Revert "[mlir][OpenMP] implement SIMD reduction (llvm#146671)"

This reverts commit 16b75c8.

breaks:

 hpc2021: 519.clvleaf_t,

 accel2023: 450.md, 453.clvrleaf,

 smoke-fort: flang-nestred

Author: ronlieb

mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp

@@ -234,7 +234,7 @@ static LogicalResult checkImplementationStatus(Operation &op) {
     }
   };
   auto checkReduction = [&todo](auto op, LogicalResult &result) {
-    if (isa<omp::TeamsOp>(op))
+    if (isa<omp::TeamsOp>(op) || isa<omp::SimdOp>(op))
       if (!op.getReductionVars().empty() || op.getReductionByref() ||
           op.getReductionSyms())
         result = todo("reduction");
@@ -2704,17 +2704,6 @@ convertOmpSimd(Operation &opInst, llvm::IRBuilderBase &builder,
 
   PrivateVarsInfo privateVarsInfo(simdOp);
 
-  MutableArrayRef<BlockArgument> reductionArgs =
-      cast<omp::BlockArgOpenMPOpInterface>(opInst).getReductionBlockArgs();
-  DenseMap<Value, llvm::Value *> reductionVariableMap;
-  SmallVector<llvm::Value *> privateReductionVariables(
-      simdOp.getNumReductionVars());
-  SmallVector<DeferredStore> deferredStores;
-  SmallVector<omp::DeclareReductionOp> reductionDecls;
-  collectReductionDecls(simdOp, reductionDecls);
-  llvm::ArrayRef<bool> isByRef = getIsByRef(simdOp.getReductionByref());
-  assert(isByRef.size() == simdOp.getNumReductionVars());
-
   llvm::OpenMPIRBuilder::InsertPointTy allocaIP =
       findAllocaInsertPoint(builder, moduleTranslation);
 
@@ -2723,27 +2712,11 @@ convertOmpSimd(Operation &opInst, llvm::IRBuilderBase &builder,
   if (handleError(afterAllocas, opInst).failed())
     return failure();
 
-  if (failed(allocReductionVars(simdOp, reductionArgs, builder,
-                                moduleTranslation, allocaIP, reductionDecls,
-                                privateReductionVariables, reductionVariableMap,
-                                deferredStores, isByRef)))
-    return failure();
-
   if (handleError(initPrivateVars(builder, moduleTranslation, privateVarsInfo),
                   opInst)
           .failed())
     return failure();
 
-  // TODO: no call to copyFirstPrivateVars?
-
-  assert(afterAllocas.get()->getSinglePredecessor());
-  if (failed(initReductionVars(simdOp, reductionArgs, builder,
-                               moduleTranslation,
-                               afterAllocas.get()->getSinglePredecessor(),
-                               reductionDecls, privateReductionVariables,
-                               reductionVariableMap, isByRef, deferredStores)))
-    return failure();
-
   llvm::ConstantInt *simdlen = nullptr;
   if (std::optional<uint64_t> simdlenVar = simdOp.getSimdlen())
     simdlen = builder.getInt64(simdlenVar.value());
@@ -2788,50 +2761,6 @@ convertOmpSimd(Operation &opInst, llvm::IRBuilderBase &builder,
                             : nullptr,
                         order, simdlen, safelen);
 
-  // We now need to reduce the per-simd-lane reduction variable into the
-  // original variable. This works a bit differently to other reductions (e.g.
-  // wsloop) because we don't need to call into the OpenMP runtime to handle
-  // threads: everything happened in this one thread.
-  for (auto [i, tuple] : llvm::enumerate(
-           llvm::zip(reductionDecls, isByRef, simdOp.getReductionVars(),
-                     privateReductionVariables))) {
-    auto [decl, byRef, reductionVar, privateReductionVar] = tuple;
-
-    OwningReductionGen gen = makeReductionGen(decl, builder, moduleTranslation);
-    llvm::Value *originalVariable = moduleTranslation.lookupValue(reductionVar);
-    llvm::Type *reductionType = moduleTranslation.convertType(decl.getType());
-
-    // We have one less load for by-ref case because that load is now inside of
-    // the reduction region.
-    llvm::Value *redValue = originalVariable;
-    if (!byRef)
-      redValue =
-          builder.CreateLoad(reductionType, redValue, "red.value." + Twine(i));
-    llvm::Value *privateRedValue = builder.CreateLoad(
-        reductionType, privateReductionVar, "red.private.value." + Twine(i));
-    llvm::Value *reduced;
-
-    auto res = gen(builder.saveIP(), redValue, privateRedValue, reduced);
-    if (failed(handleError(res, opInst)))
-      return failure();
-    builder.restoreIP(res.get());
-
-    // For by-ref case, the store is inside of the reduction region.
-    if (!byRef)
-      builder.CreateStore(reduced, originalVariable);
-  }
-
-  // After the construct, deallocate private reduction variables.
-  SmallVector<Region *> reductionRegions;
-  llvm::transform(reductionDecls, std::back_inserter(reductionRegions),
-                  [](omp::DeclareReductionOp reductionDecl) {
-                    return &reductionDecl.getCleanupRegion();
-                  });
-  if (failed(inlineOmpRegionCleanup(reductionRegions, privateReductionVariables,
-                                    moduleTranslation, builder,
-                                    "omp.reduction.cleanup")))
-    return failure();
-
   return cleanupPrivateVars(builder, moduleTranslation, simdOp.getLoc(),
                             privateVarsInfo.llvmVars,
                             privateVarsInfo.privatizers);

mlir/test/Target/LLVMIR/openmp-simd-reduction-byref.mlir

@@ -1,4 +1,5 @@
 // RUN: mlir-translate -mlir-to-llvmir -split-input-file -verify-diagnostics %s
+// XFAIL: *
 
 llvm.func @atomic_hint(%v : !llvm.ptr, %x : !llvm.ptr, %expr : i32) {
   // expected-warning@below {{hint clause discarded}}
@@ -140,6 +141,36 @@ llvm.func @simd_linear(%lb : i32, %ub : i32, %step : i32, %x : !llvm.ptr) {
 
 // -----
 
+omp.declare_reduction @add_f32 : f32
+init {
+^bb0(%arg: f32):
+  %0 = llvm.mlir.constant(0.0 : f32) : f32
+  omp.yield (%0 : f32)
+}
+combiner {
+^bb1(%arg0: f32, %arg1: f32):
+  %1 = llvm.fadd %arg0, %arg1 : f32
+  omp.yield (%1 : f32)
+}
+atomic {
+^bb2(%arg2: !llvm.ptr, %arg3: !llvm.ptr):
+  %2 = llvm.load %arg3 : !llvm.ptr -> f32
+  llvm.atomicrmw fadd %arg2, %2 monotonic : !llvm.ptr, f32
+  omp.yield
+}
+llvm.func @simd_reduction(%lb : i32, %ub : i32, %step : i32, %x : !llvm.ptr) {
+  // expected-error@below {{not yet implemented: Unhandled clause reduction in omp.simd operation}}
+  // expected-error@below {{LLVM Translation failed for operation: omp.simd}}
+  omp.simd reduction(@add_f32 %x -> %prv : !llvm.ptr) {
+    omp.loop_nest (%iv) : i32 = (%lb) to (%ub) step (%step) {
+      omp.yield
+    }
+  }
+  llvm.return
+}
+
+// -----
+
 omp.declare_reduction @add_f32 : f32
 init {
 ^bb0(%arg: f32):