[flang] Apply nocapture attribute to dummy arguments (#116182)

Apply llvm.nocapture attribute to dummy arguments that do not have the
target, asynchronous, volatile, or pointer attributes in a procedure
that is not a bind(c). This was discussed in


https://discourse.llvm.org/t/applying-the-nocapture-attribute-to-reference-passed-arguments-in-fortran-subroutines/81401

22 files changed, 164 insertions, 100 deletions

diff --git a/flang/lib/Optimizer/Passes/Pipelines.cpp b/flang/lib/Optimizer/Passes/Pipelines.cpp
index 1568165..0b7b3ba 100644
--- a/flang/lib/Optimizer/Passes/Pipelines.cpp
+++ b/flang/lib/Optimizer/Passes/Pipelines.cpp
@@ -278,22 +278,17 @@ void createDefaultFIRCodeGenPassPipeline(mlir::PassManager &pm,
   // Add function attributes
   mlir::LLVM::framePointerKind::FramePointerKind framePointerKind;
 
-  if (config.FramePointerKind != llvm::FramePointerKind::None ||
-      config.NoInfsFPMath || config.NoNaNsFPMath || config.ApproxFuncFPMath ||
-      config.NoSignedZerosFPMath || config.UnsafeFPMath) {
-    if (config.FramePointerKind == llvm::FramePointerKind::NonLeaf)
-      framePointerKind =
-          mlir::LLVM::framePointerKind::FramePointerKind::NonLeaf;
-    else if (config.FramePointerKind == llvm::FramePointerKind::All)
-      framePointerKind = mlir::LLVM::framePointerKind::FramePointerKind::All;
-    else
-      framePointerKind = mlir::LLVM::framePointerKind::FramePointerKind::None;
-
-    pm.addPass(fir::createFunctionAttr(
-        {framePointerKind, config.NoInfsFPMath, config.NoNaNsFPMath,
-         config.ApproxFuncFPMath, config.NoSignedZerosFPMath,
-         config.UnsafeFPMath}));
-  }
+  if (config.FramePointerKind == llvm::FramePointerKind::NonLeaf)
+    framePointerKind = mlir::LLVM::framePointerKind::FramePointerKind::NonLeaf;
+  else if (config.FramePointerKind == llvm::FramePointerKind::All)
+    framePointerKind = mlir::LLVM::framePointerKind::FramePointerKind::All;
+  else
+    framePointerKind = mlir::LLVM::framePointerKind::FramePointerKind::None;
+
+  pm.addPass(fir::createFunctionAttr(
+      {framePointerKind, config.NoInfsFPMath, config.NoNaNsFPMath,
+       config.ApproxFuncFPMath, config.NoSignedZerosFPMath,
+       config.UnsafeFPMath}));
 
   fir::addFIRToLLVMPass(pm, config);
 }
diff --git a/flang/lib/Optimizer/Transforms/FunctionAttr.cpp b/flang/lib/Optimizer/Transforms/FunctionAttr.cpp
index 69c4159..c79843f 100644
--- a/flang/lib/Optimizer/Transforms/FunctionAttr.cpp
+++ b/flang/lib/Optimizer/Transforms/FunctionAttr.cpp
@@ -10,6 +10,8 @@
 /// \file
 /// This is a generic pass for adding attributes to functions.
 //===----------------------------------------------------------------------===//
+#include "flang/Optimizer/Dialect/FIROpsSupport.h"
+#include "flang/Optimizer/Support/InternalNames.h"
 #include "flang/Optimizer/Transforms/Passes.h"
 #include "mlir/Dialect/LLVMIR/LLVMAttrs.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
@@ -45,6 +47,24 @@ void FunctionAttrPass::runOnOperation() {
 
   LLVM_DEBUG(llvm::dbgs() << "Func-name:" << func.getSymName() << "\n");
 
+  llvm::StringRef name = func.getSymName();
+  auto deconstructed = fir::NameUniquer::deconstruct(name);
+  bool isFromModule = !deconstructed.second.modules.empty();
+
+  if ((isFromModule || !func.isDeclaration()) &&
+      !fir::hasBindcAttr(func.getOperation())) {
+    llvm::StringRef nocapture = mlir::LLVM::LLVMDialect::getNoCaptureAttrName();
+    mlir::UnitAttr unitAttr = mlir::UnitAttr::get(func.getContext());
+
+    for (auto [index, argType] : llvm::enumerate(func.getArgumentTypes())) {
+      if (mlir::isa<fir::ReferenceType>(argType) &&
+          !func.getArgAttr(index, fir::getTargetAttrName()) &&
+          !func.getArgAttr(index, fir::getAsynchronousAttrName()) &&
+          !func.getArgAttr(index, fir::getVolatileAttrName()))
+        func.setArgAttr(index, nocapture, unitAttr);
+    }
+  }
+
   mlir::MLIRContext *context = &getContext();
   if (framePointerKind != mlir::LLVM::framePointerKind::FramePointerKind::None)
     func->setAttr("frame_pointer", mlir::LLVM::FramePointerKindAttr::get(
diff --git a/flang/test/Driver/mlir-pass-pipeline.f90 b/flang/test/Driver/mlir-pass-pipeline.f90
index 7d57135..33c8183 100644
--- a/flang/test/Driver/mlir-pass-pipeline.f90
+++ b/flang/test/Driver/mlir-pass-pipeline.f90
@@ -123,5 +123,7 @@ end program
 ! ALL-NEXT: ExternalNameConversion
 ! ALL-NEXT: TargetRewrite
 ! ALL-NEXT: CompilerGeneratedNamesConversion
+! ALL-NEXT:  'func.func' Pipeline
+! ALL-NEXT:   FunctionAttr
 ! ALL-NEXT: FIRToLLVMLowering
 ! ALL-NOT: LLVMIRLoweringPass
diff --git a/flang/test/Fir/arrayset.fir b/flang/test/Fir/arrayset.fir
index a9630c8..d201e34 100644
--- a/flang/test/Fir/arrayset.fir
+++ b/flang/test/Fir/arrayset.fir
@@ -1,7 +1,7 @@
 // RUN: tco %s | FileCheck %s
 // RUN: %flang_fc1 -emit-llvm %s -o - | FileCheck %s
 
-// CHECK-LABEL: define void @x(ptr %0)
+// CHECK-LABEL: define void @x(ptr nocapture %0)
 func.func @x(%arr : !fir.ref<!fir.array<10xf32>>) {
   %1 = arith.constant 0 : index
   %2 = arith.constant 9 : index
diff --git a/flang/test/Fir/arrexp.fir b/flang/test/Fir/arrexp.fir
index 5d265a5..3363ead 100644
--- a/flang/test/Fir/arrexp.fir
+++ b/flang/test/Fir/arrexp.fir
@@ -1,7 +1,7 @@
 // RUN: tco %s | FileCheck %s
 
 // CHECK-LINE: define void @f1
-// CHECK: (ptr %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
+// CHECK: (ptr nocapture %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
 func.func @f1(%a : !fir.ref<!fir.array<?x?xf32>>, %n : index, %m : index, %o : index, %p : index, %f : f32) {
   %c1 = arith.constant 1 : index
   %s = fir.shape_shift %o, %n, %p, %m : (index, index, index, index) -> !fir.shapeshift<2>
@@ -23,7 +23,7 @@ func.func @f1(%a : !fir.ref<!fir.array<?x?xf32>>, %n : index, %m : index, %o : i
 }
 
 // CHECK-LINE: define void @f2
-// CHECK: (ptr %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
+// CHECK: (ptr nocapture %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
 func.func @f2(%a : !fir.ref<!fir.array<?x?xf32>>, %b : !fir.ref<!fir.array<?x?xf32>>, %n : index, %m : index, %o : index, %p : index, %f : f32) {
   %c1 = arith.constant 1 : index
   %s = fir.shape_shift %o, %n, %p, %m : (index, index, index, index) -> !fir.shapeshift<2>
@@ -47,7 +47,7 @@ func.func @f2(%a : !fir.ref<!fir.array<?x?xf32>>, %b : !fir.ref<!fir.array<?x?xf
 }
 
 // CHECK-LINE: define void @f3
-// CHECK: (ptr %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
+// CHECK: (ptr nocapture %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
 func.func @f3(%a : !fir.ref<!fir.array<?x?xf32>>, %b : !fir.ref<!fir.array<?x?xf32>>, %n : index, %m : index, %o : index, %p : index, %f : f32) {
   %c1 = arith.constant 1 : index
   %s = fir.shape_shift %o, %n, %p, %m : (index, index, index, index) -> !fir.shapeshift<2>
@@ -72,7 +72,7 @@ func.func @f3(%a : !fir.ref<!fir.array<?x?xf32>>, %b : !fir.ref<!fir.array<?x?xf
 }
 
 // CHECK-LINE: define void @f4
-// CHECK: (ptr %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
+// CHECK: (ptr nocapture %[[A:[^,]*]], {{.*}}, float %[[F:.*]])
 func.func @f4(%a : !fir.ref<!fir.array<?x?xf32>>, %b : !fir.ref<!fir.array<?x?xf32>>, %n : index, %m : index, %o : index, %p : index, %f : f32) {
   %c1 = arith.constant 1 : index
   %s = fir.shape_shift %o, %n, %p, %m : (index, index, index, index) -> !fir.shapeshift<2>
@@ -165,7 +165,7 @@ func.func @f6(%arg0: !fir.box<!fir.array<?xf32>>, %arg1: f32) {
 // Non contiguous array with lower bounds (x = y(100), with y(4:))
 // Test array_coor offset computation.
 // CHECK-LABEL:  define void @f7(
-// CHECK: ptr %[[X:[^,]*]], ptr %[[Y:.*]])
+// CHECK: ptr nocapture %[[X:[^,]*]], ptr %[[Y:.*]])
 func.func @f7(%arg0: !fir.ref<f32>, %arg1: !fir.box<!fir.array<?xf32>>) {
   %c4 = arith.constant 4 : index
   %c100 = arith.constant 100 : index
@@ -181,7 +181,7 @@ func.func @f7(%arg0: !fir.ref<f32>, %arg1: !fir.box<!fir.array<?xf32>>) {
 
 // Test A(:, :)%x reference codegen with A constant shape.
 // CHECK-LABEL:  define void @f8(
-// CHECK-SAME: ptr %[[A:.*]], i32 %[[I:.*]])
+// CHECK-SAME: ptr nocapture %[[A:.*]], i32 %[[I:.*]])
 func.func @f8(%a : !fir.ref<!fir.array<2x2x!fir.type<t{i:i32}>>>, %i : i32) {
   %c0 = arith.constant 0 : index
   %c1 = arith.constant 1 : index
@@ -198,7 +198,7 @@ func.func @f8(%a : !fir.ref<!fir.array<2x2x!fir.type<t{i:i32}>>>, %i : i32) {
 
 // Test casts in in array_coor offset computation when type parameters are not i64
 // CHECK-LABEL: define ptr @f9(
-// CHECK-SAME: i32 %[[I:.*]], i64 %{{.*}}, i64 %{{.*}}, ptr %[[C:.*]])
+// CHECK-SAME: i32 %[[I:.*]], i64 %{{.*}}, i64 %{{.*}}, ptr nocapture %[[C:.*]])
 func.func @f9(%i: i32, %e : i64, %j: i64, %c: !fir.ref<!fir.array<?x?x!fir.char<1,?>>>) -> !fir.ref<!fir.char<1,?>> {
   %s = fir.shape %e, %e : (i64, i64) -> !fir.shape<2>
   // CHECK: %[[CAST:.*]] = sext i32 %[[I]] to i64
diff --git a/flang/test/Fir/basic-program.fir b/flang/test/Fir/basic-program.fir
index 4b18acb..ad5201a 100644
--- a/flang/test/Fir/basic-program.fir
+++ b/flang/test/Fir/basic-program.fir
@@ -120,6 +120,8 @@ func.func @_QQmain() {
 // PASSES-NEXT:   (S) 0 num-dce'd - Number of operations eliminated
 // PASSES-NEXT: TargetRewrite
 // PASSES-NEXT: CompilerGeneratedNamesConversion
+// PASSES-NEXT: 'func.func' Pipeline
+// PASSES-NEXT:  FunctionAttr
 // PASSES-NEXT: FIRToLLVMLowering
 // PASSES-NEXT: ReconcileUnrealizedCasts
 // PASSES-NEXT: LLVMIRLoweringPass
diff --git a/flang/test/Fir/box-offset-codegen.fir b/flang/test/Fir/box-offset-codegen.fir
index 389ceeb..5be3ad1 100644
--- a/flang/test/Fir/box-offset-codegen.fir
+++ b/flang/test/Fir/box-offset-codegen.fir
@@ -7,7 +7,7 @@ func.func @scalar_addr(%scalar : !fir.ref<!fir.box<!fir.type<t>>>) -> !fir.llvm_
   return %addr : !fir.llvm_ptr<!fir.ref<!fir.type<t>>>
 }
 // CHECK-LABEL: define ptr @scalar_addr(
-// CHECK-SAME: ptr %[[BOX:.*]]){{.*}}{
+// CHECK-SAME: ptr nocapture %[[BOX:.*]]){{.*}}{
 // CHECK:    %[[VAL_0:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, ptr %[[BOX]], i32 0, i32 0
 // CHECK:    ret ptr %[[VAL_0]]
 
@@ -16,7 +16,7 @@ func.func @scalar_tdesc(%scalar : !fir.ref<!fir.box<!fir.type<t>>>) -> !fir.llvm
   return %tdesc : !fir.llvm_ptr<!fir.tdesc<!fir.type<t>>>
 }
 // CHECK-LABEL: define ptr @scalar_tdesc(
-// CHECK-SAME: ptr %[[BOX:.*]]){{.*}}{
+// CHECK-SAME: ptr nocapture %[[BOX:.*]]){{.*}}{
 // CHECK:    %[[VAL_0:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }, ptr %[[BOX]], i32 0, i32 7
 // CHECK:    ret ptr %[[VAL_0]]
 
@@ -25,7 +25,7 @@ func.func @array_addr(%array : !fir.ref<!fir.class<!fir.ptr<!fir.array<?x!fir.ty
   return %addr : !fir.llvm_ptr<!fir.ptr<!fir.array<?x!fir.type<t>>>>
 }
 // CHECK-LABEL: define ptr @array_addr(
-// CHECK-SAME: ptr %[[BOX:.*]]){{.*}}{
+// CHECK-SAME: ptr nocapture %[[BOX:.*]]){{.*}}{
 // CHECK:    %[[VAL_0:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[BOX]], i32 0, i32 0
 // CHECK:    ret ptr %[[VAL_0]]
 
@@ -34,6 +34,6 @@ func.func @array_tdesc(%array : !fir.ref<!fir.class<!fir.ptr<!fir.array<?x!fir.t
   return %tdesc : !fir.llvm_ptr<!fir.tdesc<!fir.type<t>>>
 }
 // CHECK-LABEL: define ptr @array_tdesc(
-// CHECK-SAME: ptr %[[BOX:.*]]){{.*}}{
+// CHECK-SAME: ptr nocapture %[[BOX:.*]]){{.*}}{
 // CHECK:    %[[VAL_0:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[BOX]], i32 0, i32 8
 // CHECK:    ret ptr %[[VAL_0]]
diff --git a/flang/test/Fir/box.fir b/flang/test/Fir/box.fir
index fd9fa1f..841e10d 100644
--- a/flang/test/Fir/box.fir
+++ b/flang/test/Fir/box.fir
@@ -24,7 +24,7 @@ func.func private @g(%b : !fir.box<f32>)
 func.func private @ga(%b : !fir.box<!fir.array<?xf32>>)
 
 // CHECK-LABEL: define void @f
-// CHECK: (ptr %[[ARG:.*]])
+// CHECK: (ptr nocapture %[[ARG:.*]])
 func.func @f(%a : !fir.ref<f32>) {
   // CHECK: %[[DESC:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8 }
   // CHECK: %[[INS0:.*]] = insertvalue {{.*}} { ptr undef, i64 ptrtoint (ptr getelementptr (float, ptr null, i32 1) to i64), i32 20240719, i8 0, i8 27, i8 0, i8 0 }, ptr %[[ARG]], 0
@@ -38,7 +38,7 @@ func.func @f(%a : !fir.ref<f32>) {
 }
 
 // CHECK-LABEL: define void @fa
-// CHECK: (ptr %[[ARG:.*]])
+// CHECK: (ptr nocapture %[[ARG:.*]])
 func.func @fa(%a : !fir.ref<!fir.array<100xf32>>) {
   %c = fir.convert %a : (!fir.ref<!fir.array<100xf32>>) -> !fir.ref<!fir.array<?xf32>>
   %c1 = arith.constant 1 : index
@@ -54,7 +54,7 @@ func.func @fa(%a : !fir.ref<!fir.array<100xf32>>) {
 
 // Boxing of a scalar character of dynamic length
 // CHECK-LABEL: define void @b1(
-// CHECK-SAME: ptr %[[res:.*]], ptr %[[arg0:.*]], i64 %[[arg1:.*]])
+// CHECK-SAME: ptr nocapture %[[res:.*]], ptr nocapture %[[arg0:.*]], i64 %[[arg1:.*]])
 func.func @b1(%arg0 : !fir.ref<!fir.char<1,?>>, %arg1 : index) -> !fir.box<!fir.char<1,?>> {
   // CHECK: %[[alloca:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8 }
   // CHECK: %[[size:.*]] = mul i64 ptrtoint (ptr getelementptr (i8, ptr null, i32 1) to i64), %[[arg1]]
@@ -69,8 +69,8 @@ func.func @b1(%arg0 : !fir.ref<!fir.char<1,?>>, %arg1 : index) -> !fir.box<!fir.
 
 // Boxing of a dynamic array of character with static length (5)
 // CHECK-LABEL: define void @b2(
-// CHECK-SAME: ptr %[[res]],
-// CHECK-SAME: ptr %[[arg0:.*]], i64 %[[arg1:.*]])
+// CHECK-SAME: ptr nocapture %[[res]],
+// CHECK-SAME: ptr nocapture %[[arg0:.*]], i64 %[[arg1:.*]])
 func.func @b2(%arg0 : !fir.ref<!fir.array<?x!fir.char<1,5>>>, %arg1 : index) -> !fir.box<!fir.array<?x!fir.char<1,5>>> {
   %1 = fir.shape %arg1 : (index) -> !fir.shape<1>
   // CHECK: %[[alloca:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }
@@ -85,7 +85,7 @@ func.func @b2(%arg0 : !fir.ref<!fir.array<?x!fir.char<1,5>>>, %arg1 : index) ->
 
 // Boxing of a dynamic array of character of dynamic length
 // CHECK-LABEL: define void @b3(
-// CHECK-SAME: ptr %[[res:.*]], ptr %[[arg0:.*]], i64 %[[arg1:.*]], i64 %[[arg2:.*]])
+// CHECK-SAME: ptr nocapture %[[res:.*]], ptr nocapture %[[arg0:.*]], i64 %[[arg1:.*]], i64 %[[arg2:.*]])
 func.func @b3(%arg0 : !fir.ref<!fir.array<?x!fir.char<1,?>>>, %arg1 : index, %arg2 : index) -> !fir.box<!fir.array<?x!fir.char<1,?>>> {
   %1 = fir.shape %arg2 : (index) -> !fir.shape<1>
   // CHECK: %[[alloca:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }
@@ -103,7 +103,7 @@ func.func @b3(%arg0 : !fir.ref<!fir.array<?x!fir.char<1,?>>>, %arg1 : index, %ar
 
 // Boxing of a static array of character of dynamic length
 // CHECK-LABEL: define void @b4(
-// CHECK-SAME: ptr %[[res:.*]], ptr %[[arg0:.*]], i64 %[[arg1:.*]])
+// CHECK-SAME: ptr nocapture %[[res:.*]], ptr nocapture %[[arg0:.*]], i64 %[[arg1:.*]])
 func.func @b4(%arg0 : !fir.ref<!fir.array<7x!fir.char<1,?>>>, %arg1 : index) -> !fir.box<!fir.array<7x!fir.char<1,?>>> {
   %c_7 = arith.constant 7 : index
   %1 = fir.shape %c_7 : (index) -> !fir.shape<1>
@@ -122,7 +122,7 @@ func.func @b4(%arg0 : !fir.ref<!fir.array<7x!fir.char<1,?>>>, %arg1 : index) ->
 
 // Storing a fir.box into a fir.ref<fir.box> (modifying descriptors).
 // CHECK-LABEL: define void @b5(
-// CHECK-SAME: ptr %[[arg0:.*]], ptr %[[arg1:.*]])
+// CHECK-SAME: ptr nocapture %[[arg0:.*]], ptr %[[arg1:.*]])
 func.func @b5(%arg0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?x?xf32>>>>, %arg1 : !fir.box<!fir.heap<!fir.array<?x?xf32>>>) {
   fir.store %arg1 to %arg0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?x?xf32>>>>
   // CHECK: call void @llvm.memcpy.p0.p0.i32(ptr %0, ptr %1, i32 72, i1 false)
@@ -132,7 +132,7 @@ func.func @b5(%arg0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?x?xf32>>>>, %arg1
 func.func private @callee6(!fir.box<none>) -> i32
 
 // CHECK-LABEL: define i32 @box6(
-// CHECK-SAME: ptr %[[ARG0:.*]], i64 %[[ARG1:.*]], i64 %[[ARG2:.*]])
+// CHECK-SAME: ptr nocapture %[[ARG0:.*]], i64 %[[ARG1:.*]], i64 %[[ARG2:.*]])
 func.func @box6(%0 : !fir.ref<!fir.array<?x?x?x?xf32>>, %1 : index, %2 : index) -> i32 {
   %c100 = arith.constant 100 : index
   %c50 = arith.constant 50 : index
diff --git a/flang/test/Fir/boxproc.fir b/flang/test/Fir/boxproc.fir
index 9e4ea0b..27d8953 100644
--- a/flang/test/Fir/boxproc.fir
+++ b/flang/test/Fir/boxproc.fir
@@ -12,7 +12,7 @@
 // CHECK:         call void @_QPtest_proc_dummy_other(ptr %[[VAL_6]])
 
 // CHECK-LABEL: define void @_QFtest_proc_dummyPtest_proc_dummy_a(ptr
-// CHECK-SAME:              %[[VAL_0:.*]], ptr nest %[[VAL_1:.*]])
+// CHECK-SAME:              nocapture %[[VAL_0:.*]], ptr nest nocapture %[[VAL_1:.*]])
 
 // CHECK-LABEL: define void @_QPtest_proc_dummy_other(ptr
 // CHECK-SAME:              %[[VAL_0:.*]])
@@ -86,7 +86,7 @@ func.func @_QPtest_proc_dummy_other(%arg0: !fir.boxproc<() -> ()>) {
 // CHECK:         call void @llvm.stackrestore.p0(ptr %[[VAL_27]])
 
 // CHECK-LABEL: define { ptr, i64 } @_QFtest_proc_dummy_charPgen_message(ptr
-// CHECK-SAME:                %[[VAL_0:.*]], i64 %[[VAL_1:.*]], ptr nest %[[VAL_2:.*]])
+// CHECK-SAME:                nocapture %[[VAL_0:.*]], i64 %[[VAL_1:.*]], ptr nest nocapture %[[VAL_2:.*]])
 // CHECK:         %[[VAL_3:.*]] = getelementptr { { ptr, i64 } }, ptr %[[VAL_2]], i32 0, i32 0
 // CHECK:         %[[VAL_4:.*]] = load { ptr, i64 }, ptr %[[VAL_3]], align 8
 // CHECK:         %[[VAL_5:.*]] = extractvalue { ptr, i64 } %[[VAL_4]], 0
diff --git a/flang/test/Fir/commute.fir b/flang/test/Fir/commute.fir
index be25fd6..7533816 100644
--- a/flang/test/Fir/commute.fir
+++ b/flang/test/Fir/commute.fir
@@ -11,7 +11,7 @@ func.func @f1(%a : i32, %b : i32) -> i32 {
   return %3 : i32
 }
 
-// CHECK-LABEL: define i32 @f2(ptr %0)
+// CHECK-LABEL: define i32 @f2(ptr nocapture %0)
 func.func @f2(%a : !fir.ref<i32>) -> i32 {
   %1 = fir.load %a : !fir.ref<i32>
   // CHECK: %[[r2:.*]] = load
diff --git a/flang/test/Fir/coordinateof.fir b/flang/test/Fir/coordinateof.fir
index acb9fd5..f96f5b48 100644
--- a/flang/test/Fir/coordinateof.fir
+++ b/flang/test/Fir/coordinateof.fir
@@ -62,7 +62,7 @@ func.func @foo5(%box : !fir.box<!fir.ptr<!fir.array<?xi32>>>, %i : index) -> i32
 }
 
 // CHECK-LABEL: @foo6
-// CHECK-SAME: (ptr %[[box:.*]], i64 %{{.*}}, ptr %{{.*}}) 
+// CHECK-SAME: (ptr %[[box:.*]], i64 %{{.*}}, ptr nocapture %{{.*}}) 
 func.func @foo6(%box : !fir.box<!fir.ptr<!fir.array<?x!fir.char<1>>>>, %i : i64 , %res : !fir.ref<!fir.char<1>>) {
   // CHECK: %[[addr_gep:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }, ptr %[[box]], i32 0, i32 0
   // CHECK: %[[addr:.*]] = load ptr, ptr %[[addr_gep]]
diff --git a/flang/test/Fir/embox.fir b/flang/test/Fir/embox.fir
index cd13c5c..b21e134 100644
--- a/flang/test/Fir/embox.fir
+++ b/flang/test/Fir/embox.fir
@@ -64,7 +64,7 @@ func.func @_QPtest_dt_slice() {
 func.func private @takesRank2CharBox(!fir.box<!fir.array<?x?x!fir.char<1,?>>>)
 
 // CHECK-LABEL: define void @emboxSubstring(
-// CHECK-SAME: ptr %[[arg0:.*]])
+// CHECK-SAME: ptr nocapture %[[arg0:.*]])
 func.func @emboxSubstring(%arg0: !fir.ref<!fir.array<2x3x!fir.char<1,4>>>) {
   %c2 = arith.constant 2 : index
   %c3 = arith.constant 3 : index
@@ -85,7 +85,7 @@ func.func @emboxSubstring(%arg0: !fir.ref<!fir.array<2x3x!fir.char<1,4>>>) {
 
 func.func private @do_something(!fir.box<!fir.array<?xf32>>) -> ()
 // CHECK: define void @fir_dev_issue_1416
-// CHECK-SAME: ptr %[[base_addr:.*]], i64 %[[low:.*]], i64 %[[up:.*]], i64 %[[at:.*]])
+// CHECK-SAME: ptr nocapture %[[base_addr:.*]], i64 %[[low:.*]], i64 %[[up:.*]], i64 %[[at:.*]])
 func.func @fir_dev_issue_1416(%arg0: !fir.ref<!fir.array<40x?xf32>>, %low: index, %up: index, %at : index) {
     // Test fir.embox with a constant interior array shape.
     %c1 = arith.constant 1 : index
diff --git a/flang/test/Fir/field-index.fir b/flang/test/Fir/field-index.fir
index 8c9391f..0865375 100644
--- a/flang/test/Fir/field-index.fir
+++ b/flang/test/Fir/field-index.fir
@@ -7,7 +7,7 @@
 // CHECK-DAG: %[[c:.*]] = type { float, %[[b]] }
 
 // CHECK-LABEL: @simple_field
-// CHECK-SAME: (ptr %[[arg0:.*]])
+// CHECK-SAME: (ptr nocapture %[[arg0:.*]])
 func.func @simple_field(%arg0: !fir.ref<!fir.type<a{x:f32,i:i32}>>) -> i32 {
   %1 = fir.field_index i, !fir.type<a{x:f32,i:i32}>
   // CHECK: %[[GEP:.*]] = getelementptr %a, ptr %[[arg0]], i32 0, i32 1
@@ -18,7 +18,7 @@ func.func @simple_field(%arg0: !fir.ref<!fir.type<a{x:f32,i:i32}>>) -> i32 {
 }
 
 // CHECK-LABEL: @derived_field
-// CHECK-SAME: (ptr %[[arg0:.*]])
+// CHECK-SAME: (ptr nocapture %[[arg0:.*]])
 func.func @derived_field(%arg0: !fir.ref<!fir.type<c{x:f32,some_b:!fir.type<b{x:f32,i:i32}>}>>) -> i32 {
   %1 = fir.field_index some_b, !fir.type<c{x:f32,some_b:!fir.type<b{x:f32,i:i32}>}>
   %2 = fir.field_index i, !fir.type<b{x:f32,i:i32}>
diff --git a/flang/test/Fir/ignore-missing-type-descriptor.fir b/flang/test/Fir/ignore-missing-type-descriptor.fir
index 228d9a1c..009e110 100644
--- a/flang/test/Fir/ignore-missing-type-descriptor.fir
+++ b/flang/test/Fir/ignore-missing-type-descriptor.fir
@@ -15,7 +15,7 @@ func.func @test_embox(%addr: !fir.ref<!some_freestyle_type>) {
   return
 }
 // CHECK-LABEL: define void @test_embox(
-// CHECK-SAME: ptr %[[ADDR:.*]])
+// CHECK-SAME: ptr nocapture %[[ADDR:.*]])
 // CHECK: insertvalue { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK-SAME: { ptr undef, i64 ptrtoint (ptr getelementptr (%some_not_mangled_type, ptr null, i32 1) to i64),
 // CHECK-SAME: i32 20240719, i8 0, i8 42, i8 0, i8 1, ptr null, [1 x i64] zeroinitializer },
diff --git a/flang/test/Fir/polymorphic.fir b/flang/test/Fir/polymorphic.fir
index 78e5b8d..74b29ed 100644
--- a/flang/test/Fir/polymorphic.fir
+++ b/flang/test/Fir/polymorphic.fir
@@ -175,7 +175,7 @@ func.func @_QMmod2Pinitp(%arg0: !fir.ref<!fir.class<!fir.ptr<none>>> {fir.bindc_
 func.func private @_FortranAPointerAssociate(!fir.ref<!fir.box<none>>, !fir.box<none>) -> none attributes {fir.runtime}
 
 // CHECK-LABEL: define void @_QMmod2Pinitp(
-// CHECK-SAME: ptr %[[ARG0:.*]]){{.*}}{
+// CHECK-SAME: ptr nocapture %[[ARG0:.*]]){{.*}}{
 // CHECK: %[[ALLOCA_CLASS_NONE:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, ptr, [1 x i64] }
 // CHECK: call void @llvm.memcpy.p0.p0.i32(ptr %[[ALLOCA_CLASS_NONE]], ptr %[[ARG0]], i32 40, i1 false)
 // CHECK: %{{.*}} = call {} @_FortranAPointerAssociate(ptr @_QMmod2Ep, ptr %[[ALLOCA_CLASS_NONE]])
diff --git a/flang/test/Fir/struct-passing-x86-64-byval.fir b/flang/test/Fir/struct-passing-x86-64-byval.fir
index b686901..44256c0 100644
--- a/flang/test/Fir/struct-passing-x86-64-byval.fir
+++ b/flang/test/Fir/struct-passing-x86-64-byval.fir
@@ -81,27 +81,27 @@ func.func @not_enough_int_reg_3(%arg0: i32, %arg1: i32, %arg2: i32, %arg3: i32,
 }
 }
 
-// CHECK: define void @takes_toobig(ptr byval(%toobig) align 8 %{{.*}}) {
-// CHECK: define void @takes_toobig_align16(ptr byval(%toobig_align16) align 16 %{{.*}}) {
-// CHECK: define void @not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%fits_in_1_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_int_reg_1b(ptr %{{.*}}, ptr %{{.*}}, ptr %{{.*}}, ptr %{{.*}}, ptr %{{.*}}, ptr %{{.*}}, ptr byval(%fits_in_1_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_int_reg_2(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%fits_in_2_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @ftakes_toobig(ptr byval(%ftoobig) align 8 %{{.*}}) {
-// CHECK: define void @ftakes_toobig_align16(ptr byval(%ftoobig_align16) align 16 %{{.*}}) {
-// CHECK: define void @not_enough_sse_reg_1(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_sse_reg_1b(<2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, ptr byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_sse_reg_1c(double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, ptr byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_sse_reg_2(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr byval(%fits_in_2_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @test_contains_x87(ptr byval(%contains_x87) align 16 %{{.*}}) {
-// CHECK: define void @test_contains_complex_x87(ptr byval(%contains_complex_x87) align 16 %{{.*}}) {
-// CHECK: define void @test_nested_toobig(ptr byval(%nested_toobig) align 8 %{{.*}}) {
-// CHECK: define void @test_badly_aligned(ptr byval(%badly_aligned) align 8 %{{.*}}) {
-// CHECK: define void @test_logical_toobig(ptr byval(%logical_too_big) align 8 %{{.*}}) {
-// CHECK: define void @l_not_enough_int_reg(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%l_fits_in_2_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @test_complex_toobig(ptr byval(%complex_too_big) align 8 %{{.*}}) {
-// CHECK: define void @cplx_not_enough_sse_reg_1(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr byval(%cplx_fits_in_1_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @test_char_to_big(ptr byval(%char_too_big) align 8 %{{.*}}) {
-// CHECK: define void @char_not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%char_fits_in_1_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @mix_not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%mix_in_1_int_reg) align 8 %{{.*}}) {
-// CHECK: define void @mix_not_enough_sse_reg_2(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr byval(%mix_in_1_int_reg_1_sse_reg) align 8 %{{.*}}) {
-// CHECK: define void @not_enough_int_reg_3(ptr sret({ fp128, fp128 }) align 16 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr byval(%fits_in_1_int_reg) align 8 %{{.*}})
+// CHECK: define void @takes_toobig(ptr nocapture byval(%toobig) align 8 %{{.*}}) {
+// CHECK: define void @takes_toobig_align16(ptr nocapture byval(%toobig_align16) align 16 %{{.*}}) {
+// CHECK: define void @not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%fits_in_1_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_int_reg_1b(ptr nocapture %{{.*}}, ptr nocapture %{{.*}}, ptr nocapture %{{.*}}, ptr nocapture %{{.*}}, ptr nocapture %{{.*}}, ptr nocapture %{{.*}}, ptr nocapture byval(%fits_in_1_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_int_reg_2(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%fits_in_2_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @ftakes_toobig(ptr nocapture byval(%ftoobig) align 8 %{{.*}}) {
+// CHECK: define void @ftakes_toobig_align16(ptr nocapture byval(%ftoobig_align16) align 16 %{{.*}}) {
+// CHECK: define void @not_enough_sse_reg_1(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr nocapture byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_sse_reg_1b(<2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, <2 x float> %{{.*}}, ptr nocapture byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_sse_reg_1c(double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, double %{{.*}}, ptr nocapture byval(%fits_in_1_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_sse_reg_2(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr nocapture byval(%fits_in_2_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @test_contains_x87(ptr nocapture byval(%contains_x87) align 16 %{{.*}}) {
+// CHECK: define void @test_contains_complex_x87(ptr nocapture byval(%contains_complex_x87) align 16 %{{.*}}) {
+// CHECK: define void @test_nested_toobig(ptr nocapture byval(%nested_toobig) align 8 %{{.*}}) {
+// CHECK: define void @test_badly_aligned(ptr nocapture byval(%badly_aligned) align 8 %{{.*}}) {
+// CHECK: define void @test_logical_toobig(ptr nocapture byval(%logical_too_big) align 8 %{{.*}}) {
+// CHECK: define void @l_not_enough_int_reg(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%l_fits_in_2_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @test_complex_toobig(ptr nocapture byval(%complex_too_big) align 8 %{{.*}}) {
+// CHECK: define void @cplx_not_enough_sse_reg_1(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr nocapture byval(%cplx_fits_in_1_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @test_char_to_big(ptr nocapture byval(%char_too_big) align 8 %{{.*}}) {
+// CHECK: define void @char_not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%char_fits_in_1_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @mix_not_enough_int_reg_1(i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%mix_in_1_int_reg) align 8 %{{.*}}) {
+// CHECK: define void @mix_not_enough_sse_reg_2(float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, float %{{.*}}, ptr nocapture byval(%mix_in_1_int_reg_1_sse_reg) align 8 %{{.*}}) {
+// CHECK: define void @not_enough_int_reg_3(ptr nocapture sret({ fp128, fp128 }) align 16 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}}, ptr nocapture byval(%fits_in_1_int_reg) align 8 %{{.*}})
diff --git a/flang/test/Fir/target-rewrite-complex-10-x86.fir b/flang/test/Fir/target-rewrite-complex-10-x86.fir
index 404f5f9..651d1e7 100644
--- a/flang/test/Fir/target-rewrite-complex-10-x86.fir
+++ b/flang/test/Fir/target-rewrite-complex-10-x86.fir
@@ -29,4 +29,4 @@ func.func @takecomplex10(%z: complex<f80>) {
 // AMD64:    %[[VAL_3:.*]] = fir.alloca complex<f80>
 // AMD64:    fir.store %[[VAL_2]] to %[[VAL_3]] : !fir.ref<complex<f80>>
 
-// AMD64_LLVM: define void @takecomplex10(ptr byval({ x86_fp80, x86_fp80 }) align 16 %0)
+// AMD64_LLVM: define void @takecomplex10(ptr nocapture byval({ x86_fp80, x86_fp80 }) align 16 %0)
diff --git a/flang/test/Fir/target.fir b/flang/test/Fir/target.fir
index 788deeb..478d681 100644
--- a/flang/test/Fir/target.fir
+++ b/flang/test/Fir/target.fir
@@ -26,7 +26,7 @@ func.func @gen4() -> complex<f32> {
   return %6 : complex<f32>
 }
 
-// I32-LABEL: define void @gen8(ptr sret({ double, double }) align 4 %
+// I32-LABEL: define void @gen8(ptr nocapture sret({ double, double }) align 4 %
 // X64-LABEL: define { double, double } @gen8()
 // AARCH64-LABEL: define { double, double } @gen8()
 // PPC-LABEL: define { double, double } @gen8()
@@ -93,9 +93,9 @@ func.func @call8() {
   return
 }
 
-// I32-LABEL: define i64 @char1lensum(ptr %0, ptr %1, i32 %2, i32 %3)
-// X64-LABEL: define i64 @char1lensum(ptr %0, ptr %1, i64 %2, i64 %3)
-// PPC-LABEL: define i64 @char1lensum(ptr %0, ptr %1, i64 %2, i64 %3)
+// I32-LABEL: define i64 @char1lensum(ptr nocapture %0, ptr nocapture %1, i32 %2, i32 %3)
+// X64-LABEL: define i64 @char1lensum(ptr nocapture %0, ptr nocapture %1, i64 %2, i64 %3)
+// PPC-LABEL: define i64 @char1lensum(ptr nocapture %0, ptr nocapture %1, i64 %2, i64 %3)
 func.func @char1lensum(%arg0 : !fir.boxchar<1>, %arg1 : !fir.boxchar<1>) -> i64 {
   // X64-DAG: %[[p0:.*]] = insertvalue { ptr, i64 } undef, ptr %1, 0
   // X64-DAG: = insertvalue { ptr, i64 } %[[p0]], i64 %3, 1
@@ -111,9 +111,9 @@ func.func @char1lensum(%arg0 : !fir.boxchar<1>, %arg1 : !fir.boxchar<1>) -> i64
   return %3 : i64
 }
 
-// I32-LABEL: define void @char1copy(ptr sret(i8) %0, i32 %1, ptr %2, i32 %3)
-// I64-LABEL: define void @char1copy(ptr sret(i8) %0, i64 %1, ptr %2, i64 %3)
-// PPC-LABEL: define void @char1copy(ptr sret(i8) %0, i64 %1, ptr %2, i64 %3)
+// I32-LABEL: define void @char1copy(ptr nocapture sret(i8) %0, i32 %1, ptr nocapture %2, i32 %3)
+// I64-LABEL: define void @char1copy(ptr nocapture sret(i8) %0, i64 %1, ptr nocapture %2, i64 %3)
+// PPC-LABEL: define void @char1copy(ptr nocapture sret(i8) %0, i64 %1, ptr nocapture %2, i64 %3)
 func.func @char1copy(%arg0 : !fir.boxchar<1> {llvm.sret = !fir.char<1, ?>}, %arg1 : !fir.boxchar<1>) {
   // I32-DAG: %[[p0:.*]] = insertvalue { ptr, i32 } undef, ptr %2, 0
   // I32-DAG: = insertvalue { ptr, i32 } %[[p0]], i32 %3, 1
diff --git a/flang/test/Integration/OpenMP/copyprivate.f90 b/flang/test/Integration/OpenMP/copyprivate.f90
index d32319a..47e932a 100644
--- a/flang/test/Integration/OpenMP/copyprivate.f90
+++ b/flang/test/Integration/OpenMP/copyprivate.f90
@@ -8,25 +8,25 @@
 
 !RUN: %flang_fc1 -emit-llvm -fopenmp %s -o - | FileCheck %s
 
-!CHECK-DAG: define void @_copy_box_Uxi32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_10xi32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_i64(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_box_Uxi64(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_f32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_2x3xf32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_z32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_10xz32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_l32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_5xl32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_c8x8(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_10xc8x8(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_c16x5(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_rec__QFtest_typesTdt(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_box_heap_Uxi32(ptr %{{.*}}, ptr %{{.*}})
-!CHECK-DAG: define void @_copy_box_ptr_Uxc8x9(ptr %{{.*}}, ptr %{{.*}})
+!CHECK-DAG: define void @_copy_box_Uxi32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_10xi32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_i64(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_box_Uxi64(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_f32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_2x3xf32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_z32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_10xz32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_l32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_5xl32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_c8x8(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_10xc8x8(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_c16x5(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_rec__QFtest_typesTdt(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_box_heap_Uxi32(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
+!CHECK-DAG: define void @_copy_box_ptr_Uxc8x9(ptr nocapture %{{.*}}, ptr nocapture %{{.*}})
 
 !CHECK-LABEL: define void @_copy_i32(
-!CHECK-SAME:                         ptr %[[DST:.*]], ptr %[[SRC:.*]]){{.*}} {
+!CHECK-SAME:                         ptr nocapture %[[DST:.*]], ptr nocapture %[[SRC:.*]]){{.*}} {
 !CHECK-NEXT:    %[[SRC_VAL:.*]] = load i32, ptr %[[SRC]]
 !CHECK-NEXT:    store i32 %[[SRC_VAL]], ptr %[[DST]]
 !CHECK-NEXT:    ret void
diff --git a/flang/test/Integration/debug-local-var-2.f90 b/flang/test/Integration/debug-local-var-2.f90
index 525474a..5a675cb 100644
--- a/flang/test/Integration/debug-local-var-2.f90
+++ b/flang/test/Integration/debug-local-var-2.f90
@@ -27,7 +27,7 @@
 ! BOTH-LABEL: }
 
 ! BOTH-LABEL: define {{.*}}i64 @_QFPfn1
-! BOTH-SAME: (ptr %[[ARG1:.*]], ptr %[[ARG2:.*]], ptr %[[ARG3:.*]])
+! BOTH-SAME: (ptr nocapture %[[ARG1:.*]], ptr nocapture %[[ARG2:.*]], ptr nocapture %[[ARG3:.*]])
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[ARG1]], metadata ![[A1:.*]], metadata !DIExpression())
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[ARG2]], metadata ![[B1:.*]], metadata !DIExpression())
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[ARG3]], metadata ![[C1:.*]], metadata !DIExpression())
@@ -40,7 +40,7 @@
 ! BOTH-LABEL: }
 
 ! BOTH-LABEL: define {{.*}}i32 @_QFPfn2
-! BOTH-SAME: (ptr %[[FN2ARG1:.*]], ptr %[[FN2ARG2:.*]], ptr %[[FN2ARG3:.*]])
+! BOTH-SAME: (ptr nocapture %[[FN2ARG1:.*]], ptr nocapture %[[FN2ARG2:.*]], ptr nocapture %[[FN2ARG3:.*]])
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[FN2ARG1]], metadata ![[A2:.*]], metadata !DIExpression())
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[FN2ARG2]], metadata ![[B2:.*]], metadata !DIExpression())
 ! INTRINSICS-DAG: call void @llvm.dbg.declare(metadata ptr %[[FN2ARG3]], metadata ![[C2:.*]], metadata !DIExpression())
diff --git a/flang/test/Transforms/constant-argument-globalisation.fir b/flang/test/Transforms/constant-argument-globalisation.fir
index 553c3c6..5656de0 100644
--- a/flang/test/Transforms/constant-argument-globalisation.fir
+++ b/flang/test/Transforms/constant-argument-globalisation.fir
@@ -49,8 +49,8 @@ module {
 // DISABLE-LABEL: ; ModuleID =
 // DISABLE-NOT: @_extruded
 // DISABLE:  define void @sub1(
-// DISABLE-SAME: ptr [[ARG0:%.*]],
-// DISABLE-SAME: ptr [[ARG1:%.*]])
+// DISABLE-SAME: ptr nocapture [[ARG0:%.*]],
+// DISABLE-SAME: ptr nocapture [[ARG1:%.*]])
 // DISABLE-SAME: {
 // DISABLE: [[CONST_R0:%.*]] = alloca double
 // DISABLE: [[CONST_R1:%.*]] = alloca double
diff --git a/flang/test/Transforms/function-attrs.fir b/flang/test/Transforms/function-attrs.fir
new file mode 100644
index 0000000..5f871a1
--- /dev/null
+++ b/flang/test/Transforms/function-attrs.fir
@@ -0,0 +1,45 @@
+// RUN: fir-opt --function-attr %s | FileCheck %s
+
+// If a function has a body and is not bind(c), and if the dummy argument doesn't have the target,
+// asynchronous, volatile, or pointer attribute, then add llvm.nocapture to the dummy argument.
+
+func.func @_QParg_nocapture(%arg0: !fir.ref<i32> {fir.bindc_name = "tar", fir.target}, %arg1: !fir.ref<i32> {fir.asynchronous, fir.bindc_name = "asynch"}, %arg2: !fir.ref<i32> {fir.bindc_name = "vol", fir.volatile}, %arg3: !fir.ref<!fir.box<!fir.ptr<i32>>> {fir.bindc_name = "ptr"}, %arg4: !fir.ref<i32> {fir.bindc_name = "nocap"}) {
+    %0 = fir.dummy_scope : !fir.dscope
+    %1 = fir.declare %arg0 dummy_scope %0 {fortran_attrs = #fir.var_attrs<target>, uniq_name = "_QFarg_nocaptureEtar"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    %2 = fir.declare %arg1 dummy_scope %0 {fortran_attrs = #fir.var_attrs<asynchronous>, uniq_name = "_QFarg_nocaptureEasynch"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    %3 = fir.declare %arg2 dummy_scope %0 {uniq_name = "_QFarg_nocaptureEvol"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    %4 = fir.declare %arg3 dummy_scope %0 {fortran_attrs = #fir.var_attrs<pointer>, uniq_name = "_QFarg_nocaptureEptr"} : (!fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.dscope) -> !fir.ref<!fir.box<!fir.ptr<i32>>>
+    %5 = fir.declare %arg4 dummy_scope %0 {uniq_name = "_QFarg_nocaptureEnocap"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    return
+}
+// CHECK-LABEL: func.func @_QParg_nocapture(
+// CHECK-SAME:                                 %[[ARG0:.*]]: !fir.ref<i32> {fir.bindc_name = "tar", fir.target},
+// CHECK-SAME:                                 %[[ARG1:.*]]: !fir.ref<i32> {fir.asynchronous, fir.bindc_name = "asynch"},
+// CHECK-SAME:                                 %[[ARG2:.*]]: !fir.ref<i32> {fir.bindc_name = "vol", fir.volatile},
+// CHECK-SAME:                                 %[[ARG3:.*]]: !fir.ref<!fir.box<!fir.ptr<i32>>> {fir.bindc_name = "ptr", llvm.nocapture},
+// CHECK-SAME:                                 %[[ARG4:.*]]: !fir.ref<i32> {fir.bindc_name = "nocap", llvm.nocapture}) {
+// CHECK:    return
+// CHECK-NEXT: }
+
+func.func @arg_nocapture_bindc(%arg0: !fir.ref<i32> {fir.bindc_name = "tar", fir.target}, %arg1: !fir.ref<i32> {fir.bindc_name = "nocap"}) attributes {fir.bindc_name = "arg_nocapture_bindc", fir.proc_attrs = #fir.proc_attrs<bind_c>} {
+    %0 = fir.dummy_scope : !fir.dscope
+    %1 = fir.declare %arg0 dummy_scope %0 {fortran_attrs = #fir.var_attrs<target>, uniq_name = "_QFarg_nocapture_bindcEtar"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    %2 = fir.declare %arg1 dummy_scope %0 {uniq_name = "_QFarg_nocapture_bindcEnocap"} : (!fir.ref<i32>, !fir.dscope) -> !fir.ref<i32>
+    return
+}
+// CHECK-LABEL: func.func @arg_nocapture_bindc(
+// CHECK-NOT:  llvm.nocapture
+
+
+// If a function declaration is from a module and is not bind(c), and if the dummy argument doesn't have
+// the target, asynchronous, volatile, or pointer attribute, then add llvm.nocapture to the dummy argument.
+
+func.func private @_QMarg_modPcheck_args(!fir.ref<i32> {fir.target}, !fir.ref<i32> {fir.asynchronous}, !fir.ref<i32> {fir.volatile}, !fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.ref<i32>, !fir.boxchar<1>, !fir.ref<complex<f32>>)
+// CHECK-LABEL: func.func private @_QMarg_modPcheck_args(
+// CHECK-SAME:                                 !fir.ref<i32> {fir.target},
+// CHECK-SAME:                                 !fir.ref<i32> {fir.asynchronous},
+// CHECK-SAME:                                 !fir.ref<i32> {fir.volatile},
+// CHECK-SAME:                                 !fir.ref<!fir.box<!fir.ptr<i32>>> {llvm.nocapture},
+// CHECK-SAME:                                 !fir.ref<i32> {llvm.nocapture},
+// CHECK-SAME:                                 !fir.boxchar<1>,
+// CHECK-SAME:                                 !fir.ref<complex<f32>> {llvm.nocapture})