of the store instruction is placed in a given store queue belonging to the given thread. The entry for the store instruction has a starting memory address and an ending memory address on the cache line. The starting memory addresses through ending memory addresses of load queues of the threads are compared on a byte-per-byte basis against the starting through ending memory address of the store instruction. Responsive to one memory address byte in the starting through ending memory addresses in the load queues overlapping with a memory address byte in the starting through ending memory address of the store instruction, the threads having the one memory address byte is flushed.

Abstract: Embodiments relate to cache coherency verification using ordered lists. An aspect includes maintaining a plurality of ordered lists, each ordered list corresponding to a respective thread that is executed by a processor, wherein each ordered list comprises a plurality of atoms, each atom corresponding to a respective operation performed in a cache by the respective thread that corresponds to the ordered list in which the atom is located, wherein the plurality of atoms in an ordered list are ordered based on program order. Another aspect includes determining a state of an atom in an ordered list of the plurality of ordered lists. Another aspect includes comparing the state of the atom in an ordered list to a state of an operation corresponding to the atom in the cache. Yet another aspect includes, based on the comparing, determining that there is a coherency violation in the cache.

Abstract: Embodiments relate to cache coherency verification using ordered lists. An aspect includes maintaining a plurality of ordered lists, each ordered list corresponding to a respective thread that is executed by a processor, wherein each ordered list comprises a plurality of atoms, each atom corresponding to a respective operation performed in a cache by the respective thread that corresponds to the ordered list in which the atom is located, wherein the plurality of atoms in an ordered list are ordered based on program order. Another aspect includes determining a state of an atom in an ordered list of the plurality of ordered lists. Another aspect includes comparing the state of the atom in an ordered list to a state of an operation corresponding to the atom in the cache. Yet another aspect includes, based on the comparing, determining that there is a coherency violation in the cache.

Abstract: Embodiments relate to a method, system and computer program product for storing a system-absolute address (SAA) in a first level look-aside buffer (TLB). In one embodiment, the system includes a central processor including the TLB and general purpose registers (GPRS). The TLB is configured for storing the SAA. The central processor is configured for issuing a load system-absolute address (LSAA) instruction. The system includes a translation unit that is in communication with the TLB of the central processor. The system is configured to perform a method including determining, based on the LSAA instruction being issued, whether the SAA is stored in the TLB. The method includes sending a translation request to the translation unit from the central processor based on the SAA not being stored in the TLB. The method includes determining the SAA by the translation unit based on receiving the translation request.

Abstract: A technique is provided for monitoring a value without repeated storage access. A processing circuit processes an instruction of a program that specifies a memory address of a memory location to be monitored. The processing circuit configures a monitor station for monitoring the memory location. The memory location includes a state descriptor for the program. The processing circuit receives a cross-invalidate request from a memory controller. The cross-invalidate request indicates to the monitor station that content of the memory location has been changed by another processing circuit.

Abstract: Embodiments relate to tracking a transactional execution footprint. An aspect includes receiving a store instruction which includes store data. It is determined if the store instruction is executing within a transaction that effectively delays committing stores to a shared cache until the transaction has completed. The store data is stored to a cache line in a local cache. The cache line is marked as dirty if the transaction is active. The stored data that was marked as dirty in the local cache is invalidated if the transaction has terminated abnormally. The stored data is un-marked if it is determined that the transaction has successfully ended.

Abstract: Embodiments relate to collision-based alternate hashing. An aspect includes receiving an incoming instruction address. Another aspect includes determining whether an entry for the incoming instruction address exists in a history table based on a hash of the incoming instruction address. Another aspect includes based on determining that the entry for the incoming instruction address exists in the history table, determining whether the incoming instruction address matches an address tag in the determined entry. Another aspect includes based on determining that the incoming instruction address does not match the address tag in the determined entry, determining whether a collision exists for the incoming instruction address. Another aspect includes based on determining that the collision exists for the incoming instruction address, activating alternate hashing for the incoming instruction address using an alternate hash buffer.

Abstract: Embodiments relate to determining the logical address of a transaction abort. In an embodiment, one or more instructions are received are received from an application. The one or more instructions are executed within a first transaction. The first transaction delays committing stores to memory until it has completed. At least one of the one or more instructions includes a first logical memory address. The first logical memory address corresponds to a first memory address in a memory system. It is determined if the first memory address is equal to a second memory address that is stored in a conflict register. Based on determining that they are equal the first logical memory address is saved as a logical address associated with a cross invalidate (XI) signal at a location available to the application.

Abstract: A technique is provided for monitoring a value without repeated storage access. A processing circuit processes an instruction of a program that specifies a memory address of a memory location to be monitored. The processing circuit configures a monitor station for monitoring the memory location. The memory location includes a state descriptor for the program. The processing circuit receives a cross-invalidate request from a memory controller. The cross-invalidate request indicates to the monitor station that content of the memory location has been changed by another processing circuit.

Abstract: A method and central processing unit supporting atomic access of shared data by a sequence of memory access operations. A processor status flag is reset. A processor executes, subsequent to the setting of the processor status flag, a sequence of program instructions with instructions accessing a subset of shared data contained within its local cache. During execution of the sequence of program instructions and in response to a modification by another processor of the subset of shared data, the processor status flag is set. Subsequent to the executing the sequence of program instructions and based upon the state of the processor status flag, either a first program processing or a second program processing is executed. In some examples the first program processing includes storing results data into the local cache and the second program processing includes discarding the results data.

Abstract: Embodiments relate to prefetch address translation in a computer processor. An aspect includes issuing, by prefetch logic, a prefetch request comprising a virtual page address. Another aspect includes, based on the prefetch request missing the TLB and the address translation logic of the processor being busy performing a current translation request, comparing a page of the prefetch request to a page of the current translation request. Yet another aspect includes, based on the page of the prefetch request matching the page of the current translation request, storing the prefetch request in a prefetch buffer.

Abstract: Embodiments relate to a transactional read footprint after a cache line eviction. An aspect includes executing one or more read instructions in an active transaction. A cross invalidate (XI) request for a target cache line is received, and it is determined if the target cache line is part of a congruence class in a local cache. It is further determined whether an extension flag associated with the congruence class is set. The extension flag is used to indicate that cache lines of the congruence class associated with the active transaction have been replaced based only on being least recently used and that the target cache line is not in the cache. Execution of the active transaction continues based on determining that the extension flag is not set. Execution of the active transaction is aborted based on determining that the extension flag is set.

Abstract: Embodiments relate to automatic pattern-based operand prefetching. An aspect includes receiving, by prefetch logic in a processor, an operand cache miss from a pipeline of the processor. Another aspect includes determining that an entry in a history table corresponding to the operand cache miss exists based on an instruction address of the operand cache miss. Yet another aspect includes, based on determining that the entry corresponding to the operand cache miss exists in the history table, issuing a prefetch instruction for a second operand based on the determined entry in the history table, and writing the determined entry into a miss buffer.

Abstract: A method and central processing unit supporting atomic access of shared data by a sequence of memory access operations. A processor status flag is reset. A processor executes, subsequent to the setting of the processor status flag, a sequence of program instructions with instructions accessing a subset of shared data contained within its local cache. During execution of the sequence of program instructions and in response to a modification by another processor of the subset of shared data, the processor status flag is set. Subsequent to the executing the sequence of program instructions and based upon the state of the processor status flag, either a first program processing or a second program processing is executed. In some examples the first program processing includes storing results data into the local cache and the second program processing includes discarding the results data.

Abstract: A method and central processing unit supporting atomic access of shared data by a sequence of memory access operations. A processor status flag is reset. A processor executes, subsequent to the setting of the processor status flag, a sequence of program instructions with instructions accessing a subset of shared data contained within its local cache. During execution of the sequence of program instructions and in response to a modification by another processor of the subset of shared data, the processor status flag is set. Subsequent to the executing the sequence of program instructions and based upon the state of the processor status flag, either a first program processing or a second program processing is executed. In some examples the first program processing includes storing results data into the local cache and the second program processing includes discarding the results data.

Abstract: Responsive to receiving a logical address for a cache access, a mechanism looks up a first portion of the logical address in a local cache directory for a local cache. The local cache directory returns a set identifier for each set in the local cache directory. Each set identifier indicates a set within a higher level cache directory. The mechanism looks up a second portion of the logical address in the higher level cache directory and compares each absolute address value received from the higher level cache directory to an absolute address received from a translation look-aside buffer to generate a higher level cache hit signal. The mechanism compares the higher level cache hit signal to each set identifier to generate a local cache hit signal and responsive to the local cache hit signal indicating a local cache hit, accesses the local cache based on the local cache hit signal.