summaryrefslogtreecommitdiff
path: root/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp')
-rw-r--r--llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp16
1 files changed, 16 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
index b461c3c4bfdc..f5e12fd960d0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
@@ -11,6 +11,7 @@
#include "AMDGPUPerfHintAnalysis.h"
#include "AMDGPUSubtarget.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/IR/Constants.h"
#include "llvm/Target/TargetMachine.h"
using namespace llvm;
@@ -101,6 +102,21 @@ void AMDGPUMachineFunction::allocateModuleLDSGlobal(const Function &F) {
}
}
+Optional<uint32_t>
+AMDGPUMachineFunction::getLDSKernelIdMetadata(const Function &F) {
+ auto MD = F.getMetadata("llvm.amdgcn.lds.kernel.id");
+ if (MD && MD->getNumOperands() == 1) {
+ ConstantInt *KnownSize = mdconst::extract<ConstantInt>(MD->getOperand(0));
+ if (KnownSize) {
+ uint64_t V = KnownSize->getZExtValue();
+ if (V <= UINT32_MAX) {
+ return V;
+ }
+ }
+ }
+ return {};
+}
+
void AMDGPUMachineFunction::setDynLDSAlign(const DataLayout &DL,
const GlobalVariable &GV) {
assert(DL.getTypeAllocSize(GV.getValueType()).isZero());