[clang] d1327f8 - [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

Ethan Stewart via cfe-commits cfe-commits at lists.llvm.org
Mon Dec 13 14:30:37 PST 2021


Author: Ethan Stewart
Date: 2021-12-13T16:31:24-06:00
New Revision: d1327f8a574a0936f462387778adf0dfc14358f6

URL: https://github.com/llvm/llvm-project/commit/d1327f8a574a0936f462387778adf0dfc14358f6
DIFF: https://github.com/llvm/llvm-project/commit/d1327f8a574a0936f462387778adf0dfc14358f6.diff

LOG: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

There are instances where clang codegen creates stores to
address space 4 in ctors, which causes a crash in llc.
This store was being optimized out at opt levels > 0.

For example:

pragma omp declare target
static  const double log_smallx = log2(smallx);
pragma omp end declare target

This patch ensures that any global const that does not
have constant initialization stays in address space 1.

Note - a second patch is in the works where all global
constants are placed in address space 1 during
codegen and then the opt pass InferAdressSpaces
will promote to address space 4 where necessary.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D115661

Added: 
    

Modified: 
    clang/lib/CodeGen/TargetInfo.cpp
    clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
    clang/test/CodeGenCXX/cxx11-extern-constexpr.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index 0e03588f9b248..5a1564575d6c0 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -9362,7 +9362,9 @@ AMDGPUTargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
   if (AddrSpace != LangAS::Default)
     return AddrSpace;
 
-  if (CGM.isTypeConstant(D->getType(), false)) {
+  // Only promote to address space 4 if VarDecl has constant initialization.
+  if (CGM.isTypeConstant(D->getType(), false) &&
+      D->hasConstantInitialization()) {
     if (auto ConstAS = CGM.getTarget().getConstantAddressSpace())
       return ConstAS.getValue();
   }

diff  --git a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
index f1b6584c48497..234be25e8ec38 100644
--- a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
+++ b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
@@ -78,12 +78,12 @@ std::initializer_list<int> thread_local x = {1, 2, 3, 4};
 // X86: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE2_]] = internal global [2 x i32] zeroinitializer, align 4
 // X86: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE3_]] = internal constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4
 // AMDGCN: @_ZN15partly_constant1kE ={{.*}} addrspace(1) global i32 0, align 4
-// AMDGCN: @_ZN15partly_constant2ilE ={{.*}} addrspace(4) global {{.*}} null, align 8
-// AMDGCN: @[[PARTLY_CONSTANT_OUTER:_ZGRN15partly_constant2ilE_]] = internal addrspace(4) global {{.*}} zeroinitializer, align 8
-// AMDGCN: @[[PARTLY_CONSTANT_INNER:_ZGRN15partly_constant2ilE0_]] = internal addrspace(4) global [3 x {{.*}}] zeroinitializer, align 8
-// AMDGCN: @[[PARTLY_CONSTANT_FIRST:_ZGRN15partly_constant2ilE1_]] = internal addrspace(4) constant [3 x i32] [i32 1, i32 2, i32 3], align 4
-// AMDGCN: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE2_]] = internal addrspace(4) global [2 x i32] zeroinitializer, align 4
-// AMDGCN: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE3_]] = internal addrspace(4) constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4
+// AMDGCN: @_ZN15partly_constant2ilE ={{.*}} addrspace(1) global {{.*}} null, align 8
+// AMDGCN: @[[PARTLY_CONSTANT_OUTER:_ZGRN15partly_constant2ilE_]] = internal addrspace(1) global {{.*}} zeroinitializer, align 8
+// AMDGCN: @[[PARTLY_CONSTANT_INNER:_ZGRN15partly_constant2ilE0_]] = internal addrspace(1) global [3 x {{.*}}] zeroinitializer, align 8
+// AMDGCN: @[[PARTLY_CONSTANT_FIRST:_ZGRN15partly_constant2ilE1_]] = internal addrspace(1) constant [3 x i32] [i32 1, i32 2, i32 3], align 4
+// AMDGCN: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE2_]] = internal addrspace(1) global [2 x i32] zeroinitializer, align 4
+// AMDGCN: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE3_]] = internal addrspace(1) constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4
 
 // X86: @[[REFTMP1:.*]] = private constant [2 x i32] [i32 42, i32 43], align 4
 // X86: @[[REFTMP2:.*]] = private constant [3 x %{{.*}}] [%{{.*}} { i32 1 }, %{{.*}} { i32 2 }, %{{.*}} { i32 3 }], align 4

diff  --git a/clang/test/CodeGenCXX/cxx11-extern-constexpr.cpp b/clang/test/CodeGenCXX/cxx11-extern-constexpr.cpp
index 13ba10935daef..940941936effb 100644
--- a/clang/test/CodeGenCXX/cxx11-extern-constexpr.cpp
+++ b/clang/test/CodeGenCXX/cxx11-extern-constexpr.cpp
@@ -7,7 +7,7 @@ struct A {
   static const int Foo = 123;
 };
 // X86: @_ZN1A3FooE ={{.*}} constant i32 123, align 4
-// AMD: @_ZN1A3FooE ={{.*}} addrspace(4) constant i32 123, align 4
+// AMD: @_ZN1A3FooE ={{.*}} addrspace(1) constant i32 123, align 4
 const int *p = &A::Foo; // emit available_externally
 const int A::Foo;       // convert to full definition
 
@@ -37,7 +37,7 @@ struct Foo {
   // CXX11X86: @_ZN3Foo21ConstexprStaticMemberE = available_externally constant i32 42,
   // CXX17X86: @_ZN3Foo21ConstexprStaticMemberE = linkonce_odr constant i32 42,
   // CXX11AMD: @_ZN3Foo21ConstexprStaticMemberE = available_externally addrspace(4) constant i32 42,
-  // CXX17AMD: @_ZN3Foo21ConstexprStaticMemberE = linkonce_odr addrspace(4) constant i32 42,
+  // CXX17AMD: @_ZN3Foo21ConstexprStaticMemberE = linkonce_odr addrspace(4) constant i32 42, comdat, align 4
   static constexpr int ConstexprStaticMember = 42;
   // X86: @_ZN3Foo17ConstStaticMemberE = available_externally constant i32 43,
   // AMD: @_ZN3Foo17ConstStaticMemberE = available_externally addrspace(4) constant i32 43,


        


More information about the cfe-commits mailing list