https://github.com/skatrak created
https://github.com/llvm/llvm-project/pull/150927
This patch updates the OpenMP optimization pass to know about the new DeviceRTL
functions for loop constructs.
This change marks these functions as potentially containing parallel regions,
which fixes a current bug with the state machine rewrite optimization. It
previously failed to identify parallel regions located inside of the callbacks
passed to these new DeviceRTL functions, causing the resulting code to skip
executing these parallel regions.
As a result, Generic kernels produced by Flang that contain parallel regions
now work properly.
One known related issue not fixed by this patch is that the presence of calls
to these functions will prevent the SPMD-ization of Generic kernels by
OpenMPOpt. Previously, this was due to assuming there was no parallel region.
This is changed by this patch, but instead we now mark it temporarily as
unsupported in an SPMD context. The reason is that, without additional changes,
code intended for the main thread of the team located outside of the parallel
region would not be guarded properly, resulting in race conditions and
generally invalid behavior.
>From aac44b842037ec2d0b8e9779fbad0baa55fba290 Mon Sep 17 00:00:00 2001
From: Sergio Afonso <safon...@amd.com>
Date: Fri, 25 Jul 2025 13:52:11 +0100
Subject: [PATCH] [OpenMPOpt] Make parallel regions reachable from new
DeviceRTL loop functions
This patch updates the OpenMP optimization pass to know about the new DeviceRTL
functions for loop constructs.
This change marks these functions as potentially containing parallel regions,
which fixes a current bug with the state machine rewrite optimization. It
previously failed to identify parallel regions located inside of the callbacks
passed to these new DeviceRTL functions, causing the resulting code to skip
executing these parallel regions.
As a result, Generic kernels produced by Flang that contain parallel regions
now work properly.
One known related issue not fixed by this patch is that the presence of calls
to these functions will prevent the SPMD-ization of Generic kernels by
OpenMPOpt. Previously, this was due to assuming there was no parallel region.
This is changed by this patch, but instead we now mark it temporarily as
unsupported in an SPMD context. The reason is that, without additional changes,
code intended for the main thread of the team located outside of the parallel
region would not be guarded properly, resulting in race conditions and
generally invalid behavior.
---
llvm/lib/Transforms/IPO/OpenMPOpt.cpp | 22 +++
.../fortran/target-generic-loops.f90 | 130 ++++++++++++++++++
.../offloading/fortran/target-spmd-loops.f90 | 39 ++++++
3 files changed, 191 insertions(+)
create mode 100644 offload/test/offloading/fortran/target-generic-loops.f90
create mode 100644 offload/test/offloading/fortran/target-spmd-loops.f90
diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
index 5e2247f2a88d0..d58da7b1db0e3 100644
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -5020,6 +5020,28 @@ struct AAKernelInfoCallSite : AAKernelInfo {
case OMPRTL___kmpc_free_shared:
// Return without setting a fixpoint, to be resolved in updateImpl.
return;
+ case OMPRTL___kmpc_distribute_static_loop_4:
+ case OMPRTL___kmpc_distribute_static_loop_4u:
+ case OMPRTL___kmpc_distribute_static_loop_8:
+ case OMPRTL___kmpc_distribute_static_loop_8u:
+ case OMPRTL___kmpc_distribute_for_static_loop_4:
+ case OMPRTL___kmpc_distribute_for_static_loop_4u:
+ case OMPRTL___kmpc_distribute_for_static_loop_8:
+ case OMPRTL___kmpc_distribute_for_static_loop_8u:
+ case OMPRTL___kmpc_for_static_loop_4:
+ case OMPRTL___kmpc_for_static_loop_4u:
+ case OMPRTL___kmpc_for_static_loop_8:
+ case OMPRTL___kmpc_for_static_loop_8u:
+ // Parallel regions might be reached by these calls, as they take a
+ // callback argument potentially arbitrary user-provided code.
+ ReachedUnknownParallelRegions.insert(&CB);
+ // TODO: The presence of these calls on their own does not prevent a
+ // kernel from being SPMD-izable. We mark it as such because we need
+ // further changes in order to also consider the contents of the
+ // callbacks passed to them.
+ SPMDCompatibilityTracker.indicatePessimisticFixpoint();
+ SPMDCompatibilityTracker.insert(&CB);
+ break;
default:
// Unknown OpenMP runtime calls cannot be executed in SPMD-mode,
// generally. However, they do not hide parallel regions.
diff --git a/offload/test/offloading/fortran/target-generic-loops.f90
b/offload/test/offloading/fortran/target-generic-loops.f90
new file mode 100644
index 0000000000000..07bcbfd2c8752
--- /dev/null
+++ b/offload/test/offloading/fortran/target-generic-loops.f90
@@ -0,0 +1,130 @@
+! Offloading test for generic target regions containing different kinds of
+! loop constructs inside.
+! REQUIRES: flang, amdgpu
+
+! RUN: %libomptarget-compile-fortran-run-and-check-generic
+program main
+ integer :: i1, i2, n1, n2, counter
+
+ n1 = 100
+ n2 = 50
+
+ counter = 0
+ !$omp target map(tofrom:counter)
+ !$omp teams distribute reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ !$omp end target
+
+ ! CHECK: 1 100
+ print '(I2" "I0)', 1, counter
+
+ counter = 0
+ !$omp target map(tofrom:counter)
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ !$omp end target
+
+ ! CHECK: 2 200
+ print '(I2" "I0)', 2, counter
+
+ counter = 0
+ !$omp target map(tofrom:counter)
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ !$omp end target
+
+ ! CHECK: 3 203
+ print '(I2" "I0)', 3, counter
+
+ counter = 0
+ !$omp target map(tofrom: counter)
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ !$omp end target
+
+ ! CHECK: 4 102
+ print '(I2" "I0)', 4, counter
+
+
+ counter = 0
+ !$omp target teams distribute reduction(+:counter)
+ do i1=1, n1
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ end do
+
+ ! CHECK: 5 5000
+ print '(I2" "I0)', 5, counter
+
+ counter = 0
+ !$omp target teams distribute reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ end do
+
+ ! CHECK: 6 5200
+ print '(I2" "I0)', 6, counter
+
+ counter = 0
+ !$omp target teams distribute reduction(+:counter)
+ do i1=1, n1
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ end do
+
+ ! CHECK: 7 10000
+ print '(I2" "I0)', 7, counter
+
+ counter = 0
+ !$omp target teams distribute reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ !$omp parallel do reduction(+:counter)
+ do i2=1, n2
+ counter = counter + 1
+ end do
+ counter = counter + 1
+ end do
+
+ ! CHECK: 8 10300
+ print '(I2" "I0)', 8, counter
+end program
diff --git a/offload/test/offloading/fortran/target-spmd-loops.f90
b/offload/test/offloading/fortran/target-spmd-loops.f90
new file mode 100644
index 0000000000000..7407f0c0768cb
--- /dev/null
+++ b/offload/test/offloading/fortran/target-spmd-loops.f90
@@ -0,0 +1,39 @@
+! Offloading test for generic target regions containing different kinds of
+! loop constructs inside.
+! REQUIRES: flang, amdgpu
+
+! RUN: %libomptarget-compile-fortran-run-and-check-generic
+program main
+ integer :: i1, n1, counter
+
+ n1 = 100
+
+ counter = 0
+ !$omp target parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+
+ ! CHECK: 1 100
+ print '(I2" "I0)', 1, counter
+
+ counter = 0
+ !$omp target map(tofrom:counter)
+ !$omp parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+ !$omp end target
+
+ ! CHECK: 2 100
+ print '(I2" "I0)', 2, counter
+
+ counter = 0
+ !$omp target teams distribute parallel do reduction(+:counter)
+ do i1=1, n1
+ counter = counter + 1
+ end do
+
+ ! CHECK: 3 100
+ print '(I2" "I0)', 3, counter
+end program
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
