[PATCH] D14268: AMDGPU: Split x8 and x16 vector loads instead of scalarize

[Tom Stellard via llvm-commits]

tstellarAMD added inline comments.

================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:405-406
@@ -397,1 +404,4 @@
+  // N > 4 stores on the same chain.
+  GatherAllAliasesMaxDepth = 16;
+
   // FIXME: Need to really handle these.
----------------
Was this member variable added in a different patch?


http://reviews.llvm.org/D14268