[PATCH] D39998: AMDGPU: Directly implement computeKnownBits for workitem intrinsics

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPUSubtarget.cpp:357
+    // Used when emitting loads from dispatch packet.
+    MaxSize = getFlatWorkGroupSizes(*I->getParent()->getParent()).second;
+
----------------
You probably need to check isa<LoadInst>(I) here.


https://reviews.llvm.org/D39998