12ba74e181
Runtime function call to a void function are producing a ssa value because the FunctionType result is set to NoneType with is later translated to a empty struct. This is not an issue when going to LLVM IR but it breaks when lowering a gpu module to PTX. This patch update the RTModel to correctly set the FunctionType result type to nothing. This is one runtime call before this patch at the LLVM IR dialect step. ``` %45 = llvm.call @_FortranAAssign(%arg0, %1, %44, %4) : (!llvm.ptr, !llvm.ptr, !llvm.ptr, i32) -> !llvm.struct<()> ``` After the patch the call would be correctly formed ``` llvm.call @_FortranAAssign(%arg0, %1, %44, %4) : (!llvm.ptr, !llvm.ptr, !llvm.ptr, i32) -> () ``` Without the patch it would lead to error like: ``` ptxas /tmp/mlir-cuda_device_mod-nvptx64-nvidia-cuda-sm_60-e804b6.ptx, line 10; error : Output parameter cannot be an incomplete array. ptxas /tmp/mlir-cuda_device_mod-nvptx64-nvidia-cuda-sm_60-e804b6.ptx, line 125; error : Call has wrong number of parameters ``` The change is pretty much mechanical.
57 lines
3.8 KiB
Plaintext
57 lines
3.8 KiB
Plaintext
// Test overlapping assignment of derived type arrays with allocatable components.
|
|
// This requires initializing the allocatable components to an unallocated status
|
|
// before they can be used in component assignments, and to deallocate the components
|
|
// that may have been allocated in the end.
|
|
|
|
// RUN: fir-opt --array-value-copy %s | FileCheck %s
|
|
// RUN: fir-opt --array-value-copy="optimize-conflicts=true" %s | FileCheck %s
|
|
|
|
|
|
!t_with_alloc_comp = !fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>
|
|
func.func private @custom_assign(!fir.ref<!t_with_alloc_comp>, !fir.ref<!t_with_alloc_comp>)
|
|
func.func @test_overlap_with_alloc_components(%arg0: !fir.ref<!fir.array<10x!t_with_alloc_comp>>) {
|
|
%0 = fir.alloca !fir.box<!t_with_alloc_comp>
|
|
%c10 = arith.constant 10 : index
|
|
%c9 = arith.constant 9 : index
|
|
%c1 = arith.constant 1 : index
|
|
%c-1 = arith.constant -1 : index
|
|
%c0 = arith.constant 0 : index
|
|
%1 = fir.shape %c10 : (index) -> !fir.shape<1>
|
|
%6 = fir.slice %c10, %c1, %c-1 : (index, index, index) -> !fir.slice<1>
|
|
%2 = fir.array_load %arg0(%1) : (!fir.ref<!fir.array<10x!t_with_alloc_comp>>, !fir.shape<1>) -> !fir.array<10x!t_with_alloc_comp>
|
|
%7 = fir.array_load %arg0(%1) [%6] : (!fir.ref<!fir.array<10x!t_with_alloc_comp>>, !fir.shape<1>, !fir.slice<1>) -> !fir.array<10x!t_with_alloc_comp>
|
|
%9 = fir.do_loop %arg1 = %c0 to %c9 step %c1 unordered iter_args(%arg2 = %2) -> (!fir.array<10x!t_with_alloc_comp>) {
|
|
%10 = fir.array_access %7, %arg1 : (!fir.array<10x!t_with_alloc_comp>, index) -> !fir.ref<!t_with_alloc_comp>
|
|
%11 = fir.array_access %arg2, %arg1 : (!fir.array<10x!t_with_alloc_comp>, index) -> !fir.ref<!t_with_alloc_comp>
|
|
fir.call @custom_assign(%11, %10) : (!fir.ref<!t_with_alloc_comp>, !fir.ref<!t_with_alloc_comp>) -> ()
|
|
%19 = fir.array_amend %arg2, %11 : (!fir.array<10x!t_with_alloc_comp>, !fir.ref<!t_with_alloc_comp>) -> !fir.array<10x!t_with_alloc_comp>
|
|
fir.result %19 : !fir.array<10x!t_with_alloc_comp>
|
|
}
|
|
fir.array_merge_store %2, %9 to %arg0 : !fir.array<10x!t_with_alloc_comp>, !fir.array<10x!t_with_alloc_comp>, !fir.ref<!fir.array<10x!t_with_alloc_comp>>
|
|
return
|
|
}
|
|
|
|
// CHECK-LABEL: func @test_overlap_with_alloc_components(
|
|
// CHECK-SAME: %[[VAL_0:.*]]: !fir.ref<!fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>>) {
|
|
// CHECK: %[[VAL_4:.*]] = arith.constant 10 : index
|
|
// CHECK: %[[VAL_6:.*]] = arith.constant 1 : index
|
|
// CHECK: %[[VAL_7:.*]] = arith.constant -1 : index
|
|
// CHECK: %[[VAL_9:.*]] = fir.shape %[[VAL_4]] : (index) -> !fir.shape<1>
|
|
// CHECK: %[[VAL_10:.*]] = fir.slice %[[VAL_4]], %[[VAL_6]], %[[VAL_7]] : (index, index, index) -> !fir.slice<1>
|
|
// CHECK: %[[VAL_11:.*]] = fir.allocmem !fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>
|
|
// CHECK: %[[VAL_12:.*]] = fir.embox %[[VAL_11]](%[[VAL_9]]) : (!fir.heap<!fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>>, !fir.shape<1>) -> !fir.box<!fir.heap<!fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>>>
|
|
// CHECK: %[[VAL_16:.*]] = fir.convert %[[VAL_12]] : (!fir.box<!fir.heap<!fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>>>) -> !fir.box<none>
|
|
// CHECK: fir.call @_FortranAInitialize(%[[VAL_16]], %{{.*}}, %{{.*}}) : (!fir.box<none>, !fir.ref<i8>, i32) -> ()
|
|
// CHECK: fir.do_loop {{.*}} {
|
|
// CHECK: fir.call @_FortranAAssign
|
|
// CHECK: }
|
|
// CHECK: fir.do_loop {{.*}} {
|
|
// CHECK: fir.call @custom_assign
|
|
// CHECK: }
|
|
// CHECK: fir.do_loop %{{.*}} {
|
|
// CHECK: fir.call @_FortranAAssign
|
|
// CHECK: }
|
|
// CHECK: %[[VAL_72:.*]] = fir.convert %[[VAL_12]] : (!fir.box<!fir.heap<!fir.array<10x!fir.type<t{i:!fir.box<!fir.heap<!fir.array<?xi32>>>}>>>>) -> !fir.box<none>
|
|
// CHECK: fir.call @_FortranADestroy(%[[VAL_72]]) : (!fir.box<none>) -> ()
|
|
// CHECK: fir.freemem %[[VAL_11]]
|