International Business Machines Corporation

Willm Hinrichs

Martin Recktenwald

Markus Kaltenbach

Hans-Werner Tast

Uwe Brandt

Eyal Naor

Walter Heinrich Lipponer

Christian Jacobi

Alper Buyuktosunoglu

Brian Robert Prasky

Anthony Saporito

James J Bonanno

Vijayalakshmi Srinivasan

Brian William Curran

Jane Helen Bartik

Tilman Gloekler

Patrick M West, Jr

John-David Wellman

Thomas G Koehler

Joerg Deutschle

Eberhard Engler

Thuyen Le

Guenter Gerwig

Sebastian Ehrenreich

Jens Kuenzer

Simon H Friedmann

Ralf Ludewig

Barinjato Ramanandray

Driving address translations in a microprocessor system by sending a rejected Lx+1 cache request from a first set of caches of a first level Lx to a central request unit, transferring an Lx+1 cache request having a translation of a virtual address into a physical address stored in a first buffer, from the central request unit to the at least one Lx+1 cache, and keeping an Lx+1 cache request lacking a translation of a virtual address into a physical address stored in the first buffer, pending in the central request unit.

Fetch request arbiter

A first request is received to access a first set of data in a first cache. A likelihood that a second request to a second cache for the first set of data will be canceled is determined. Access to the first set of data is completed based on the determining the likelihood that the second request to the second cache for the first set of data will be canceled.

Selective downstream cache processing for data access

In an approach to tracking and invalidating memory address synonyms in a memory system includes establishing a bits register for a first virtual address in a memory system, the bits register having synonym fields representing each bit of a first synonym identifier portion of the first virtual address, the first virtual address being mapped to a physical address; determining, for a second virtual address mapped to the physical address, the second virtual address having a second synonym identifier portion, a set of differing bits within the second synonym identifier portion compared to the first synonym identifier portion; and registering the set of differing bits in the bits register.

Bits register for synonyms in a memory system

A method for tracking and invalidating memory address synonyms in a cache memory system includes receiving a request to associate a second memory address with a first memory address in a cache memory system that supports synonyms, wherein the second memory address and the first memory address each comprise a synonym identifier. The method also includes determining a set of differing bits within the synonym identifier of the first memory address and the second memory address, and including the set of differing bits within a set of synonym generation bits for the cache memory system. A corresponding apparatus, computer program product, and system are also disclosed herein.

A tool for determining eviction of store cache entries based on store pressure. The tool determines, by one or more computer processors, a count value for one or more new store cache entry allocations. The tool determines whether a new store cache entry allocation limit is exceeded. Responsive to determining the new store cache entry allocation limit is exceeded, the tool determines an allocation value for one or more existing store cache entries, the allocation value indicating an allocation class for each of the one or more existing store cache entries. The tool determines based, at least in part, on the allocation value for the one or more existing store cache entries, at least one allocation class for eviction. The tool program determines an eviction request setting for evicting the one or more existing store cache entries.

Evicting cached stores

A tool for determining eviction of store cache entries based on store pressure. The tool determines, by one or more computer processors, a count value for one or more new store cache entry allocations. The tool determines, by one or more computer processors, whether a new store cache entry allocation limit is exceeded. Responsive to determining the new store cache entry allocation limit is exceeded, the tool determines, by one or more computer processors, an allocation value for one or more existing store cache entries, the allocation value indicating an allocation class for each of the one or more existing store cache entries. The tool determines, by one or more computer processors based, at least in part, on the allocation value for the one or more existing store cache entries, at least one allocation class for eviction. The tool program determines, by one or more computer processors, an eviction request setting for evicting the one or more existing store cache entries.

Cache miss rates for threads operating in a simultaneous multi-threading computer processing environment can be estimated. The single thread rates can be estimated by monitoring a shared directory for cache misses for a first thread. Memory access requests can be routed to metering cache directories associated with the particular thread. Single thread misses to the shared directory and single thread misses to the associated metering cache directory are monitored and a performance indication is determined by comparing the cache misses with the thread misses. The directory in the associated metering cache is rotated, and a second sharing performance indication is determined.

Single-thread cache miss rate estimation

Single thread cache miss rate estimation

A method to merge one or more non-transactional stores and one or more thread-specific transactional stores into one or more cache line templates in a store buffer in a store cache. The method receives a thread-specific non-transactional store address and a first data, maps the store address to a first cache line template, and merges the first data into the first cache line template, according to a store policy. The method further receives a thread-specific transactional store address and a second data, maps the thread-specific store address into a second cache line template, according to a store policy. The method further writes back a copy of a cache line template to a cache and invalidates a third cache line template, which frees the third cache line template from a store address mapping.

Store cache for transactional memory

An indication of time that indicates at least one of the current day and the current time is received. It is determined that a raw interval pulse transmitted by a first oscillator should be adjusted based, at least partly, on the indication of time. In response to determining that the raw interval pulse should be adjusted, a steered time interval pulse is generated based, at least partly, on the raw time interval pulse and the indication of time. The steered time interval pulse is distributed to a plurality of hardware components.

Generation and distribution of steered time interval pulse to a plurality of hardware components of the computing system

Growing community of inventors

Holzgerlingen, Germany

Willm Hinrichs