[Openmp-commits] [libc] [clang] [compiler-rt] [libcxxabi] [clang-tools-extra] [flang] [libcxx] [openmp] [llvm] [mlir] [AArch64] Add custom lowering for load <3 x i8>. (PR #78632)

Tim Northover via Openmp-commits openmp-commits at lists.llvm.org
Mon Jan 29 07:09:10 PST 2024


================
@@ -21248,6 +21297,51 @@ static SDValue foldTruncStoreOfExt(SelectionDAG &DAG, SDNode *N) {
   return SDValue();
 }
 
+// A custom combine to lower load <3 x i8> as the more efficient sequence
+// below:
+//    ldrb wX, [x0, #2]
+//    ldrh wY, [x0]
+//    orr wX, wY, wX, lsl #16
+//    fmov s0, wX
+//
+static SDValue combineV3I8LoadExt(LoadSDNode *LD, SelectionDAG &DAG) {
+  EVT MemVT = LD->getMemoryVT();
+  if (MemVT != EVT::getVectorVT(*DAG.getContext(), MVT::i8, 3) ||
+      LD->getOriginalAlign() >= 4)
+    return SDValue();
+
+  SDLoc DL(LD);
+  MachineFunction &MF = DAG.getMachineFunction();
+  SDValue Chain = LD->getChain();
+  SDValue BasePtr = LD->getBasePtr();
+  MachineMemOperand *MMO = LD->getMemOperand();
+  assert(LD->getOffset().isUndef() && "undef offset expected");
+
+  // Load 2 x i8, then 1 x i8.
+  SDValue L16 = DAG.getLoad(MVT::i16, DL, Chain, BasePtr,
+                            MF.getMachineMemOperand(MMO, 0, 2));
+  TypeSize Offset2 = TypeSize::getFixed(2);
+  SDValue L8 = DAG.getLoad(MVT::i8, DL, Chain,
+                           DAG.getMemBasePlusOffset(BasePtr, Offset2, DL),
+                           MF.getMachineMemOperand(MMO, 2, 1));
+
+  SDValue Ins16 = DAG.getNode(ISD::SPLAT_VECTOR, DL, MVT::v4i16, L16);
+
+  SDValue Cast = DAG.getNode(ISD::BITCAST, DL, MVT::v8i8, Ins16);
+
+  SDValue Ext8 = DAG.getNode(ISD::ZERO_EXTEND, DL, MVT::i32, L8);
+  SDValue Trunc8 = DAG.getNode(ISD::TRUNCATE, DL, MVT::i8, Ext8);
----------------
TNorthover wrote:

What are these two doing? They ought to amount to a nop.

https://github.com/llvm/llvm-project/pull/78632


More information about the Openmp-commits mailing list