[HashRecognize] Introduce new analysis

Introduce a fresh analysis for recognizing polynomial hashes, with the
rationale that several targets have specific instructions to optimize
things like CRC and GHASH (eg. X86 and RISC-V crypto extension). We
limit the scope to polynomial hashes computed in a Galois field of
characteristic 2, since this class of operations can also be optimized
in the absence of target-specific instructions to use a lookup table.

At the moment, we only recognize the CRC algorithm.

Author: artagnon

llvm/include/llvm/Analysis/HashRecognize.h

@@ -0,0 +1,89 @@
+//===- HashRecognize.h ------------------------------------------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Interface for the HashRecognize analysis, which identifies hash functions
+// that can be optimized using a lookup-table or with target-specific
+// instructions.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_HASHRECOGNIZE_H
+#define LLVM_ANALYSIS_HASHRECOGNIZE_H
+
+#include "llvm/ADT/APInt.h"
+#include "llvm/Analysis/LoopAnalysisManager.h"
+#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/IR/Value.h"
+#include "llvm/Support/KnownBits.h"
+#include "llvm/Transforms/Scalar/LoopPassManager.h"
+
+namespace llvm {
+/// A tuple of bits that are expected to be zero, number N of them expected to
+/// be zero, with a boolean indicating whether it's the top or bottom N bits
+/// expected to be zero.
+using ErrBits = std::tuple<KnownBits, unsigned, bool>;
+
+/// A custom std::array with 256 entries, that also has a print function.
+struct CRCTable : public std::array<APInt, 256> {
+  void print(raw_ostream &OS) const;
+};
+
+/// The structure that is returned when a polynomial algorithm was recognized by
+/// the analysis. Currently, only the CRC algorithm is recognized.
+struct PolynomialInfo {
+  unsigned TripCount;
+  const Value *LHS;
+  APInt RHS;
+  const Value *ComputedValue;
+  bool ByteOrderSwapped;
+  const Value *LHSAux;
+  PolynomialInfo(unsigned TripCount, const Value *LHS, const APInt &RHS,
+                 const Value *ComputedValue, bool ByteOrderSwapped,
+                 const Value *LHSAux = nullptr);
+};
+
+/// The analysis.
+class HashRecognize {
+  const Loop &L;
+  ScalarEvolution &SE;
+
+public:
+  HashRecognize(const Loop &L, ScalarEvolution &SE);
+
+  // The main analysis entry point.
+  std::variant<PolynomialInfo, ErrBits, StringRef> recognizeCRC() const;
+
+  // Auxilary entry point after analysis to interleave the generating polynomial
+  // and return a 256-entry CRC table.
+  CRCTable genSarwateTable(const APInt &GenPoly, bool ByteOrderSwapped) const;
+
+  void print(raw_ostream &OS) const;
+};
+
+class HashRecognizePrinterPass
+    : public PassInfoMixin<HashRecognizePrinterPass> {
+  raw_ostream &OS;
+
+public:
+  explicit HashRecognizePrinterPass(raw_ostream &OS) : OS(OS) {}
+  PreservedAnalyses run(Loop &L, LoopAnalysisManager &AM,
+                        LoopStandardAnalysisResults &AR, LPMUpdater &);
+};
+
+class HashRecognizeAnalysis : public AnalysisInfoMixin<HashRecognizeAnalysis> {
+  friend AnalysisInfoMixin<HashRecognizeAnalysis>;
+  static AnalysisKey Key;
+
+public:
+  using Result = HashRecognize;
+  Result run(Loop &L, LoopAnalysisManager &AM, LoopStandardAnalysisResults &AR);
+};
+} // namespace llvm
+
+#endif

llvm/lib/Analysis/CMakeLists.txt

@@ -77,6 +77,7 @@ add_llvm_component_library(LLVMAnalysis
   FunctionPropertiesAnalysis.cpp
   GlobalsModRef.cpp
   GuardUtils.cpp
+  HashRecognize.cpp
   HeatUtils.cpp
   IRSimilarityIdentifier.cpp
   IVDescriptors.cpp