diff options
| author | Valentin Clement (バレンタイン クレメン) <clementval@gmail.com> | 2025-04-29 16:52:55 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-04-29 16:52:55 -0700 |
| commit | d5272e4f4130788f261b44b5412c75a6b87fc836 (patch) | |
| tree | 1ca980bc7991835419ec697d18d7073b5a7e4265 | |
| parent | c68535581135a1513c9c4c1c7672307d4b5e616e (diff) | |
| download | llvm-d5272e4f4130788f261b44b5412c75a6b87fc836.zip llvm-d5272e4f4130788f261b44b5412c75a6b87fc836.tar.gz llvm-d5272e4f4130788f261b44b5412c75a6b87fc836.tar.bz2 | |
[flang][cuda] Only copy global that have effective use (#137890)
| -rw-r--r-- | flang/lib/Optimizer/Transforms/CUFDeviceGlobal.cpp | 9 | ||||
| -rw-r--r-- | flang/test/Fir/CUDA/cuda-implicit-device-global.f90 | 13 |
2 files changed, 22 insertions, 0 deletions
diff --git a/flang/lib/Optimizer/Transforms/CUFDeviceGlobal.cpp b/flang/lib/Optimizer/Transforms/CUFDeviceGlobal.cpp index 3f13a18..328e237 100644 --- a/flang/lib/Optimizer/Transforms/CUFDeviceGlobal.cpp +++ b/flang/lib/Optimizer/Transforms/CUFDeviceGlobal.cpp @@ -32,6 +32,15 @@ static void processAddrOfOp(fir::AddrOfOp addrOfOp, mlir::SymbolTable &symbolTable, llvm::DenseSet<fir::GlobalOp> &candidates, bool recurseInGlobal) { + + // Check if there is a real use of the global. + if (addrOfOp.getOperation()->hasOneUse()) { + mlir::OpOperand &addrUse = *addrOfOp.getOperation()->getUses().begin(); + if (mlir::isa<fir::DeclareOp>(addrUse.getOwner()) && + addrUse.getOwner()->use_empty()) + return; + } + if (auto globalOp = symbolTable.lookup<fir::GlobalOp>( addrOfOp.getSymbol().getRootReference().getValue())) { // TO DO: limit candidates to non-scalars. Scalars appear to have been diff --git a/flang/test/Fir/CUDA/cuda-implicit-device-global.f90 b/flang/test/Fir/CUDA/cuda-implicit-device-global.f90 index 11866d8..758c2e2 100644 --- a/flang/test/Fir/CUDA/cuda-implicit-device-global.f90 +++ b/flang/test/Fir/CUDA/cuda-implicit-device-global.f90 @@ -329,3 +329,16 @@ fir.global internal @_QFkernel4Ea : i32 { // CHECK-LABEL: fir.global internal @_QFkernel4Ea : i32 // CHECK-LABEL: gpu.module @cuda_device_mod // CHECK: fir.global internal @_QFkernel4Ea : i32 + +// ----- + +fir.global @_QMiso_c_bindingECc_alert constant : !fir.char<1> +func.func @_QMcudafor_lib_internalsPfoo() attributes {cuf.proc_attr = #cuf.cuda_proc<global>} { + %19 = fir.address_of(@_QMiso_c_bindingECc_alert) : !fir.ref<!fir.char<1>> + %c1 = arith.constant 1 : index + %20 = fir.declare %19 typeparams %c1 {fortran_attrs = #fir.var_attrs<parameter>, uniq_name = "_QMiso_c_bindingECc_alert"} : (!fir.ref<!fir.char<1>>, index) -> !fir.ref<!fir.char<1>> + return +} + +// CHECK-LABEL: gpu.module @cuda_device_mod +// CHECK-NOT: _QMiso_c_bindingECc_alert |