[llvm] [LoopIdiomRecognize] Enable clmul optimization for CRC loops (PR #203405)

[Ramkumar Ramachandra via llvm-commits]

================
@@ -1549,7 +1552,151 @@ bool LoopIdiomRecognize::avoidLIRForMultiBlockLoop(bool IsMemset,
   return false;
 }
 
-bool LoopIdiomRecognize::optimizeCRCLoop(const PolynomialInfo &Info) {
+bool LoopIdiomRecognize::optimizeCRCLoopToClmul(const PolynomialInfo &Info) {
+  Type *CRCTy = Info.LHS->getType();
+  LLVMContext &Ctx = CRCTy->getContext();
+  unsigned CRCBW = CRCTy->getIntegerBitWidth();
+  // The TripCount determines how many bits of data are processed, regardless of
+  // whether the actual data bit width matches (if auxiliary data is even used
+  // at all).
+  unsigned TC = Info.TripCount;
+  // The first clmul uses 2*TC bits, and the second clmul uses CRCBW+TC bits.
+  // For simplicity, have both operate on the same bit width.
+  unsigned ClmulBW = std::max(2 * TC, CRCBW + TC);
+  Type *ClmulTy = IntegerType::get(Ctx, ClmulBW);
+
+  // This optimization should only be applied if clmul for the required width is
+  // a fast operation on the target.
+  // TODO: If TC > CRCBW, then the data could probably be split into multiple
+  // chunks and processed in a loop.
+  if (!TTI->haveFastClmul(ClmulTy))
+    return false;
+
+  // First, generate the constants required for GF(2) Barrett reduction.
+  CRCBarrettConstants Constants =
+      HashRecognize::genBarrettConstants(Info.RHS, TC, Info.ByteOrderSwapped);
+  Value *Mu = ConstantInt::get(Ctx, Constants.Mu.zext(ClmulBW));
+  Value *FullGenPoly =
+      ConstantInt::get(Ctx, Constants.FullGenPoly.zext(ClmulBW));
----------------
artagnon wrote:

Ah, never mind then. My thinko.

https://github.com/llvm/llvm-project/pull/203405