[llvm] [NVPTX] Improve NVVMReflect Efficiency (PR #134416)

[Alex MacLean via llvm-commits]

================
@@ -78,27 +91,51 @@ INITIALIZE_PASS(NVVMReflect, "nvvm-reflect",
                 "Replace occurrences of __nvvm_reflect() calls with 0/1", false,
                 false)
 
-static bool runNVVMReflect(Function &F, unsigned SmVersion) {
-  if (!NVVMReflectEnabled)
-    return false;
+static cl::list<std::string>
+    ReflectList("nvvm-reflect-list", cl::value_desc("name=<int>"), cl::Hidden,
+                cl::desc("A list of string=num assignments"),
+                cl::ValueRequired);
 
-  if (F.getName() == NVVM_REFLECT_FUNCTION ||
-      F.getName() == NVVM_REFLECT_OCL_FUNCTION) {
-    assert(F.isDeclaration() && "_reflect function should not have a body");
-    assert(F.getReturnType()->isIntegerTy() &&
-           "_reflect's return type should be integer");
-    return false;
+/// The command line can look as follows :
+/// -nvvm-reflect-list a=1,b=2 -nvvm-reflect-list c=3,d=0 -R e=2
+/// The strings "a=1,b=2", "c=3,d=0", "e=2" are available in the
+/// ReflectList vector. First, each of ReflectList[i] is 'split'
+/// using "," as the delimiter. Then each of this part is split
+/// using "=" as the delimiter.
+void NVVMReflect::setVarMap(Module &M) {
+  if (auto *Flag = mdconst::extract_or_null<ConstantInt>(
+          M.getModuleFlag("nvvm-reflect-ftz")))
+    VarMap["__CUDA_FTZ"] = Flag->getSExtValue();
+
+  for (unsigned I = 0, E = ReflectList.size(); I != E; ++I) {
----------------
AlexMaclean wrote:

Can you use a foreach loop here?

https://github.com/llvm/llvm-project/pull/134416