triton , Noc, Verilog, Computer Architecture, DataFlow, Tiling, AI inference chips, memory hierarchy, TVM, hardware-software co-design, DMA scheduling, compiler-guided optimization, XLA, VHDL, memory planning, LLVM, kernel optimization, Chisel, MLIR, systemverilog, microarchitectures, AI accelerator architectures, operator mapping, compute arrays, Transformer and LLM workloads, Performance Analysis