<div dir="ltr"><div>We are considering supporting loop unrolling pragma in clang for CUDA, and want to scope what needs to be done. I came across a 3-year old post discussing this (<a href="http://lists.cs.uiuc.edu/pipermail/llvmdev/2010-June/032074.html">http://lists.cs.uiuc.edu/pipermail/llvmdev/2010-June/032074.html</a>). Is there any follow-up work/discussion on this topic? For instance, does Clang translate per-loop pragma to metadata? How stable is such metadata against LLVM standard optimizations? </div>
<div><br></div><div>Thanks, </div><div>Jingyue</div><div><br></div><div><br></div></div>