International Business Machines Corporation

Chakrapani Rayadurgam

Dean G Bair

William J Lewis

Edward James Kaminski, Jr

Rebecca Marie Gott

Shakti Kapoor

Robert J Sonnelitter, Iii

Manoj Dusanapudi

Sunil Suresh Hatti

Chad G Wilson

Shubhodeep Roy Choudhury

Ekaterina M Ambroladze

Vesselina K Papazova

Hieu Trong Huynh

Jason D Kohl

Tim Bronson

Sampan Arora

Batchu Naga Venkata Satyanarayana

Robert Sonnelitter Iii

Embodiments herein described a coherency protocol for a distributed computing topology that permits for large stalls on various interfaces. In one embodiment, the computing topology includes multiple boards which each contain multiple processors. When a particular core on a processor wants access to data that is not currently stored in its cache, the core can first initiate a request to search for the cache line in the caches for other cores on the same processor. If the cache line is not found, the cache coherency protocol permits the processor to then broadcast a request to the other processors on the same board. If a processor on the same board does not have the data, the processor can then broadcast the request to the other boards in the system. The processors in those boards can then search their caches to identify the data.

System coherency protocol

Methods and systems for cache management are provided. Aspects include providing a drawer including a plurality of clusters, each of the plurality of clusters including a plurality of processor each having one or more cores, wherein each of the one or more cores shares a first cache memory, providing a second cache memory shared among the plurality of clusters, and receiving a cache line request from one of the one or more cores to the first cache memory, wherein the first cache memory sends a request to a memory controller to retrieve the cache line from a memory, store the cache line in the first cache memory, create a directory state associated with the cache line, and provide the directory state to the second cache memory to create a directory entry for the cache line.

Efficient inclusive cache management

Embodiments relate to pre-silicon device testing using a persistent command table. An aspect includes receiving a value for a persistent command parameter from a user. Another aspect includes determining whether the value of the persistent command parameter is greater than zero. Another aspect includes based on determining whether the value of the persistent command parameter is greater than zero, selecting a number of commands equal to the value of the persistent command parameter from a regular command table of a driver of a device under test. Another aspect includes adding the selected commands to the persistent command table of the driver. Another aspect includes performing testing of the device under test via the driver using only commands that are in the persistent command table of the driver.

Persistent command parameter table for pre-silicon device testing

A system and method for creating different start cache and bus states using multiple test patterns for processor design verification and validation is presented. A test pattern generator/tester re-uses test patterns in different configurations that alter cache states and translation lookaside buffer (TLB) states, which produces different timing scenarios on a broadband bus. The test pattern generator/tester creates multiple test patterns for a multi-processor system and executes the test patterns repeatedly in different configurations without rebuilding the test patterns. This enables a system to dedicate more time executing the test patterns instead of building the test patterns. By repeatedly executing the same test patterns in a different configuration, the invention described herein produces different start cache states, different TLB states, along with other processor units, each time the test patterns execute that, in turn, changes the bus timing.

System and method for creating different start cache and bus states using multiple test patterns for processor design verification and validation

A system and method for verifying cache snoop logic and coherency between instruction cache and data cache using instruction stream 'holes' that are created by branch instructions is presented. A test pattern generator includes instructions that load/store data into instruction stream holes. In turn, by executing the test pattern, a processor thread loads an L2 cache line into both instruction cache (icache) and data cache (dcache). The test pattern modifies the data in the dcache in response to a store instruction. In turn, the invention described herein identifies whether snoop logic detects the change and updates the icache's corresponding cache line accordingly.

System and method for verification of cache snoop logic and coherency between instruction & data caches for processor design verification and validation

Growing community of inventors

Bengaluru, India

Chakrapani Rayadurgam