================ @@ -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"); ---------------- inclyc wrote:
I recently encountered a miscompilation when the program is relatively large, related to this assertion (not in aarch64 backend). Should we use some if-branch to detect this, and return `SDValue()`? I'm not sure how to construct indexed load directly in IR, perhaps I may make a reproducer from the test suite. https://github.com/llvm/llvm-project/pull/78632 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits