Cache only memory architecture (COMA) is a computer memory organization for use in multiprocessors in which the local memories (typically DRAM) at each node are used as cache. This is in contrast to using the local memories as actual main memory, as in NUMA organizations. The terms storage (U.K.) or memory (U.S.) refer to the parts of a digital computer that retain physical state (data) for some interval of time, possibly even after electrical power to the computer is turned off. ... Multiprocessing is traditionally known as the use of multiple concurrent processes in a system as opposed to a single process at any one instant. ... Dram can mean several things: For the imperial unit of volume see dram (unit), commonly used to describe a measure of Scotch whisky For the imperial unit of weight or mass see avoirdupois and apothecaries system (of mass) For the Armenian monetary unit see dram (currency) DRAM is a type... Non-Uniform Memory Access or Non-Uniform Memory Architecture (NUMA) is a computer memory design used in multiprocessors, where the memory access time depends on the memory location relative to a processor. ...

In NUMA, each address in the global address space is typically assigned a fixed home node. When processors access some data, a copy is made in their local cache, but space remains allocated in the home node. Instead, with COMA, there is no home. An access from a remote node may cause that data to migrate. Compared to NUMA, this reduces the number of redundant copies and may allow more efficient use of the memory resources. On the other hand, it raises problems of how to find a particular datum (there is no longer a home node) and what to do if a local memory fills up (migrating some data into the local memory then needs to evict some other data, which doesn't have a home to go to). Hardware memory coherence mechanisms are typically used to implement the migration. Memory coherence (also cache coherence or cache consistency) is the property of the shared memory systems (multiprocessors and distributed shared memory systems) in which any shared piece of memory (cache line or memory page) gives consistent values with accordance to earlier agreed consistency model despite accesses (maybe parallel) from different...

A huge body of research has explored these issues. Various forms of directories, policies for maintaining free space in the local memories, migration policies, and policies for read-only copies have been developed. Hybrid NUMA-COMA organizations have also been proposed, such as Reactive NUMA, which allows pages to start in NUMA mode and switch to COMA mode if appropriate and is implemented in the Sun WildFire.

See also

• Non-Uniform Memory Architecture

Non-Uniform Memory Access or Non-Uniform Memory Architecture (NUMA) is a computer memory design used in multiprocessors, where the memory access time depends on the memory location relative to a processor. ...

References

• F. Dahlgren and J. Torrellas (June 1999). "Cache-only memory architectures". IEEE Computer 32 (6): 72–79. 
• E. Hagersten, A. Landin, and S. Haridi (September 1992). "DDM-A cache-only memory architecture". IEEE Computer 25 (9): 44–54. 
• B. Falsafi and D. A. Wood (June 1997). "Reactive NUMA: a design for unifying S-COMA and CC-NUMA". Proceedings of the 24th Annual International Symposium on Computer Architecture (ISCA): 229–40.