insertpoint fix

Author: harishch4

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

@@ -5206,10 +5206,11 @@ void OpenMPIRBuilder::applySimd(CanonicalLoopInfo *CanonicalLoop,
   Loop *L = LI.getLoopFor(CanonicalLoop->getHeader());
   if (AlignedVars.size()) {
     InsertPointTy IP = Builder.saveIP();
-    Builder.SetInsertPoint(CanonicalLoop->getPreheader()->getTerminator());
     for (auto &AlignedItem : AlignedVars) {
       Value *AlignedPtr = AlignedItem.first;
       Value *Alignment = AlignedItem.second;
+      Instruction *loadInst = dyn_cast<Instruction>(AlignedPtr);
+      Builder.SetInsertPoint(loadInst->getNextNode());
       Builder.CreateAlignmentAssumption(F->getDataLayout(),
                                         AlignedPtr, Alignment);
     }

mlir/test/Target/LLVMIR/openmp-simd-aligned.mlir

@@ -3,7 +3,6 @@
 //CHECK-LABEL: define void @_QPsimd_aligned_pointer() {
 //CHECK:   %[[A_PTR:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8 }, i64 1, align 8
 //CHECK:   %[[A_VAL:.*]] = load ptr, ptr %[[A_PTR]], align 8
-//CHECK: omp_loop.preheader:                               ; preds = %0
 //CHECK:   call void @llvm.assume(i1 true) [ "align"(ptr %[[A_VAL]], i64 256) ]
 llvm.func @_QPsimd_aligned_pointer() {
   %1 = llvm.mlir.constant(1 : i64) : i64
@@ -17,14 +16,14 @@ llvm.func @_QPsimd_aligned_pointer() {
       llvm.store %arg0, %3 : i32, !llvm.ptr
       omp.yield
     }
+    omp.terminator
   }
   llvm.return
 }
 
 //CHECK-LABEL: define void @_QPsimd_aligned_cptr() {
 //CHECK:   %[[A_CPTR:.*]] = alloca %_QM__fortran_builtinsT__builtin_c_ptr, i64 1, align 8
 //CHECK:   %[[A_VAL:.*]] = load ptr, ptr %[[A_CPTR]], align 8
-//CHECK: omp_loop.preheader:                               ; preds = %0
 //CHECK:   call void @llvm.assume(i1 true) [ "align"(ptr %[[A_VAL]], i64 256) ]
 llvm.func @_QPsimd_aligned_cptr() {
   %0 = llvm.mlir.constant(1 : i64) : i64
@@ -39,14 +38,14 @@ llvm.func @_QPsimd_aligned_cptr() {
       llvm.store %arg0, %3 : i32, !llvm.ptr
       omp.yield
     }
+    omp.terminator
   }
   llvm.return
 }
 
 //CHECK-LABEL: define void @_QPsimd_aligned_allocatable() {
 //CHECK:   %[[A_ADDR:.*]] = alloca { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }, i64 1, align 8
 //CHECK:   %[[A_VAL:.*]] = load ptr, ptr %[[A_ADDR]], align 8
-//CHECK: omp_loop.preheader:                               ; preds = %0
 //CHECK:   call void @llvm.assume(i1 true) [ "align"(ptr %[[A_VAL]], i64 256) ]
 llvm.func @_QPsimd_aligned_allocatable() {
   %0 = llvm.mlir.constant(1 : i64) : i64
@@ -58,6 +57,7 @@ llvm.func @_QPsimd_aligned_allocatable() {
     omp.loop_nest (%arg0) : i32 = (%2) to (%3) inclusive step (%4) {
       omp.yield
     }
+    omp.terminator
   }
   llvm.return
 }