[clang] [SYCL] Basic code generation for SYCL kernel caller offload entry point functions. (PR #133030)

[Tom Honermann via cfe-commits]

================
@@ -0,0 +1,186 @@
+// RUN: %clang_cc1 -fsycl-is-host -emit-llvm -triple x86_64-unknown-linux-gnu %s -o - | FileCheck --check-prefixes=CHECK-HOST,CHECK-HOST-LINUX %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple amdgcn-amd-amdhsa %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-AMDGCN %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple nvptx-nvidia-cuda %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-NVPTX %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple nvptx64-nvidia-cuda %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-NVPTX %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple spir-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple spir64-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple spirv32-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-unknown-linux-gnu -triple spirv64-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-host -emit-llvm -triple x86_64-pc-windows-msvc %s -o - | FileCheck --check-prefixes=CHECK-HOST,CHECK-HOST-WINDOWS %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple amdgcn-amd-amdhsa %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-AMDGCN %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple nvptx-nvidia-cuda %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-NVPTX %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple nvptx64-nvidia-cuda %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-NVPTX %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple spir-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple spir64-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple spirv32-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+// RUN: %clang_cc1 -fsycl-is-device -emit-llvm -aux-triple x86_64-pc-windows-msvc -triple spirv64-unknown-unknown %s -o - | FileCheck --check-prefixes=CHECK-DEVICE,CHECK-SPIR %s
+
+// Test the generation of SYCL kernel caller functions. These functions are
+// generated from functions declared with the sycl_kernel_entry_point attribute
+// and emited during device compilation. They are not emitted during device
+// compilation.
+
+template <typename KernelName, typename KernelType>
+[[clang::sycl_kernel_entry_point(KernelName)]]
+void kernel_single_task(KernelType kernelFunc) {
+  kernelFunc();
+}
+
+struct single_purpose_kernel_name;
+struct single_purpose_kernel {
+  void operator()() const {}
+};
+
+[[clang::sycl_kernel_entry_point(single_purpose_kernel_name)]]
+void single_purpose_kernel_task(single_purpose_kernel kernelFunc) {
+  kernelFunc();
+}
+
+int main() {
+  int capture;
+  kernel_single_task<class lambda_kernel_name>(
+    [=]() {
+      (void) capture;
+    });
+  single_purpose_kernel obj;
+  single_purpose_kernel_task(obj);
+}
+
+// Verify that SYCL kernel caller functions are not emitted during host
+// compilation.
+//
+// CHECK-HOST-NOT: _ZTS26single_purpose_kernel_name
+// CHECK-HOST-NOT: _ZTSZ4mainE18lambda_kernel_name
+
+// Verify that sycl_kernel_entry_point attributed functions are not emitted
+// during device compilation.
+//
+// CHECK-DEVICE-NOT: single_purpose_kernel_task
+// CHECK-DEVICE-NOT: kernel_single_task
+
+// Verify that no code is generated for the bodies of sycl_kernel_entry_point
+// attributed functions during host compilation. ODR-use of these functions may
+// require them to be emitted, but they have no effect if called.
+//
+// CHECK-HOST-LINUX:      define dso_local void @_Z26single_purpose_kernel_task21single_purpose_kernel() #[[LINUX_ATTR0:[0-9]+]] {
+// CHECK-HOST-LINUX-NEXT: entry:
+// CHECK-HOST-LINUX-NEXT:   %kernelFunc = alloca %struct.single_purpose_kernel, align 1
+// CHECK-HOST-LINUX-NEXT:   ret void
+// CHECK-HOST-LINUX-NEXT: }
+//
+// CHECK-HOST-LINUX:      define internal void @_Z18kernel_single_taskIZ4mainE18lambda_kernel_nameZ4mainEUlvE_EvT0_(i32 %kernelFunc.coerce) #[[LINUX_ATTR0:[0-9]+]] {
+// CHECK-HOST-LINUX-NEXT: entry:
+// CHECK-HOST-LINUX-NEXT:   %kernelFunc = alloca %class.anon, align 4
+// CHECK-HOST-LINUX-NEXT:   %coerce.dive = getelementptr inbounds nuw %class.anon, ptr %kernelFunc, i32 0, i32 0
+// CHECK-HOST-LINUX-NEXT:   store i32 %kernelFunc.coerce, ptr %coerce.dive, align 4
+// CHECK-HOST-LINUX-NEXT:   ret void
+// CHECK-HOST-LINUX-NEXT: }
+//
+// CHECK-HOST-WINDOWS:      define dso_local void @"?single_purpose_kernel_task@@YAXUsingle_purpose_kernel@@@Z"(i8 %kernelFunc.coerce) #[[WINDOWS_ATTR0:[0-9]+]] {
----------------
tahonermann wrote:

Yup, will fix.

https://github.com/llvm/llvm-project/pull/133030