docs/specs/ppc-spapr-numa.rst

14 Associativity is defined as a group of platform resources that has
113   P1 and P2 does not have a common performance boundary. Since this is a one level
118 In a hypothetical platform where all resources inside the same hardware module
142 value between the relevant resources. LOPAPR does not provide a standard
144 provides a common-performance hierarchy,  and the ibm,associativity-reference-points
157 * resources three NUMA levels apart: 80
178 around for such a long time, with users seeing NUMA distances 10 and 40
179 (and 80 if using NVLink2 GPUs), and there is no need to disrupt the
192 that to the values that the Linux kernel operates on (10, 20, 40, 80, 160).
197 * user distance 61 to 120 will be interpreted as 80
206 have to accept that a large array of values will be translated to the same
230   0  10  40  80
232   2  80  20  10
260   1  40  10  80  40
261   2  20  80  10  20
284 the NUMA level matches. Between 0 and 1, a match in 0x2, we'll also copy
300 node 1 to 2 is 80, matching at 0x1, and distance from 1 to 3 is 40,
310 between 2 and 3 is 20, i.e. a match in 0x3:
342 As mentioned above, the pSeries NUMA distance logic is, in fact, a way to approximate
348   the distance from node A to B is always the same as B to A. We do not support
349   any A-B pair where the distance back and forth is asymmetric. For example, the
361   kind of topology where the distance from a node A to B is X, B to C is X, but
362   the distance A to C is not X. E.g.:
368   1  20  10  80  40
369   2  20  80  10  20
375   nodes. This means that a distance equal to 20 between nodes 0 and 2 and the
387 * if it's a NVLink GPU device, distance: 80
390 The way the pseries Linux guest calculates NUMA distances has a direct effect
397 The first and second level are equal, 0x4, and a third one was added in
405 * all resources that aren't a NVLink GPU, it is guaranteed that they will belong
407 * for NVLink GPUs, distance = 80 from everything else