[LLVM] New NoDivergenceSource function attribute (#111832)

A call to a function that has this attribute is not a source of
divergence, as used by UniformityAnalysis. That allows a front-end to
use known-name calls as an instruction extension mechanism (e.g.
https://github.com/GPUOpen-Drivers/llvm-dialects ) without such a call
being a source of divergence.

Author: trenouf

llvm/docs/LangRef.rst

@@ -2082,6 +2082,12 @@ example:
     function call, use of ``longjmp``, or other means. It is a compiler hint that
     is used at module level to improve dataflow analysis, dropped during linking,
     and has no effect on functions defined in the current module.
+``nodivergencesource``
+    A call to this function is not a source of divergence. In uniformity
+    analysis, a *source of divergence* is an instruction that generates
+    divergence even if its inputs are uniform. A call with no further information
+    would normally be considered a source of divergence; setting this attribute
+    on a function means that a call to it is not a source of divergence.
 ``noduplicate``
     This attribute indicates that calls to the function cannot be
     duplicated. A call to a ``noduplicate`` function may be moved

llvm/include/llvm/Bitcode/LLVMBitCodes.h

@@ -767,6 +767,7 @@ enum AttributeKindCodes {
   ATTR_KIND_SANITIZE_REALTIME_UNSAFE = 97,
   ATTR_KIND_CORO_ELIDE_SAFE = 98,
   ATTR_KIND_NO_EXT = 99,
+  ATTR_KIND_NO_DIVERGENCE_SOURCE = 100,
 };
 
 enum ComdatSelectionKindCodes {

llvm/include/llvm/IR/Attributes.td

@@ -183,6 +183,9 @@ def NoCallback : EnumAttr<"nocallback", IntersectAnd, [FnAttr]>;
 /// Function creates no aliases of pointer.
 def NoCapture : EnumAttr<"nocapture", IntersectAnd, [ParamAttr]>;
 
+/// Function is not a source of divergence.
+def NoDivergenceSource : EnumAttr<"nodivergencesource", IntersectAnd, [FnAttr]>;
+
 /// Call cannot be duplicated.
 def NoDuplicate : EnumAttr<"noduplicate", IntersectPreserve, [FnAttr]>;
 

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -292,6 +292,10 @@ bool TargetTransformInfo::hasBranchDivergence(const Function *F) const {
 }
 
 bool TargetTransformInfo::isSourceOfDivergence(const Value *V) const {
+  if (const auto *Call = dyn_cast<CallBase>(V)) {
+    if (Call->hasFnAttr(Attribute::NoDivergenceSource))
+      return false;
+  }
   return TTIImpl->isSourceOfDivergence(V);
 }
 

llvm/lib/Bitcode/Reader/BitcodeReader.cpp

@@ -2066,6 +2066,8 @@ static Attribute::AttrKind getAttrFromCode(uint64_t Code) {
     return Attribute::NoCallback;
   case bitc::ATTR_KIND_NO_CAPTURE:
     return Attribute::NoCapture;
+  case bitc::ATTR_KIND_NO_DIVERGENCE_SOURCE:
+    return Attribute::NoDivergenceSource;
   case bitc::ATTR_KIND_NO_DUPLICATE:
     return Attribute::NoDuplicate;
   case bitc::ATTR_KIND_NOFREE:

llvm/lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -763,6 +763,8 @@ static uint64_t getAttrKindEncoding(Attribute::AttrKind Kind) {
     return bitc::ATTR_KIND_NO_CALLBACK;
   case Attribute::NoCapture:
     return bitc::ATTR_KIND_NO_CAPTURE;
+  case Attribute::NoDivergenceSource:
+    return bitc::ATTR_KIND_NO_DIVERGENCE_SOURCE;
   case Attribute::NoDuplicate:
     return bitc::ATTR_KIND_NO_DUPLICATE;
   case Attribute::NoFree:

llvm/lib/Transforms/Utils/CodeExtractor.cpp

@@ -917,6 +917,7 @@ Function *CodeExtractor::constructFunction(const ValueSet &inputs,
       case Attribute::NoFPClass:
       case Attribute::CoroDestroyOnlyWhenComplete:
       case Attribute::CoroElideSafe:
+      case Attribute::NoDivergenceSource:
         continue;
       // Those attributes should be safe to propagate to the extracted function.
       case Attribute::AlwaysInline:

llvm/test/Analysis/UniformityAnalysis/AMDGPU/nodivergencesource.ll

@@ -0,0 +1,16 @@
+; RUN: opt -mtriple amdgcn-- -passes='print<uniformity>' -disable-output %s 2>&1 | FileCheck %s
+
+; CHECK: DIVERGENT: %divergentval
+; CHECK-NOT: DIVERGENT: %uniformval
+; CHECK: %uniformval
+define void @test() {
+  %divergentval = call i32 @normalfunc()
+  %uniformval = call i32 @nodivergencesourcefunc()
+  ret void
+}
+
+declare i32 @normalfunc() #0
+declare i32 @nodivergencesourcefunc() #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind nodivergencesource }

llvm/test/Bitcode/attributes.ll

@@ -537,6 +537,11 @@ define void @f91(ptr dead_on_unwind %p) {
   ret void
 }
 
+; CHECK: define void @f94() [[NODIVERGENCESOURCE:#[0-9]+]]
+define void @f94() nodivergencesource {
+  ret void;
+}
+
 ; CHECK: define range(i32 -1, 42) i32 @range_attribute(<4 x i32> range(i32 -1, 42) %a)
 define range(i32 -1, 42) i32 @range_attribute(<4 x i32> range(i32 -1, 42) %a) {
   ret i32 0
@@ -615,4 +620,5 @@ define void @initializes(ptr initializes((-4, 0), (4, 8)) %a) {
 ; CHECK: attributes [[FNRETTHUNKEXTERN]] = { fn_ret_thunk_extern }
 ; CHECK: attributes [[SKIPPROFILE]] = { skipprofile }
 ; CHECK: attributes [[OPTDEBUG]] = { optdebug }
+; CHECK: attributes [[NODIVERGENCESOURCE]] = { nodivergencesource }
 ; CHECK: attributes #[[NOBUILTIN]] = { nobuiltin }