[PATCH] D153257: AMDGPU: Implement llvm.set.rounding

[Pierre van Houtryve via Phabricator via llvm-commits]

Pierre-vh added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:3616-3617
+      uint32_t ClampedVal = std::min(
+          static_cast<uint32_t>(ConstMode->getZExtValue()),
+          static_cast<uint32_t>(AMDGPU::TowardZeroF32_TowardNegativeF64));
+      NewMode = DAG.getConstant(
----------------
optional nit: can use the constructor form to make it less verbose (same below for the `uint64_t`)



================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:3621
+  } else {
+    SDValue BitTable =
+      DAG.getConstant(AMDGPU::FltRoundToHWConversionTable, SL, MVT::i64);
----------------
Can you add a short explanation of how the lowering works, with the bit table?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153257/new/

https://reviews.llvm.org/D153257