From 5458014282ff5977db7ccfcf3e8d1c3e68d9aefa Mon Sep 17 00:00:00 2001
From: Christian Sigg <chsigg@users.noreply.github.com>
Date: Wed, 4 Oct 2023 06:05:10 +0200
Subject: [PATCH] [BACKEND] Lower to PTX with `trap-unreachable` (#2429)

We've seen cases where the entire kernel is poisoned due to
division-by-zero, resulting in a single `unreachable` instruction at the
LLIR level. Emit this instruction as `trap` (instead of dropping it) so
that the kernel doesn't run successfully without writing any outputs.
---
 lib/Target/PTX/PTXTranslation.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/Target/PTX/PTXTranslation.cpp b/lib/Target/PTX/PTXTranslation.cpp
index 3ae1bac1a..4a51cc9b3 100644
--- a/lib/Target/PTX/PTXTranslation.cpp
+++ b/lib/Target/PTX/PTXTranslation.cpp
@@ -88,6 +88,7 @@ std::string translateLLVMIRToPTX(llvm::Module &module, int cc, int version) {
   opt.UnsafeFPMath = false;
   opt.NoInfsFPMath = false;
   opt.NoNaNsFPMath = true;
+  opt.TrapUnreachable = true;
   std::unique_ptr<llvm::TargetMachine> machine{target->createTargetMachine(
       module.getTargetTriple(), proc, features, opt, llvm::Reloc::PIC_,
       std::nullopt, llvm::CodeGenOpt::Aggressive)};