[PATCH] D142642: [mlgo] Introduce an "InteractiveModelRunner"

[Jacob Hegna via Phabricator via llvm-commits]

jacobhegna added inline comments.


================
Comment at: llvm/lib/Analysis/InteractiveModelRunner.cpp:50
+  const size_t Limit = OutputBuffer.size();
+  while (InsPoint < Limit) {
+    auto Read = Inbound.read(Buff + InsPoint, OutputBuffer.size() - InsPoint);
----------------
When waiting for advice, the compiler blocks until it reads the number of bytes specified by the output tensor spec size. Do we want to make any assurances of what will happen if the host sends bad data back over the wire, writes too much data, etc? Or we just say "that's the host's problem." If so, I think we should document that in the description of the class.



Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D142642/new/

https://reviews.llvm.org/D142642