[llvm] [PreISelIntrinsicLowering] Produce a memset_pattern16 libcall for llvm.experimental.memset.pattern when available (PR #120420)

[Alex Bradbury via llvm-commits]

================
@@ -322,7 +376,41 @@ bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
     }
     case Intrinsic::experimental_memset_pattern: {
       auto *Memset = cast<MemSetPatternInst>(Inst);
-      expandMemSetPatternAsLoop(Memset);
+      const TargetLibraryInfo &TLI = LookupTLI(*Memset->getFunction());
+      if (Constant *PatternValue = getMemSetPattern16Value(Memset, TLI)) {
+        // FIXME: There is currently no profitability calculation for emitting
+        // the libcall vs expanding the memset.pattern directly.
+        IRBuilder<> Builder(Inst);
+        Module *M = Memset->getModule();
+        const DataLayout &DL = Memset->getDataLayout();
+
+        StringRef FuncName = "memset_pattern16";
+        FunctionCallee MSP = getOrInsertLibFunc(
+            M, TLI, LibFunc_memset_pattern16, Builder.getVoidTy(),
+            Memset->getRawDest()->getType(), Builder.getPtrTy(),
+            Memset->getLength()->getType());
+        inferNonMandatoryLibFuncAttrs(M, FuncName, TLI);
+
+        // Otherwise we should form a memset_pattern16.  PatternValue is known
+        // to be an constant array of 16-bytes. Put the value into a mergable
+        // global.
+        GlobalVariable *GV = new GlobalVariable(
+            *M, PatternValue->getType(), true, GlobalValue::PrivateLinkage,
+            PatternValue, ".memset_pattern");
+        GV->setUnnamedAddr(
+            GlobalValue::UnnamedAddr::Global); // Ok to merge these.
+        GV->setAlignment(Align(16));
+        Value *PatternPtr = GV;
+        Value *NumBytes = Builder.CreateMul(
+            Builder.getInt64(
+                DL.getTypeSizeInBits(Memset->getValue()->getType()) / 8),
+            Memset->getLength());
+        CallInst *MemsetPattern16Call = Builder.CreateCall(
+            MSP, {Memset->getRawDest(), PatternPtr, NumBytes});
----------------
asb wrote:

I think copying the attributes for the first parameter (the destination ptr) should be find, and good point that we'll lose the alignment right now. But for the second argument we're going from an integer value argument containing the pattern to a pointer to a 16-byte pattern.

https://github.com/llvm/llvm-project/pull/120420