[clang][cuda/hip] Allow `__noinline__` lambdas

D124866 seem to have had an unintended side effect: __noinline__ on lambdas was no longer accepted.

This fixes the regression and adds a test case for it.

Reviewed By: aaron.ballman

Differential Revision: https://reviews.llvm.org/D137251

clang/docs/ReleaseNotes.rst

@@ -638,6 +638,9 @@ C++2b Feature Support
 CUDA/HIP Language Changes in Clang
 ----------------------------------
 
+ - Allow the use of ``__noinline__`` as a keyword (instead of ``__attribute__((noinline))``)
+   in lambda declarations.
+
 Objective-C Language Changes in Clang
 -------------------------------------
 

clang/lib/Parse/ParseExprCXX.cpp

@@ -1291,7 +1291,22 @@ ExprResult Parser::ParseLambdaExpressionAfterIntroducer(
   if (getLangOpts().CUDA) {
     // In CUDA code, GNU attributes are allowed to appear immediately after the
     // "[...]", even if there is no "(...)" before the lambda body.
-    MaybeParseGNUAttributes(D);
+    //
+    // Note that we support __noinline__ as a keyword in this mode and thus
+    // it has to be separately handled.
+    while (true) {
+      if (Tok.is(tok::kw___noinline__)) {
+        IdentifierInfo *AttrName = Tok.getIdentifierInfo();
+        SourceLocation AttrNameLoc = ConsumeToken();
+        Attr.addNew(AttrName, AttrNameLoc, nullptr, AttrNameLoc, nullptr, 0,
+                    ParsedAttr::AS_Keyword);
+      } else if (Tok.is(tok::kw___attribute))
+        ParseGNUAttributes(Attr, nullptr, &D);
+      else
+        break;
+    }
+
+    D.takeAttributes(Attr);
   }
 
   // Helper to emit a warning if we see a CUDA host/device/global attribute

clang/test/CodeGenCUDA/lambda-noinline.cu

@@ -0,0 +1,23 @@
+// RUN: %clang_cc1 -no-opaque-pointers -x hip -emit-llvm -std=c++11 %s -o - \
+// RUN:   -triple x86_64-linux-gnu \
+// RUN:   | FileCheck -check-prefix=HOST %s
+// RUN: %clang_cc1 -no-opaque-pointers -x hip -emit-llvm -std=c++11 %s -o - \
+// RUN:   -triple amdgcn-amd-amdhsa -fcuda-is-device \
+// RUN:   | FileCheck -check-prefix=DEV %s
+
+#include "Inputs/cuda.h"
+
+// Checks noinline is correctly added to the lambda function.
+
+// HOST: define{{.*}}@_ZZ4HostvENKUlvE_clEv({{.*}}) #[[ATTR:[0-9]+]]
+// HOST: attributes #[[ATTR]]{{.*}}noinline
+
+// DEV: define{{.*}}@_ZZ6DevicevENKUlvE_clEv({{.*}}) #[[ATTR:[0-9]+]]
+// DEV: attributes #[[ATTR]]{{.*}}noinline
+
+__device__ int a;
+int b;
+
+__device__ int Device() { return ([&] __device__ __noinline__ (){ return a; })(); }
+
+__host__ int Host() { return ([&] __host__ __noinline__ (){ return b; })(); }

clang/test/Parser/lambda-attr.cu

@@ -18,6 +18,10 @@ __attribute__((device)) void device_attr() {
   ([&](int) __attribute__((device)){ device_fn(); })(0);
   // expected-warning@-1 {{nvcc does not allow '__device__' to appear after the parameter list in lambdas}}
   ([&] __attribute__((device)) (int) { device_fn(); })(0);
+
+  // test that noinline can appear anywhere.
+  ([&] __attribute__((device)) __noinline__ () { device_fn(); })();
+  ([&] __noinline__ __attribute__((device)) () { device_fn(); })();
 }
 
 __attribute__((host)) __attribute__((device)) void host_device_attrs() {
@@ -37,6 +41,11 @@ __attribute__((host)) __attribute__((device)) void host_device_attrs() {
   // expected-warning@-1 {{nvcc does not allow '__host__' to appear after the parameter list in lambdas}}
   // expected-warning@-2 {{nvcc does not allow '__device__' to appear after the parameter list in lambdas}}
   ([&] __attribute__((host)) __attribute__((device)) (int) { hd_fn(); })(0);
+
+  // test that noinline can also appear anywhere.
+  ([] __attribute__((host)) __attribute__((device)) () { hd_fn(); })();
+  ([] __attribute__((host)) __noinline__ __attribute__((device)) () { hd_fn(); })();
+  ([] __attribute__((host)) __attribute__((device)) __noinline__ () { hd_fn(); })();
 }
 
 // TODO: Add tests for __attribute__((global)) once we support global lambdas.