[llvm] [TableGen][DecoderEmitter] Rework table construction/emission (PR #155889)

[Sergei Barannikov via llvm-commits]

================
@@ -0,0 +1,342 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "DecoderTableEmitter.h"
+#include "Common/CodeGenInstruction.h"
+#include "Common/InstructionEncoding.h"
+#include "llvm/Support/Format.h"
+#include "llvm/Support/LEB128.h"
+
+using namespace llvm;
+
+void DecoderTableEmitter::analyzeNode(const DecoderTreeNode *Node) const {
+  switch (Node->getKind()) {
+  case DecoderTreeNode::CheckAny: {
+    const auto *N = static_cast<const CheckAnyNode *>(Node);
+    for (const DecoderTreeNode *Child : N->children())
+      analyzeNode(Child);
+    break;
+  }
+  case DecoderTreeNode::CheckAll: {
+    const auto *N = static_cast<const CheckAllNode *>(Node);
+    for (const DecoderTreeNode *Child : N->children())
+      analyzeNode(Child);
+    break;
+  }
+  case DecoderTreeNode::CheckField:
+    break;
+  case DecoderTreeNode::SwitchField: {
+    const auto *N = static_cast<const SwitchFieldNode *>(Node);
+    for (const DecoderTreeNode *Child : make_second_range(N->cases()))
+      analyzeNode(Child);
+    break;
+  }
+  case DecoderTreeNode::CheckPredicate: {
+    const auto *N = static_cast<const CheckPredicateNode *>(Node);
+    TableInfo.insertPredicate(N->getPredicateString());
+    break;
+  }
+  case DecoderTreeNode::SoftFail:
+    break;
+  case DecoderTreeNode::Decode: {
+    const auto *N = static_cast<const DecodeNode *>(Node);
+    TableInfo.insertDecoder(N->getDecoderString());
+    break;
+  }
+  }
+}
+
+unsigned
+DecoderTableEmitter::computeNodeSize(const DecoderTreeNode *Node) const {
+  // To make the arithmetic below clearer.
+  static constexpr unsigned OpcodeSize = 1;
+  static constexpr unsigned FieldWidthSize = 1;
+
+  switch (Node->getKind()) {
+  case DecoderTreeNode::CheckAny: {
+    const auto *N = static_cast<const CheckAnyNode *>(Node);
+    // Pretend the node was optimized. See the comment in emitCheckAnyNode.
+    if (range_size(N->children()) == 1)
+      return computeNodeSize(*N->child_begin());
+    unsigned Size = 0;
+    // All children except the last one are preceded by OPC_Scope opcode and
+    // the size of the child.
+    for (const DecoderTreeNode *Child : drop_end(N->children())) {
+      unsigned ChildSize = computeNodeSize(Child);
+      Size += OpcodeSize + getULEB128Size(ChildSize) + ChildSize;
+    }
+    const DecoderTreeNode *Child = *std::prev(N->child_end());
+    return Size + computeNodeSize(Child);
+  }
+  case DecoderTreeNode::CheckAll: {
+    const auto *N = static_cast<const CheckAllNode *>(Node);
+    unsigned Size = 0;
+    for (const DecoderTreeNode *Child : N->children())
+      Size += computeNodeSize(Child);
+    return Size;
+  }
+  case DecoderTreeNode::CheckField: {
+    const auto *N = static_cast<const CheckFieldNode *>(Node);
+    return OpcodeSize + getULEB128Size(N->getStartBit()) + FieldWidthSize +
+           getULEB128Size(N->getValue());
+  }
+  case DecoderTreeNode::SwitchField: {
+    const auto *N = static_cast<const SwitchFieldNode *>(Node);
+    unsigned Size =
+        OpcodeSize + getULEB128Size(N->getStartBit()) + FieldWidthSize;
+
+    for (auto [Val, Child] : drop_end(N->cases())) {
+      unsigned ChildSize = computeNodeSize(Child);
+      Size += getULEB128Size(Val) + getULEB128Size(ChildSize) + ChildSize;
+    }
+
+    auto [Val, Child] = *std::prev(N->case_end());
+    unsigned ChildSize = computeNodeSize(Child);
+    Size += getULEB128Size(Val) + getULEB128Size(0) + ChildSize;
+    return Size;
+  }
+  case DecoderTreeNode::CheckPredicate: {
+    const auto *N = static_cast<const CheckPredicateNode *>(Node);
+    unsigned PredicateIndex =
+        TableInfo.getPredicateIndex(N->getPredicateString());
+    return OpcodeSize + getULEB128Size(PredicateIndex);
+  }
+  case DecoderTreeNode::SoftFail: {
+    const auto *N = static_cast<const SoftFailNode *>(Node);
+    return OpcodeSize + getULEB128Size(N->getPositiveMask()) +
+           getULEB128Size(N->getNegativeMask());
+  }
+  case DecoderTreeNode::Decode: {
+    const auto *N = static_cast<const DecodeNode *>(Node);
+    unsigned InstOpcode = N->getEncoding().getInstruction()->EnumVal;
+    unsigned DecoderIndex = TableInfo.getDecoderIndex(N->getDecoderString());
+    return OpcodeSize + getULEB128Size(InstOpcode) +
+           getULEB128Size(DecoderIndex);
+  }
+  }
+  llvm_unreachable("Unknown node kind");
+}
+
+unsigned DecoderTableEmitter::computeTableSize(const DecoderTreeNode *Root,
+                                               unsigned BitWidth) const {
+  unsigned Size = 0;
+  if (BitWidth)
+    Size += getULEB128Size(BitWidth);
+  Size += computeNodeSize(Root);
+  return Size;
+}
+
+void DecoderTableEmitter::emitStartLine() {
+  CommentIndex = CurrentIndex;
+  OS.indent(2);
+}
+
+void DecoderTableEmitter::emitOpcode(StringRef Name) {
+  emitStartLine();
+  OS << Name << ", ";
+  ++CurrentIndex;
+}
+
+void DecoderTableEmitter::emitByte(uint8_t Val) {
+  OS << static_cast<unsigned>(Val) << ", ";
+  ++CurrentIndex;
+}
+
+void DecoderTableEmitter::emitUInt8(unsigned Val) {
+  assert(isUInt<8>(Val));
+  emitByte(Val);
+}
+
+void DecoderTableEmitter::emitULEB128(uint64_t Val) {
+  while (Val >= 0x80) {
+    emitByte((Val & 0x7F) | 0x80);
+    Val >>= 7;
+  }
+  emitByte(Val);
+}
+
+formatted_raw_ostream &DecoderTableEmitter::emitComment(indent Indent) {
+  constexpr unsigned CommentColumn = 45;
+  if (OS.getColumn() > CommentColumn)
+    OS << '\n';
+  OS.PadToColumn(CommentColumn);
+  OS << "// " << format_decimal(CommentIndex, IndexWidth) << ": " << Indent;
+  return OS;
+}
+
+void DecoderTableEmitter::emitCheckAnyNode(const CheckAnyNode *N,
+                                           indent Indent) {
+  // TODO: Single-child CheckAny node should be optimized out. For now,
+  //   pretend this is the case and print the single child unindented.
+  if (range_size(N->children()) == 1) {
+    emitNode(*N->child_begin(), Indent);
+    return;
+  }
+
+  for (const DecoderTreeNode *Child : drop_end(N->children())) {
+    emitOpcode("OPC_Scope");
+    emitULEB128(computeNodeSize(Child));
+
+    emitComment(Indent) << "{\n";
+    emitNode(Child, Indent + 1);
+    emitComment(Indent) << "}\n";
+  }
+
+  const DecoderTreeNode *Child = *std::prev(N->child_end());
+  emitComment(Indent) << "{\n";
+  emitNode(Child, Indent + 1);
+  emitComment(Indent) << "}\n";
+}
+
+void DecoderTableEmitter::emitCheckAllNode(const CheckAllNode *N,
+                                           indent Indent) {
+  for (const DecoderTreeNode *Child : N->children())
----------------
s-barannikov wrote:

:)

https://github.com/llvm/llvm-project/pull/155889