White PapersThe AMD Athlon 64 and AMD Opteron family of single-core and dual-core multiprocessor systems are based on the cache coherent Non-Uniform Memory Access (ccNUMA) architecture. In this architecture, each processor has access to its own low-latency, local memory (through the processor’s on-die local memory controller), as well as to higher latency remote memory through the on-die memory controllers of the other processors in the multiprocessor environment. At the same time, the ccNUMA architecture is designed to maintain the cache coherence of the entire shared memory space. The high-performance coherent HyperTransport technology interconnects between processors in the multiprocessor system permit remote memory access and cache coherence.
As developers deploy more demanding workloads on these multiprocessor systems, common performance questions arise: Where should threads or processes be scheduled (thread or process placement)? Where should memory be allocated (memory placement)? The underlying operating system (OS), tuned for AMD Athlon 64 and AMD Opteron multiprocessor ccNUMA systems, makes these performance decisions transparent and easy. Advanced developers, however, should be aware of the more advanced tools and techniques available for performance tuning.
