yaxunl created this revision.
yaxunl added reviewers: tra, rjmccall.
constexpr variables are compile time constants and implicitly const, therefore
they are safe to emit on both device and host side. Besides, in many cases
they are intended for both device and host, therefore it makes sense
to emit them on both device and host sides if necessary.
In most cases constexpr variables are used as rvalue and the variables
themselves do not need to be emitted. However if their address is taken,
then they need to be emitted.
The following example shows constexpr is available on device side without
`__device__` or `__constant__` attribute
https://godbolt.org/z/Uf7CgK
Which indicates that we need to emit constexpr variables on device side
even without `__device__` or `__constant__` attribute when necessary.
This should be OK since the initializer is compile time constant and the
variable itself is constant. They can just be emitted in the same way
as the host side.
For C++14, clang is able to handle that since clang emits them with
available_externally linkage together with the initializer.
However for C++17, the constexpr static data member of a class or template class
become inline variables implicitly. Therefore they become definitions with
linkonce_odr or weak_odr linkages. As such, they can not have
available_externally
linkage.
This patch fixes that by allowing clang to emit definitions of constexpr
variables
in the standard way on device side.
https://reviews.llvm.org/D79237
Files:
clang/lib/CodeGen/CodeGenModule.cpp
clang/test/CodeGenCUDA/constexpr-variables.cu
Index: clang/test/CodeGenCUDA/constexpr-variables.cu
===================================================================
--- /dev/null
+++ clang/test/CodeGenCUDA/constexpr-variables.cu
@@ -0,0 +1,30 @@
+// RUN: %clang_cc1 -std=c++14 %s -emit-llvm -o - -triple nvptx \
+// RUN: -fcuda-is-device | FileCheck --check-prefixes=COM,CXX14 %s
+// RUN: %clang_cc1 -std=c++17 %s -emit-llvm -o - -triple nvptx \
+// RUN: -fcuda-is-device | FileCheck --check-prefixes=COM,CXX17 %s
+
+#include "Inputs/cuda.h"
+
+// COM: @_ZL1a = internal {{.*}}constant i32 7
+constexpr int a = 7;
+__constant__ const int &use_a = a;
+
+namespace B {
+ // COM: @_ZN1BL1bE = internal {{.*}}constant i32 9
+ constexpr int b = 9;
+}
+__constant__ const int &use_B_b = B::b;
+
+struct Q {
+ // CXX14: @_ZN1Q1kE = available_externally {{.*}}constant i32 5
+ // CXX17: @_ZN1Q1kE = linkonce_odr {{.*}}constant i32 5
+ static constexpr int k = 5;
+};
+__constant__ const int &use_Q_k = Q::k;
+
+template<typename T> struct X {
+ // CXX14: @_ZN1XIiE1aE = available_externally {{.*}}constant i32 123
+ // CXX17: @_ZN1XIiE1aE = linkonce_odr {{.*}}constant i32 123
+ static constexpr int a = 123;
+};
+__constant__ const int &use_X_a = X<int>::a;
Index: clang/lib/CodeGen/CodeGenModule.cpp
===================================================================
--- clang/lib/CodeGen/CodeGenModule.cpp
+++ clang/lib/CodeGen/CodeGenModule.cpp
@@ -2549,12 +2549,16 @@
// If this is CUDA, be selective about which declarations we emit.
if (LangOpts.CUDA) {
if (LangOpts.CUDAIsDevice) {
+ bool IsConstexprVar = false;
+ if (auto *VD = dyn_cast<VarDecl>(Global))
+ IsConstexprVar = VD->isConstexpr();
if (!Global->hasAttr<CUDADeviceAttr>() &&
!Global->hasAttr<CUDAGlobalAttr>() &&
!Global->hasAttr<CUDAConstantAttr>() &&
!Global->hasAttr<CUDASharedAttr>() &&
!Global->getType()->isCUDADeviceBuiltinSurfaceType() &&
- !Global->getType()->isCUDADeviceBuiltinTextureType())
+ !Global->getType()->isCUDADeviceBuiltinTextureType() &&
+ !IsConstexprVar)
return;
} else {
// We need to emit host-side 'shadows' for all global
Index: clang/test/CodeGenCUDA/constexpr-variables.cu
===================================================================
--- /dev/null
+++ clang/test/CodeGenCUDA/constexpr-variables.cu
@@ -0,0 +1,30 @@
+// RUN: %clang_cc1 -std=c++14 %s -emit-llvm -o - -triple nvptx \
+// RUN: -fcuda-is-device | FileCheck --check-prefixes=COM,CXX14 %s
+// RUN: %clang_cc1 -std=c++17 %s -emit-llvm -o - -triple nvptx \
+// RUN: -fcuda-is-device | FileCheck --check-prefixes=COM,CXX17 %s
+
+#include "Inputs/cuda.h"
+
+// COM: @_ZL1a = internal {{.*}}constant i32 7
+constexpr int a = 7;
+__constant__ const int &use_a = a;
+
+namespace B {
+ // COM: @_ZN1BL1bE = internal {{.*}}constant i32 9
+ constexpr int b = 9;
+}
+__constant__ const int &use_B_b = B::b;
+
+struct Q {
+ // CXX14: @_ZN1Q1kE = available_externally {{.*}}constant i32 5
+ // CXX17: @_ZN1Q1kE = linkonce_odr {{.*}}constant i32 5
+ static constexpr int k = 5;
+};
+__constant__ const int &use_Q_k = Q::k;
+
+template<typename T> struct X {
+ // CXX14: @_ZN1XIiE1aE = available_externally {{.*}}constant i32 123
+ // CXX17: @_ZN1XIiE1aE = linkonce_odr {{.*}}constant i32 123
+ static constexpr int a = 123;
+};
+__constant__ const int &use_X_a = X<int>::a;
Index: clang/lib/CodeGen/CodeGenModule.cpp
===================================================================
--- clang/lib/CodeGen/CodeGenModule.cpp
+++ clang/lib/CodeGen/CodeGenModule.cpp
@@ -2549,12 +2549,16 @@
// If this is CUDA, be selective about which declarations we emit.
if (LangOpts.CUDA) {
if (LangOpts.CUDAIsDevice) {
+ bool IsConstexprVar = false;
+ if (auto *VD = dyn_cast<VarDecl>(Global))
+ IsConstexprVar = VD->isConstexpr();
if (!Global->hasAttr<CUDADeviceAttr>() &&
!Global->hasAttr<CUDAGlobalAttr>() &&
!Global->hasAttr<CUDAConstantAttr>() &&
!Global->hasAttr<CUDASharedAttr>() &&
!Global->getType()->isCUDADeviceBuiltinSurfaceType() &&
- !Global->getType()->isCUDADeviceBuiltinTextureType())
+ !Global->getType()->isCUDADeviceBuiltinTextureType() &&
+ !IsConstexprVar)
return;
} else {
// We need to emit host-side 'shadows' for all global
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
