Lines Matching full:or

11 comprises multiple components or assemblies each of which may contain 0
12 or more CPUs, local memory, and/or IO buses.  For brevity and to
20 connected together with some sort of system interconnect--e.g., a crossbar or
26 Coherent NUMA or ccNUMA systems.   With ccNUMA systems, all memory is visible
28 is handled in hardware by the processor caches and/or the system interconnect.
31 away the cell containing the CPU or IO bus making the memory access is from the
41 [cache misses] to be to "local" memory--memory on the same cell, if any--or
49 architectures.  As with physical cells, software nodes may contain 0 or more
50 CPUs, memory and/or IO buses.  And, again, memory accesses to memory on
63 the existing nodes--or the system memory for non-NUMA platforms--into multiple
73 each memory zone [one or more of DMA, DMA32, NORMAL, HIGH_MEMORY, MOVABLE],
77 "overflow" or "fallback".
81 fall back to the same zone type on a different node, or to a different zone
83 such as DMA or DMA32, represent relatively scarce resources.  Linux chooses
114 privileged user can specify in the scheduling or NUMA commands and functions
127 Some kernel allocations do not want or cannot tolerate this allocation fallback
129 or get notified that the node has no free memory.  This is usually the case when
134 numa_node_id() or CPU_to_node() functions and then request memory from only
137 example of this.  Or, the subsystem may choose to disable or not to enable
143 or some subsystems would fail to initialize if they attempted to allocated
146 or cpu_to_mem() function to locate the "local memory node" for the calling or