Clarify Unified Addressing

[VerenaBeckham]

Unified Addressing should only be within a single context (and the host).

[hdelan]

Perhaps this section of the C++ spec could be extended to USM buffers within SYCL contexts, but not across different contexts.

[gmlueck]

Perhaps this section of the C++ spec could be extended to USM buffers within SYCL contexts, but not across different contexts.

I think that section of the C++ spec is mostly talking about nested objects. How do you think it could be extended to clarify our situation?

FWIW, I considered writing my proposed text in terms of C++ object addresses, but I changed it to refer to USM buffer addresses instead. I did this because the memory returned from the USM allocation routines is raw memory that does not contain any C++ objects.

[hdelan]

It says that except in the mentioned cases

[two objects] have distinct addresses and occupy disjoint bytes of storage

Maybe a better place to extend is here but again this refers to objects rather than memory as you say.

[TApplencourt]

• What is a USM Pointer?
  "An USM pointer, is a pointer who is returned by sycl::malloc_* like"

• Can do that in another PR for "what is allocate USM Pointer"?

  • Thomas will open an Issue

• Verena will update this PR with greg test

[gmlueck]

Looks good. Just a small formatting nit below.

[TApplencourt]

WG: The WG agree to merge this PR at a clarification of 2020.