diff --git a/llvm/include/llvm/CodeGen/ISDOpcodes.h b/llvm/include/llvm/CodeGen/ISDOpcodes.h --- a/llvm/include/llvm/CodeGen/ISDOpcodes.h +++ b/llvm/include/llvm/CodeGen/ISDOpcodes.h @@ -1103,12 +1103,25 @@ /// Generic reduction nodes. These nodes represent horizontal vector /// reduction operations, producing a scalar result. - /// The STRICT variants perform reductions in sequential order. The first + /// The SEQ variants perform reductions in sequential order. The first /// operand is an initial scalar accumulator value, and the second operand /// is the vector to reduce. - VECREDUCE_STRICT_FADD, - VECREDUCE_STRICT_FMUL, - /// These reductions are non-strict, and have a single vector operand. + /// E.g. RES = VECREDUCE_SEQ_FADD f32 ACC, <4 x f32> SRC_VEC + /// ... is equivalent to + /// RES = (((ACC + SRC_VEC[0]) + SRC_VEC[1]) + SRC_VEC[2]) + SRC_VEC[3] + VECREDUCE_SEQ_FADD, + VECREDUCE_SEQ_FMUL, + + /// These reductions have relaxed evaluation order semantics, and have a + /// single vector operand. The order of evaluation is unspecified. For + /// pow-of-2 vectors, one valid legalizer expansion is to use a tree + /// reduction, i.e.: + /// For RES = VECREDUCE_FADD <8 x f16> SRC_VEC + /// PART_RDX = FADD SRC_VEC[0:3], SRC_VEC[4:7] + /// PART_RDX2 = FADD PART_RDX[0:1], PART_RDX[2:3] + /// RES = FADD PART_RDX2[0], PART_RDX2[1] + /// For non-pow-2 vectors, this can be computed by extracting each element + /// and performing the operation as if it were scalarized. VECREDUCE_FADD, VECREDUCE_FMUL, /// FMIN/FMAX nodes can have flags, for NaN/NoNaN variants. diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp @@ -8943,7 +8943,7 @@ DAG.getNode(ISD::VECREDUCE_FADD, dl, VT, Op2, SDFlags), SDFlags); else - Res = DAG.getNode(ISD::VECREDUCE_STRICT_FADD, dl, VT, Op1, Op2, SDFlags); + Res = DAG.getNode(ISD::VECREDUCE_SEQ_FADD, dl, VT, Op1, Op2, SDFlags); break; case Intrinsic::vector_reduce_fmul: if (SDFlags.hasAllowReassociation()) @@ -8951,7 +8951,7 @@ DAG.getNode(ISD::VECREDUCE_FMUL, dl, VT, Op2, SDFlags), SDFlags); else - Res = DAG.getNode(ISD::VECREDUCE_STRICT_FMUL, dl, VT, Op1, Op2, SDFlags); + Res = DAG.getNode(ISD::VECREDUCE_SEQ_FMUL, dl, VT, Op1, Op2, SDFlags); break; case Intrinsic::vector_reduce_add: Res = DAG.getNode(ISD::VECREDUCE_ADD, dl, VT, Op1); diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp @@ -450,9 +450,9 @@ case ISD::SETFALSE2: return "setfalse2"; } case ISD::VECREDUCE_FADD: return "vecreduce_fadd"; - case ISD::VECREDUCE_STRICT_FADD: return "vecreduce_strict_fadd"; + case ISD::VECREDUCE_SEQ_FADD: return "vecreduce_seq_fadd"; case ISD::VECREDUCE_FMUL: return "vecreduce_fmul"; - case ISD::VECREDUCE_STRICT_FMUL: return "vecreduce_strict_fmul"; + case ISD::VECREDUCE_SEQ_FMUL: return "vecreduce_seq_fmul"; case ISD::VECREDUCE_ADD: return "vecreduce_add"; case ISD::VECREDUCE_MUL: return "vecreduce_mul"; case ISD::VECREDUCE_AND: return "vecreduce_and";