forked from OSchip/llvm-project
[NVPTX] Read __CUDA_FTZ from module flags in NVVMReflect.
Summary: Previously the NVVMReflect pass would read its configuration from command-line flags or a static configuration given to the pass at instantiation time. This doesn't quite work for clang's use-case. It needs to pass a value for __CUDA_FTZ down on a per-module basis. We use a module flag for this, so the NVVMReflect pass needs to be updated to read said flag. Reviewers: tra, rnk Subscribers: cfe-commits, jholewinski Differential Revision: http://reviews.llvm.org/D18672 llvm-svn: 265090
This commit is contained in:
parent
645c3014a1
commit
efcc81cbb4
|
@ -7,11 +7,16 @@
|
|||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
//
|
||||
// This pass replaces occurrences of __nvvm_reflect("string") and
|
||||
// llvm.nvvm.reflect with an integer based on the value of -nvvm-reflect-list
|
||||
// string=<int>.
|
||||
// This pass replaces occurrences of __nvvm_reflect("foo") and llvm.nvvm.reflect
|
||||
// with an integer.
|
||||
//
|
||||
// If we see a string not specified in our flags, we replace that call with 0.
|
||||
// We choose the value we use by looking, in this order, at:
|
||||
//
|
||||
// * the -nvvm-reflect-list flag, which has the format "foo=1,bar=42",
|
||||
// * the StringMap passed to the pass's constructor, and
|
||||
// * metadata in the module itself.
|
||||
//
|
||||
// If we see an unknown string, we replace its call with 0.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
|
@ -55,10 +60,9 @@ public:
|
|||
static char ID;
|
||||
NVVMReflect() : NVVMReflect(StringMap<int>()) {}
|
||||
|
||||
NVVMReflect(const StringMap<int> &Mapping) : FunctionPass(ID) {
|
||||
NVVMReflect(const StringMap<int> &Mapping)
|
||||
: FunctionPass(ID), VarMap(Mapping) {
|
||||
initializeNVVMReflectPass(*PassRegistry::getPassRegistry());
|
||||
for (const auto &KV : Mapping)
|
||||
VarMap[KV.getKey()] = KV.getValue();
|
||||
setVarMap();
|
||||
}
|
||||
|
||||
|
@ -206,6 +210,12 @@ bool NVVMReflect::runOnFunction(Function &F) {
|
|||
auto Iter = VarMap.find(ReflectArg);
|
||||
if (Iter != VarMap.end())
|
||||
ReflectVal = Iter->second;
|
||||
else if (ReflectArg == "__CUDA_FTZ") {
|
||||
// Try to pull __CUDA_FTZ from the nvvm-reflect-ftz module flag.
|
||||
if (auto *Flag = mdconst::extract_or_null<ConstantInt>(
|
||||
F.getParent()->getModuleFlag("nvvm-reflect-ftz")))
|
||||
ReflectVal = Flag->getSExtValue();
|
||||
}
|
||||
Call->replaceAllUsesWith(ConstantInt::get(Call->getType(), ReflectVal));
|
||||
ToRemove.push_back(Call);
|
||||
}
|
||||
|
|
|
@ -0,0 +1,13 @@
|
|||
; RUN: opt < %s -S -nvvm-reflect | FileCheck %s
|
||||
|
||||
declare i32 @__nvvm_reflect(i8*)
|
||||
@str = private unnamed_addr addrspace(1) constant [11 x i8] c"__CUDA_FTZ\00"
|
||||
|
||||
define i32 @foo() {
|
||||
%call = call i32 @__nvvm_reflect(i8* addrspacecast (i8 addrspace(1)* getelementptr inbounds ([11 x i8], [11 x i8] addrspace(1)* @str, i32 0, i32 0) to i8*))
|
||||
; CHECK: ret i32 42
|
||||
ret i32 %call
|
||||
}
|
||||
|
||||
!llvm.module.flags = !{!0}
|
||||
!0 = !{i32 4, !"nvvm-reflect-ftz", i32 42}
|
Loading…
Reference in New Issue