[NVPTX] remove unnecessary named metadata update that happens to brea…

…k debug info.

Also added test case to verify IR changes done by NVPTXGenericToNVVM pass.

Differential Revision: https://reviews.llvm.org/D22837

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@277520 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/NVPTX/NVPTXGenericToNVVM.cpp

@@ -55,7 +55,6 @@ class GenericToNVVM : public ModulePass {
                                                 IRBuilder<> &Builder);
   Value *remapConstantExpr(Module *M, Function *F, ConstantExpr *C,
                            IRBuilder<> &Builder);
-  void remapNamedMDNode(ValueToValueMapTy &VM, NamedMDNode *N);
 
   typedef ValueMap<GlobalVariable *, GlobalVariable *> GVMapTy;
   typedef ValueMap<Constant *, Value *> ConstantToValueMapTy;
@@ -130,12 +129,6 @@ bool GenericToNVVM::runOnModule(Module &M) {
   for (auto I = GVMap.begin(), E = GVMap.end(); I != E; ++I)
     VM[I->first] = I->second;
 
-  // Walk through the metadata section and update the debug information
-  // associated with the global variables in the default address space.
-  for (NamedMDNode &I : M.named_metadata()) {
-    remapNamedMDNode(VM, &I);
-  }
-
   // Walk through the global variable  initializers, and replace any use of
   // original global variables in GVMap with a use of the corresponding copies
   // in GVMap.  The copies need to be bitcast to the original global variable
@@ -360,32 +353,3 @@ Value *GenericToNVVM::remapConstantExpr(Module *M, Function *F, ConstantExpr *C,
     llvm_unreachable("GenericToNVVM encountered an unsupported ConstantExpr");
   }
 }
-
-void GenericToNVVM::remapNamedMDNode(ValueToValueMapTy &VM, NamedMDNode *N) {
-
-  bool OperandChanged = false;
-  SmallVector<MDNode *, 16> NewOperands;
-  unsigned NumOperands = N->getNumOperands();
-
-  // Check if any operand is or contains a global variable in  GVMap, and thus
-  // converted to another value.
-  for (unsigned i = 0; i < NumOperands; ++i) {
-    MDNode *Operand = N->getOperand(i);
-    MDNode *NewOperand = MapMetadata(Operand, VM);
-    OperandChanged |= Operand != NewOperand;
-    NewOperands.push_back(NewOperand);
-  }
-
-  // If none of the operands has been modified, return immediately.
-  if (!OperandChanged) {
-    return;
-  }
-
-  // Replace the old operands with the new operands.
-  N->dropAllReferences();
-  for (SmallVectorImpl<MDNode *>::iterator I = NewOperands.begin(),
-                                           E = NewOperands.end();
-       I != E; ++I) {
-    N->addOperand(*I);
-  }
-}

test/CodeGen/NVPTX/generic-to-nvvm-ir.ll

@@ -0,0 +1,64 @@
+; Verify functionality of NVPTXGenericToNVVM.cpp pass.
+;
+; RUN: opt < %s -march nvptx64 -S -generic-to-nvvm -verify-debug-info | FileCheck %s
+
+target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; Generic space variables should be converted to global space AKA addrspace(1).
+; CHECK-DAG: @static_var = {{.*}}addrspace(1)
+@static_var = externally_initialized global i8 0, align 1
+; CHECK-DAG: @.str = {{.*}}addrspace(1)
+@.str = private unnamed_addr constant [4 x i8] c"XXX\00", align 1
+
+; Function Attrs: convergent
+define void @func() !dbg !8 {
+;CHECK-LABEL: @func()
+;CHECK-SAME: !dbg [[FUNCNODE:![0-9]+]]
+entry:
+; References to the variables must be converted back to generic address space via llvm intrinsic call
+; CHECK-DAG: call i8* @llvm.nvvm.ptr.global.to.gen.p0i8.p1i8({{.*}} addrspace(1)* @.str
+  %0 = load i8, i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), align 1
+  call void @extfunc(i8 signext %0)
+; CHECK-DAG: call i8* @llvm.nvvm.ptr.global.to.gen.p0i8.p1i8(i8 addrspace(1)* @static_var
+  %1 = load i8, i8* @static_var, align 1
+  call void @extfunc(i8 signext %1)
+  ret void
+; CHECK: ret void
+}
+
+declare void @extfunc(i8 signext)
+
+!llvm.dbg.cu = !{!0}
+; CHECK: !llvm.dbg.cu = !{[[CUNODE:![0-9]+]]}
+!llvm.module.flags = !{!6, !7}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, file: !1,
+      producer: "clang version 4.0.0",
+      isOptimized: false, runtimeVersion: 0, emissionKind: FullDebug, enums: !2, globals: !3)
+; CHECK: [[CUNODE]] = distinct !DICompileUnit({{.*}} globals: [[GLOBALSNODE:![0-9]+]]
+!1 = !DIFile(filename: "foo.cu", directory: "/usr/local/google/home/tra/work/llvm/build/gpu/debug")
+!2 = !{}
+!3 = !{!4}
+; Find list of global variables and make sure it's the one used by DICompileUnit
+; CHECK: [[GLOBALSNODE]] = !{[[GVNODE:![0-9]+]]}
+!4 = distinct !DIGlobalVariable(name: "static_var", scope: !0, file: !1, line: 2, type: !5, isLocal: false,
+               isDefinition: true, variable: i8* @static_var)
+; Debug info must also be updated to reflect new address space.
+; CHECK: [[GVNODE]] = distinct !DIGlobalVariable(name: "static_var"
+; CHECK-SAME: scope: [[CUNODE]]
+; CHECK-SAME: type: [[TYPENODE:![0-9]+]]
+; CHECK-SAME: variable: i8* addrspacecast (i8 addrspace(1)* @static_var to i8*)
+!5 = !DIBasicType(name: "char", size: 8, align: 8, encoding: DW_ATE_signed_char)
+; CHECK: [[TYPENODE]] = !DIBasicType(name: "char"
+!6 = !{i32 2, !"Dwarf Version", i32 4}
+!7 = !{i32 2, !"Debug Info Version", i32 3}
+!8 = distinct !DISubprogram(name: "foo", linkageName: "func",
+      scope: !1, file: !1, line: 3, type: !9, isLocal: false, isDefinition: true, scopeLine: 3,
+      flags: DIFlagPrototyped, isOptimized: false, unit: !0, variables: !2)
+; CHECK: [[FUNCNODE]] = distinct !DISubprogram(name: "foo",
+; CHECK-SAME: type: [[STYPENODE:![0-9]+]]
+; CHECK-SAME: unit: [[CUNODE]],
+!9 = !DISubroutineType(types: !10)
+; CHECK: [[STYPENODE]] = !DISubroutineType
+!10 = !{null}