[clang] [OpenACC] Implement firstprivate lowering except init. (PR #153847)

[Razvan Lupusoru via cfe-commits]

================
@@ -0,0 +1,571 @@
+// RUN: %clang_cc1 -fopenacc -triple x86_64-linux-gnu -Wno-openacc-self-if-potential-conflict -emit-cir -fclangir -triple x86_64-linux-pc %s -o - | FileCheck %s
+
+struct NoCopyConstruct {};
+
+struct CopyConstruct {
+  CopyConstruct() = default;
+  CopyConstruct(const CopyConstruct&);
+};
+
+struct NonDefaultCtor {
+  NonDefaultCtor();
+};
+
+struct HasDtor {
+  ~HasDtor();
+};
+
+// CHECK: acc.firstprivate.recipe @firstprivatization__ZTSA5_7HasDtor : !cir.ptr<!cir.array<!rec_HasDtor x 5>> init {
+// CHECK-NEXT: ^bb0(%[[ARG:.*]]: !cir.ptr<!cir.array<!rec_HasDtor x 5>> {{.*}}):
+// CHECK-NEXT: cir.alloca !cir.array<!rec_HasDtor x 5>, !cir.ptr<!cir.array<!rec_HasDtor x 5>>, ["openacc.private.init"]
+// CHECK-NEXT: acc.yield
+// CHECK-NEXT: } copy {
+// CHECK-NEXT: ^bb0(%[[ARG_FROM:.*]]: !cir.ptr<!cir.array<!rec_HasDtor x 5>> {{.*}}, %[[ARG_TO:.*]]: !cir.ptr<!cir.array<!rec_HasDtor x 5>> {{.*}}):
+//
+// CHECK-NEXT: acc.yield
+//
+// CHECK-NEXT: } destroy {
+// CHECK-NEXT: ^bb0(%[[ARG:.*]]: !cir.ptr<!cir.array<!rec_HasDtor x 5>> {{.*}}):
+// CHECK-NEXT: %[[LAST_IDX:.*]] = cir.const #cir.int<4> : !u64i
+// CHECK-NEXT: %[[ARRPTR:.*]] = cir.cast(array_to_ptrdecay, %[[ARG]] : !cir.ptr<!cir.array<!rec_HasDtor x 5>>), !cir.ptr<!rec_HasDtor>
+// CHECK-NEXT: %[[ELEM:.*]] = cir.ptr_stride(%[[ARRPTR]] : !cir.ptr<!rec_HasDtor>, %[[LAST_IDX]] : !u64i), !cir.ptr<!rec_HasDtor>
+// CHECK-NEXT: %[[ITR:.*]] = cir.alloca !cir.ptr<!rec_HasDtor>, !cir.ptr<!cir.ptr<!rec_HasDtor>>, ["__array_idx"]
+// CHECK-NEXT: cir.store %[[ELEM]], %[[ITR]] : !cir.ptr<!rec_HasDtor>, !cir.ptr<!cir.ptr<!rec_HasDtor>>
+// CHECK-NEXT: cir.do {
+// CHECK-NEXT: %[[ELEM_LOAD:.*]] = cir.load %[[ITR]] : !cir.ptr<!cir.ptr<!rec_HasDtor>>, !cir.ptr<!rec_HasDtor>
+// CHECK-NEXT: cir.call @_ZN7HasDtorD1Ev(%[[ELEM_LOAD]]) nothrow : (!cir.ptr<!rec_HasDtor>) -> ()
+// CHECK-NEXT: %[[NEG_ONE:.*]] =  cir.const #cir.int<-1> : !s64i
+// CHECK-NEXT: %[[PREVELEM:.*]] = cir.ptr_stride(%[[ELEM_LOAD]] : !cir.ptr<!rec_HasDtor>, %[[NEG_ONE]] : !s64i), !cir.ptr<!rec_HasDtor>
+// CHECK-NEXT: cir.store %[[PREVELEM]], %[[ITR]] : !cir.ptr<!rec_HasDtor>, !cir.ptr<!cir.ptr<!rec_HasDtor>>
+// CHECK-NEXT: cir.yield
+// CHECK-NEXT: } while {
+// CHECK-NEXT: %[[ELEM_LOAD:.*]] = cir.load %[[ITR]] : !cir.ptr<!cir.ptr<!rec_HasDtor>>, !cir.ptr<!rec_HasDtor>
+// CHECK-NEXT: %[[CMP:.*]] = cir.cmp(ne, %[[ELEM_LOAD]], %[[ARRPTR]]) : !cir.ptr<!rec_HasDtor>, !cir.bool
+// CHECK-NEXT: cir.condition(%[[CMP]])
+// CHECK-NEXT: }
+// CHECK-NEXT: acc.yield
+// CHECK-NEXT: }
+//
+// CHECK-NEXT: acc.firstprivate.recipe @firstprivatization__ZTSA5_14NonDefaultCtor : !cir.ptr<!cir.array<!rec_NonDefaultCtor x 5>> init {
+// CHECK-NEXT: ^bb0(%[[ARG:.*]]: !cir.ptr<!cir.array<!rec_NonDefaultCtor x 5>> {{.*}}):
+// CHECK-NEXT: %[[ALLOCA:.*]] = cir.alloca !cir.array<!rec_NonDefaultCtor x 5>, !cir.ptr<!cir.array<!rec_NonDefaultCtor x 5>>, ["openacc.private.init"]
----------------
razvanlupusoru wrote:

And it is also best to leave such handling to the codegen when target accelerator is decided. Since allocation space needs decided by compiler (global memory, shared memory, stack) based on heuristics and assignment of parallelism.

https://github.com/llvm/llvm-project/pull/153847