[clang] [Clang] Fix sema checks thinking kernels aren't kernels (PR #104460)

[Joseph Huber via cfe-commits]

https://github.com/jhuber6 updated https://github.com/llvm/llvm-project/pull/104460

>From 84c89feaea8135f7dfaba488b442818974b51c9d Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Thu, 15 Aug 2024 10:34:17 -0500
Subject: [PATCH 1/2] [Clang] Fix sema checks thinking kernels aren't kernels

Summary:
Currently we have some sema checks to make sure users don't apply
kernel-only attributes to non-kernel functions. However, this currently
did not correctly check for bare NVPTX / AMDGPU kernel attributes,
making it impossible to use them at all w/o CUDA enabled. This patch
fixes that by checking for the calling convention / attributes directly.
---
 clang/lib/Sema/SemaDeclAttr.cpp                          | 7 +++++--
 clang/test/CodeGenCXX/amdgpu-kernel-arg-pointer-type.cpp | 5 +++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
index 3b5e984f4ee773..96c3759de7edc1 100644
--- a/clang/lib/Sema/SemaDeclAttr.cpp
+++ b/clang/lib/Sema/SemaDeclAttr.cpp
@@ -7147,7 +7147,9 @@ void Sema::ProcessDeclAttributeList(
   // good to have a way to specify "these attributes must appear as a group",
   // for these. Additionally, it would be good to have a way to specify "these
   // attribute must never appear as a group" for attributes like cold and hot.
-  if (!D->hasAttr<OpenCLKernelAttr>()) {
+  const FunctionType *FnTy = D->getFunctionType();
+  if (!D->hasAttr<OpenCLKernelAttr>() && FnTy &&
+      FnTy->getCallConv() != CallingConv::CC_AMDGPUKernelCall) {
     // These attributes cannot be applied to a non-kernel function.
     if (const auto *A = D->getAttr<ReqdWorkGroupSizeAttr>()) {
       // FIXME: This emits a different error message than
@@ -7163,7 +7165,8 @@ void Sema::ProcessDeclAttributeList(
     } else if (const auto *A = D->getAttr<OpenCLIntelReqdSubGroupSizeAttr>()) {
       Diag(D->getLocation(), diag::err_opencl_kernel_attr) << A;
       D->setInvalidDecl();
-    } else if (!D->hasAttr<CUDAGlobalAttr>()) {
+    } else if (!D->hasAttr<CUDAGlobalAttr>() &&
+               !D->hasAttr<NVPTXKernelAttr>()) {
       if (const auto *A = D->getAttr<AMDGPUFlatWorkGroupSizeAttr>()) {
         Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
             << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
diff --git a/clang/test/CodeGenCXX/amdgpu-kernel-arg-pointer-type.cpp b/clang/test/CodeGenCXX/amdgpu-kernel-arg-pointer-type.cpp
index c8fb12315d0eec..8df1d75e9ec8fa 100644
--- a/clang/test/CodeGenCXX/amdgpu-kernel-arg-pointer-type.cpp
+++ b/clang/test/CodeGenCXX/amdgpu-kernel-arg-pointer-type.cpp
@@ -6,6 +6,10 @@
 // The original test passes the result through opt O2, but that seems to introduce invalid
 // addrspace casts which are not being fixed as part of the present change.
 
+// COMMON: define{{.*}} amdgpu_kernel void @_Z6kernelv() #[[ATTR:[0-9]+]]
+__attribute__((amdgpu_kernel, amdgpu_flat_work_group_size(1, 256))) void
+    kernel() {}
+
 // COMMON-LABEL: define{{.*}} amdgpu_kernel void @_Z7kernel1Pi(ptr {{.*}} %x)
 // CHECK-NOT: ={{.*}} addrspacecast [[TYPE:.*]] addrspace(1)* %{{.*}} to ptr
 __attribute__((amdgpu_kernel)) void kernel1(int *x) {
@@ -81,3 +85,4 @@ __attribute__((amdgpu_kernel)) void kernel8(struct SS a) {
   *a.x += 3.f;
 }
 
+// COMMON: attributes #[[ATTR]] = { {{.*}}"amdgpu-flat-work-group-size"="1,256"{{.*}} }

>From 6a89582e570f2e2e7c347fedd3bbcf8b5b20eba2 Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn at outlook.com>
Date: Thu, 15 Aug 2024 11:07:49 -0500
Subject: [PATCH 2/2] Address comments

---
 clang/lib/Sema/SemaDeclAttr.cpp | 44 ++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
index 96c3759de7edc1..91464f739f1025 100644
--- a/clang/lib/Sema/SemaDeclAttr.cpp
+++ b/clang/lib/Sema/SemaDeclAttr.cpp
@@ -7147,9 +7147,7 @@ void Sema::ProcessDeclAttributeList(
   // good to have a way to specify "these attributes must appear as a group",
   // for these. Additionally, it would be good to have a way to specify "these
   // attribute must never appear as a group" for attributes like cold and hot.
-  const FunctionType *FnTy = D->getFunctionType();
-  if (!D->hasAttr<OpenCLKernelAttr>() && FnTy &&
-      FnTy->getCallConv() != CallingConv::CC_AMDGPUKernelCall) {
+  if (!D->hasAttr<OpenCLKernelAttr>()) {
     // These attributes cannot be applied to a non-kernel function.
     if (const auto *A = D->getAttr<ReqdWorkGroupSizeAttr>()) {
       // FIXME: This emits a different error message than
@@ -7165,25 +7163,27 @@ void Sema::ProcessDeclAttributeList(
     } else if (const auto *A = D->getAttr<OpenCLIntelReqdSubGroupSizeAttr>()) {
       Diag(D->getLocation(), diag::err_opencl_kernel_attr) << A;
       D->setInvalidDecl();
-    } else if (!D->hasAttr<CUDAGlobalAttr>() &&
-               !D->hasAttr<NVPTXKernelAttr>()) {
-      if (const auto *A = D->getAttr<AMDGPUFlatWorkGroupSizeAttr>()) {
-        Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
-            << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
-        D->setInvalidDecl();
-      } else if (const auto *A = D->getAttr<AMDGPUWavesPerEUAttr>()) {
-        Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
-            << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
-        D->setInvalidDecl();
-      } else if (const auto *A = D->getAttr<AMDGPUNumSGPRAttr>()) {
-        Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
-            << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
-        D->setInvalidDecl();
-      } else if (const auto *A = D->getAttr<AMDGPUNumVGPRAttr>()) {
-        Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
-            << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
-        D->setInvalidDecl();
-      }
+    } 
+  }
+  const FunctionType *FnTy = D->getFunctionType();
+  if (!D->hasAttr<CUDAGlobalAttr>() && !D->hasAttr<OpenCLKernelAttr>() &&
+      FnTy && FnTy->getCallConv() != CallingConv::CC_AMDGPUKernelCall) {
+    if (const auto *A = D->getAttr<AMDGPUFlatWorkGroupSizeAttr>()) {
+      Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
+          << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
+      D->setInvalidDecl();
+    } else if (const auto *A = D->getAttr<AMDGPUWavesPerEUAttr>()) {
+      Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
+          << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
+      D->setInvalidDecl();
+    } else if (const auto *A = D->getAttr<AMDGPUNumSGPRAttr>()) {
+      Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
+          << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
+      D->setInvalidDecl();
+    } else if (const auto *A = D->getAttr<AMDGPUNumVGPRAttr>()) {
+      Diag(D->getLocation(), diag::err_attribute_wrong_decl_type)
+          << A << A->isRegularKeywordAttribute() << ExpectedKernelFunction;
+      D->setInvalidDecl();
     }
   }