[Flang][OpenMP] Minimize host ops remaining in device compilation

This patch updates the function filtering OpenMP pass intended to remove host
functions from the MLIR module created by Flang lowering when targeting an
OpenMP target device.

Host functions holding target regions must be kept, so that the target regions
within them can be translated for the device. The issue is that non-target
operations inside these functions cannot be discarded because some of them hold
information that is also relevant during target device codegen. Specifically,
mapping information resides outside of `omp.target` regions.

This patch updates the previous behavior where all host operations were
preserved to then ignore all of those that are not actually needed by target
device codegen. This, in practice, means only keeping target regions and mapping
information needed by the device. Arguments for some of these remaining
operations are replaced by placeholder allocations and `fir.undefined`, since
they are only actually defined inside of the target regions themselves.

As a result, this set of changes makes it possible to later simplify target
device codegen, as it is no longer necessary to handle host operations
differently to avoid issues.

Author: skatrak

flang/include/flang/Optimizer/OpenMP/Passes.td

@@ -53,7 +53,8 @@ def FunctionFilteringPass : Pass<"omp-function-filtering"> {
                 "for the target device.";
   let dependentDialects = [
     "mlir::func::FuncDialect",
-    "fir::FIROpsDialect"
+    "fir::FIROpsDialect",
+    "mlir::omp::OpenMPDialect"
   ];
 }
 

flang/lib/Optimizer/OpenMP/FunctionFiltering.cpp

@@ -1,7 +1,7 @@
-!RUN: %flang_fc1 -emit-hlfir -fopenmp %s -o - | FileCheck %s
-!RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device %s -o - | FileCheck %s
-!RUN: bbc -emit-hlfir -fopenmp %s -o - | FileCheck %s
-!RUN: bbc -emit-hlfir -fopenmp -fopenmp-is-target-device %s -o - | FileCheck %s
+!RUN: %flang_fc1 -emit-hlfir -fopenmp %s -o - | FileCheck %s --check-prefixes=BOTH,HOST
+!RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-is-device %s -o - | FileCheck %s --check-prefixes=BOTH,DEVICE
+!RUN: bbc -emit-hlfir -fopenmp %s -o - | FileCheck %s --check-prefixes=BOTH,HOST
+!RUN: bbc -emit-hlfir -fopenmp -fopenmp-is-target-device %s -o - | FileCheck %s --check-prefixes=BOTH,DEVICE
 
 program test_link
 
@@ -20,13 +20,14 @@ program test_link
   integer, pointer :: test_ptr2
   !$omp declare target link(test_ptr2)
 
-  !CHECK-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<i32>, i32) map_clauses(implicit, tofrom) capture(ByRef) -> !fir.ref<i32> {name = "test_int"}
+  !BOTH-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<i32>, i32) map_clauses(implicit, tofrom) capture(ByRef) -> !fir.ref<i32> {name = "test_int"}
   !$omp target
     test_int = test_int + 1
   !$omp end target
 
 
-  !CHECK-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.array<3xi32>>, !fir.array<3xi32>) map_clauses(implicit, tofrom) capture(ByRef) bounds({{%.*}}) -> !fir.ref<!fir.array<3xi32>> {name = "test_array_1d"}
+  !HOST-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.array<3xi32>>, !fir.array<3xi32>) map_clauses(implicit, tofrom) capture(ByRef) bounds({{%.*}}) -> !fir.ref<!fir.array<3xi32>> {name = "test_array_1d"}
+  !DEVICE-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.array<3xi32>>, !fir.array<3xi32>) map_clauses(implicit, tofrom) capture(ByRef) -> !fir.ref<!fir.array<3xi32>> {name = "test_array_1d"}
   !$omp target
     do i = 1,3
       test_array_1d(i) = i * 2
@@ -35,18 +36,18 @@ program test_link
 
   allocate(test_ptr1)
   test_ptr1 = 1
-  !CHECK-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.box<!fir.ptr<i32>>) map_clauses(always, implicit, descriptor, to) capture(ByRef) members({{%.*}} : !fir.llvm_ptr<!fir.ref<i32>>) -> !fir.ref<!fir.box<!fir.ptr<i32>>> {name = "test_ptr1"}
+  !BOTH-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.box<!fir.ptr<i32>>) map_clauses(always, implicit, descriptor, to) capture(ByRef) members({{%.*}} : !fir.llvm_ptr<!fir.ref<i32>>) -> !fir.ref<!fir.box<!fir.ptr<i32>>> {name = "test_ptr1"}
   !$omp target
     test_ptr1 = test_ptr1 + 1
   !$omp end target
 
-  !CHECK-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<i32>, i32) map_clauses(implicit, tofrom) capture(ByRef) -> !fir.ref<i32> {name = "test_target"}
+  !BOTH-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<i32>, i32) map_clauses(implicit, tofrom) capture(ByRef) -> !fir.ref<i32> {name = "test_target"}
   !$omp target
     test_target = test_target + 1
   !$omp end target
 
 
-  !CHECK-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.box<!fir.ptr<i32>>) map_clauses(always, implicit, descriptor, to) capture(ByRef) members({{%.*}} : !fir.llvm_ptr<!fir.ref<i32>>) -> !fir.ref<!fir.box<!fir.ptr<i32>>> {name = "test_ptr2"}
+  !BOTH-DAG: {{%.*}} = omp.map.info var_ptr({{%.*}} : !fir.ref<!fir.box<!fir.ptr<i32>>>, !fir.box<!fir.ptr<i32>>) map_clauses(always, implicit, descriptor, to) capture(ByRef) members({{%.*}} : !fir.llvm_ptr<!fir.ref<i32>>) -> !fir.ref<!fir.box<!fir.ptr<i32>>> {name = "test_ptr2"}
   test_ptr2 => test_target
   !$omp target
     test_ptr2 = test_ptr2 + 1