[llvm] [LoopIdiom] Add a range attribute to formed memset/memcpy/memmove (PR #226801)

[Kuba Mracek via llvm-commits]

================
@@ -1092,6 +1092,51 @@ static const SCEV *getNumBytes(const SCEV *BECount, Type *IntPtr,
                         SCEV::FlagNUW);
 }
 
+/// Add a range to newly formed memset/memmove/memcpy intrinsic with an upper
+/// bound derived from the loop's constant max trip count.
+static void addRangeAttrFromTripCount(CallInst *NewCall, unsigned ArgNo,
+                                      uint64_t ElemsPerIter,
+                                      const SCEV *BECount, Loop *L,
+                                      ScalarEvolution *SE) {
+  Value *Len = NewCall->getArgOperand(ArgNo);
+  if (isa<Constant>(Len))
+    return;
+
+  // Two upper bounds:
+  // (1) constant max backedge-taken count
+  const APInt *Max1;
+  if (!match(SE->getConstantMaxBackedgeTakenCount(L), m_scev_APInt(Max1)))
+    return;
+
+  // (2) loop guards (new call is in preheader, so guards dominate the call)
+  APInt Max2 = SE->getUnsignedRangeMax(SE->applyLoopGuards(BECount, L));
+
+  // Use the tighter bound
+  unsigned MaxWidth = std::max(Max1->getBitWidth(), Max2.getBitWidth());
+  APInt MaxBTC = APIntOps::umin(Max1->zext(MaxWidth), Max2.zext(MaxWidth));
+
+  // The length is in [0, (MaxBTC + 1) * ElemsPerIter]. Bail if that doesn't
+  // fit in the length's type.
+  unsigned BW = Len->getType()->getIntegerBitWidth();
+  if (MaxBTC.getActiveBits() > BW)
+    return;
+  bool Overflow;
+  APInt MaxTripCount = MaxBTC.zextOrTrunc(BW).uadd_ov(APInt(BW, 1), Overflow);
+  if (Overflow)
+    return;
+  APInt MaxLen = MaxTripCount.umul_ov(APInt(BW, ElemsPerIter), Overflow);
+  if (Overflow)
+    return;
+  // ConstantRange's upper end is exclusive, so the range ends at MaxLen + 1.
+  APInt RangeEnd = MaxLen.uadd_ov(APInt(BW, 1), Overflow);
+  if (Overflow)
+    return;
----------------
kubamracek wrote:

TIL!

https://github.com/llvm/llvm-project/pull/226801