Silicon Graphics UV 2000, System User'S Manual

Page: 61 / 116

System Features
007-5832-002 41
System Features
The main features of the SGI UV 2000 series server systems are discussed in the following
sections:
• “Modularity and Scalability” on page 41
• “Distributed Shared Memory (DSM)” on page 41
• “Chassis Management Controller (CMC)” on page 43
• “Distributed Shared I/O” on page 43
• “Reliability, Availability, and Serviceability (RAS)” on page 44
Modularity and Scalability
The SGI UV 2000 series systems are modular systems. The components are primarily housed in
building blocks referred to as individual rack units (IRUs). Additional optional mass storage may
be added to the rack along with additional IRUs. You can add different types of blade options to
a system IRU to achieve the desired system configuration. You can easily configure systems
around processing capability, I/O capability, memory size, MIC/GPU capability or storage
capacity. The air-cooled IRU enclosure system has redundant, hot-swap fans and redundant,
hot-swap power supplies.
Distributed Shared Memory (DSM)
In the SGI UV 2000 series server, memory is physically distributed both within and among the
IRU enclosures (compute/memory/I/O blades); however, it is accessible to and shared by all
NUMAlinked devices within the single-system image (SSI). This is to say that all NUMAlinked
components sharing a single Linux operating system, operate and share the memory “fabric” of
the system. Memory latency is the amount of time required for a processor to retrieve data from
memory. Memory latency is lowest when a processor accesses local memory. Note the following
sub-types of memory within a system:
• If a processor accesses memory that is directly connected to its resident socket, the memory
is referred to as local memory. Figure 3-4 on page 42 shows a conceptual block diagram of
the blade’s memory, compute and I/O pathways.
• If a processor needs to access memory located in another socket, or on another blade within
the IRU, (or other NUMAlinked IRUs) the memory is referred to as remote memory.