[PATCH] D66388: AMDGPU/GlobalISel: Implement addrspacecast for 32-bit constant addrspace

[Marek Olšák via Phabricator via llvm-commits]

mareko added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:1147
+    return true;
+  }
+
----------------
The amdgpu-32bit-address-high-bits function attribute determines the high 32 bits. They are not 0.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D66388/new/

https://reviews.llvm.org/D66388