[PATCH] D88791: Rename the VECREDUCE_STRICT_{FADD,FMUL} SDNodes to VECREDUCE_SEQ_{FADD,FMUL}.

[Amara Emerson via Phabricator via llvm-commits]

aemerson updated this revision to Diff 296265.
aemerson added a comment.

Oops, brain was still in the fp-typeless GISel world. Fix types to f32/f16.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88791/new/

https://reviews.llvm.org/D88791

Files:
  llvm/include/llvm/CodeGen/ISDOpcodes.h
  llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
  llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp


Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
+++ 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";
Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -8942,7 +8942,7 @@
                         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::experimental_vector_reduce_v2_fmul:
     if (SDFlags.hasAllowReassociation())
@@ -8950,7 +8950,7 @@
                         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::experimental_vector_reduce_add:
     Res = DAG.getNode(ISD::VECREDUCE_ADD, dl, VT, Op1);
Index: llvm/include/llvm/CodeGen/ISDOpcodes.h
===================================================================
--- llvm/include/llvm/CodeGen/ISDOpcodes.h
+++ 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 SRC_VEC[0:1], SRC_VEC[2:3]
+  ///   RES = FADD SRC_VEC[0], SRC_VEC[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.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D88791.296265.patch
Type: text/x-patch
Size: 3673 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201005/d823d618/attachment.bin>