[Mlir-commits] [flang] [llvm] [mlir] [flang] Fix REAL(10)/COMPLEX(10) component sizes in runtime type info (PR #192049)
llvmlistbot at llvm.org
llvmlistbot at llvm.org
Tue Apr 14 05:54:11 PDT 2026
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mlir
Author: Sairudra More (Saieiei)
<details>
<summary>Changes</summary>
This fixes a crash caused by incorrect component sizes in runtime type info.
For REAL(10) and COMPLEX(10) components, `Component::GetElementByteSize()` was using the Fortran kind value as the byte size. On x86-64 that underestimates the actual storage size, so strided componentwise assignment can corrupt adjacent data and crash.
This patch routes REAL and COMPLEX component sizes through `Descriptor::BytesFor()`, which matches the runtime's existing storage-size handling. I also added a regression test covering strided assignment of a SEQUENCE type with REAL(10)/COMPLEX(10) components.
Locally, the original reproducer now passes, the new regression test passes, and `check-flang-rt` / `check-flang` are clean.
This is a narrow runtime-side fix only. It does not change compiler-side type info encoding or the runtime type info ABI.
---
Full diff: https://github.com/llvm/llvm-project/pull/192049.diff
5 Files Affected:
- (modified) flang-rt/lib/runtime/type-info.cpp (+3-2)
- (added) flang-rt/test/Driver/derived-type-real10-assign.f90 (+60)
- (added) flang/test/Integration/OpenMP/taskloop-bounds-cast.f90 (+33)
- (modified) llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp (-2)
- (added) mlir/test/Target/LLVMIR/openmp-taskloop-bounds-cast.mlir (+27)
``````````diff
diff --git a/flang-rt/lib/runtime/type-info.cpp b/flang-rt/lib/runtime/type-info.cpp
index cb8e894bd3922..c5acfad3a98e3 100644
--- a/flang-rt/lib/runtime/type-info.cpp
+++ b/flang-rt/lib/runtime/type-info.cpp
@@ -7,6 +7,7 @@
//===----------------------------------------------------------------------===//
#include "flang-rt/runtime/type-info.h"
+#include "flang-rt/runtime/descriptor.h"
#include "flang-rt/runtime/terminator.h"
#include "flang-rt/runtime/tools.h"
#include <cstdio>
@@ -37,11 +38,11 @@ RT_API_ATTRS std::size_t Component::GetElementByteSize(
switch (category()) {
case TypeCategory::Integer:
case TypeCategory::Unsigned:
- case TypeCategory::Real:
case TypeCategory::Logical:
return kind_;
+ case TypeCategory::Real:
case TypeCategory::Complex:
- return 2 * kind_;
+ return Descriptor::BytesFor(category(), kind_);
case TypeCategory::Character:
if (auto value{characterLen_.GetValue(&instance)}) {
return kind_ * *value;
diff --git a/flang-rt/test/Driver/derived-type-real10-assign.f90 b/flang-rt/test/Driver/derived-type-real10-assign.f90
new file mode 100644
index 0000000000000..d71ea8568f3b0
--- /dev/null
+++ b/flang-rt/test/Driver/derived-type-real10-assign.f90
@@ -0,0 +1,60 @@
+! Test that componentwise assignment of SEQUENCE types with REAL(10) and
+! COMPLEX(10) components copies the correct number of bytes. On x86-64,
+! REAL(10) occupies 16 bytes (not 10) and COMPLEX(10) occupies 32 bytes
+! (not 20). A bug in Component::GetElementByteSize() previously returned
+! the Fortran kind value instead of the actual storage size, corrupting
+! subsequent fields during strided derived-type assignment.
+
+! UNSUPPORTED: system-windows
+! UNSUPPORTED: offload-cuda
+
+! RUN: %flang -L"%libdir" %s -o %t
+! RUN: env LD_LIBRARY_PATH="$LD_LIBRARY_PATH:%libdir" %t | FileCheck %s
+
+! CHECK: PASS
+
+program derived_type_real10_assign
+ implicit none
+
+ type :: seq_t
+ sequence
+ real(10) :: r
+ complex(10) :: z
+ integer :: tag
+ end type
+
+ type(seq_t) :: a(4), b(4)
+ integer :: i
+
+ ! Initialize source array
+ do i = 1, 4
+ a(i)%r = real(i * 100, 10)
+ a(i)%z = cmplx(real(i, 10), real(i * 10, 10))
+ a(i)%tag = i
+ end do
+
+ ! Initialize destination with different values
+ do i = 1, 4
+ b(i)%r = 0.0_10
+ b(i)%z = (0.0_10, 0.0_10)
+ b(i)%tag = 0
+ end do
+
+ ! Strided section assignment — forces componentwise copy in the runtime
+ b(1:3:2) = a(2:4:2)
+
+ ! b(1) should equal a(2), b(3) should equal a(4)
+ ! b(2) and b(4) should remain zero
+ if (b(1)%r /= a(2)%r) stop 1
+ if (b(1)%z /= a(2)%z) stop 2
+ if (b(1)%tag /= a(2)%tag) stop 3
+ if (b(3)%r /= a(4)%r) stop 4
+ if (b(3)%z /= a(4)%z) stop 5
+ if (b(3)%tag /= a(4)%tag) stop 6
+
+ ! Verify untouched elements
+ if (b(2)%tag /= 0) stop 7
+ if (b(4)%tag /= 0) stop 8
+
+ print *, 'PASS'
+end program
diff --git a/flang/test/Integration/OpenMP/taskloop-bounds-cast.f90 b/flang/test/Integration/OpenMP/taskloop-bounds-cast.f90
new file mode 100644
index 0000000000000..9397b98b9ecd6
--- /dev/null
+++ b/flang/test/Integration/OpenMP/taskloop-bounds-cast.f90
@@ -0,0 +1,33 @@
+!===----------------------------------------------------------------------===!
+! This directory can be used to add Integration tests involving multiple
+! stages of the compiler (for eg. from Fortran to LLVM IR). It should not
+! contain executable tests. We should only add tests here sparingly and only
+! if there is no other way to test. Repeat this message in each test that is
+! added to this directory and sub-directories.
+!===----------------------------------------------------------------------===!
+
+! Regression test for an intermittent crash in taskloop LLVM IR codegen.
+! A dead saveIP/restoreIP pair in OpenMPIRBuilder::createTaskloop introduced
+! stale IRBuilder/debug-location state on the restore path before an
+! immediately following SetInsertPoint override. Removing the dead restore
+! avoids that restore path entirely.
+
+! RUN: %flang_fc1 -emit-llvm -fopenmp -o - %s | FileCheck %s
+
+! Verify that the taskloop runtime call is present in the generated LLVM IR
+! and that the i64 bounds casts required by the ABI are emitted.
+
+! CHECK-LABEL: define void @test_taskloop_(
+
+! CHECK: sext i32 {{.*}} to i64
+! CHECK: call void @__kmpc_taskloop(
+
+subroutine test_taskloop(n)
+ integer, intent(in) :: n
+ integer :: i
+
+ !$omp taskloop
+ do i = 1, n
+ end do
+ !$omp end taskloop
+end subroutine test_taskloop
diff --git a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
index 2a0a017fbb0f3..2e73c1791992f 100644
--- a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -2185,7 +2185,6 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
/* Create the casting for the Bounds Values that can be used when outlining
* to replace the uses of the fakes with real values */
BasicBlock *CodeReplBB = StaleCI->getParent();
- IRBuilderBase::InsertPoint CurrentIp = Builder.saveIP();
Builder.SetInsertPoint(CodeReplBB->getFirstInsertionPt());
Value *CastedLBVal =
Builder.CreateIntCast(LBVal, Builder.getInt64Ty(), true, "lb64");
@@ -2193,7 +2192,6 @@ OpenMPIRBuilder::InsertPointOrErrorTy OpenMPIRBuilder::createTaskloop(
Builder.CreateIntCast(UBVal, Builder.getInt64Ty(), true, "ub64");
Value *CastedStepVal =
Builder.CreateIntCast(StepVal, Builder.getInt64Ty(), true, "step64");
- Builder.restoreIP(CurrentIp);
Builder.SetInsertPoint(StaleCI);
diff --git a/mlir/test/Target/LLVMIR/openmp-taskloop-bounds-cast.mlir b/mlir/test/Target/LLVMIR/openmp-taskloop-bounds-cast.mlir
new file mode 100644
index 0000000000000..41121705aa2c1
--- /dev/null
+++ b/mlir/test/Target/LLVMIR/openmp-taskloop-bounds-cast.mlir
@@ -0,0 +1,27 @@
+// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
+
+// Regression test: a dead saveIP/restoreIP pair in
+// OpenMPIRBuilder::createTaskloop PostOutlineCB could introduce stale
+// IRBuilder debug-location state and cause an intermittent crash during
+// finalize(). Removing the dead pair avoids that restore path entirely.
+// Verifies that an i32 loop is lowered correctly with a __kmpc_taskloop call.
+
+omp.private {type = private} @_QPtest_taskloop_boundsEi_private_i32 : i32
+
+llvm.func @_QPtest_taskloop_bounds() {
+ %0 = llvm.mlir.constant(1 : i64) : i64
+ %1 = llvm.alloca %0 x i32 {bindc_name = "i"} : (i64) -> !llvm.ptr
+ %lb = llvm.mlir.constant(1 : i32) : i32
+ %ub = llvm.mlir.constant(10 : i32) : i32
+ %step = llvm.mlir.constant(1 : i32) : i32
+ omp.taskloop private(@_QPtest_taskloop_boundsEi_private_i32 %1 -> %arg0 : !llvm.ptr) {
+ omp.loop_nest (%arg1) : i32 = (%lb) to (%ub) inclusive step (%step) {
+ llvm.store %arg1, %arg0 : i32, !llvm.ptr
+ omp.yield
+ }
+ }
+ llvm.return
+}
+
+// CHECK-LABEL: define void @_QPtest_taskloop_bounds(
+// CHECK: call void @__kmpc_taskloop(
``````````
</details>
https://github.com/llvm/llvm-project/pull/192049
More information about the Mlir-commits
mailing list