[PATCH] D31210: [AMDGPU] Add new address space mapping

[Yaxun Liu via Phabricator via cfe-commits]

yaxunl added inline comments.


================
Comment at: lib/Basic/Targets.cpp:2029-2040
+      if (UseNew) {
+        Generic   = 0;
+        Global    = 1;
+        Local     = 3;
+        Constant  = 4;
+        Private   = 5;
+      } else {
----------------
tstellar wrote:
> What are these values used for?
The new address space mapping will be used for all kernel languages, especially for C++-based kernel languages like HCC/OpenMP/CUDA. 

We found the old address space mapping is unable to support C++ based kernel languages, that's the motivation of this change.

Eventually we will switch to the new address space mapping.

We temporarily keep two address space mapping during the transition,


================
Comment at: lib/Basic/Targets.cpp:2057
+          4,  // opencl_constant
+          0,  // opencl_generic
+          1,  // cuda_device
----------------
tstellar wrote:
> How will the backend deal with the fact that allocas return generic address space pointers?
Matt will upstream a patch which let alloca return a pointer to private address space.


https://reviews.llvm.org/D31210