direction: right

pe: PE {
  style.fill: "#f8f9fa"
  style.stroke: "#495057"
  style.border-radius: 8

  cpu: PE_CPU (control) {
    style.fill: "#bbdefb"
    style.stroke: "#1565c0"
    style.border-radius: 4
  }

  sched: PE_SCHED (dispatch) {
    style.fill: "#bbdefb"
    style.stroke: "#1565c0"
    style.border-radius: 4
  }

  ipcq_added: IPCQ (added) {
    style.fill: "#e1f5fe"
    style.stroke: "#0277bd"
    style.stroke-dash: 5
    style.stroke-width: 2
    style.border-radius: 6

    ipcq: PE_IPCQ (control plane) {
      style.fill: "#bbdefb"
      style.stroke: "#1565c0"
      style.border-radius: 4
    }
  }

  dma: PE_DMA (single FIFO inbox) {
    style.fill: "#fff3e0"
    style.stroke: "#e65100"
    style.border-radius: 6
  }

  fs: PE_FETCH_STORE {
    style.fill: "#c8e6c9"
    style.stroke: "#2e7d32"
    style.border-radius: 4
  }

  tcm: TCM (16MB SRAM) {
    style.fill: "#fce4ec"
    style.stroke: "#c62828"
    style.border-radius: 6

    ipcq_slot: IPCQ Slot Region {
      style.stroke-dash: 5
      style.fill: "#ffcdd2"
      style.stroke: "#c62828"
      style.border-radius: 3
    }
  }

  gemm: GEMM engine {
    style.fill: "#c8e6c9"
    style.stroke: "#2e7d32"
    style.border-radius: 4
  }

  math: MATH engine {
    style.fill: "#c8e6c9"
    style.stroke: "#2e7d32"
    style.border-radius: 4
  }

  fport: Fabric Port {
    style.fill: "#ffe0b2"
    style.stroke: "#e65100"
    style.border-radius: 4
  }

  # Control → dispatch
  cpu -> sched: cmd dispatch
  cpu -> ipcq_added.ipcq: IpcqRequest

  # Compute pipeline
  sched -> dma: TileToken\n(compute port)
  dma -> fs: TileToken
  dma <-> tcm: DMA_READ/WRITE\n(HBM ↔ TCM)
  fs <-> tcm: fetch/store\n(TCM ↔ reg)
  fs -> gemm: TileToken
  fs -> math: TileToken
  gemm -> fs: TileToken
  math -> fs: TileToken

  # IPCQ data path — outbound
  ipcq_added.ipcq -> dma: IpcqDmaToken\n(IPCQ port) {style.stroke: "#1565c0"}

  # IPCQ data path — inbound (MetaArrival: DMA → IPCQ)
  dma -> ipcq_added.ipcq: IpcqMetaArrival {style.stroke: "#1565c0"}

  # Credit return (dashed)
  ipcq_added.ipcq -> dma: IpcqCreditMetadata\n(NoC latency charged) {
    style.stroke: "#7b1fa2"
    style.stroke-dash: 5
  }

  # DMA ↔ Fabric
  dma <-> fport
}

# ── NoC Router + attached resources ──

noc: NoC Router {
  style.fill: "#f3e5f5"
  style.stroke: "#6a1b9a"
  style.border-radius: 6
}

hbm: Local HBM {
  style.fill: "#e8eaf6"
  style.stroke: "#283593"
  style.border-radius: 6

  ipcq_slot_hbm: IPCQ Slot Region {
    style.stroke-dash: 5
    style.fill: "#c5cae9"
    style.stroke: "#283593"
    style.border-radius: 3
  }
}

sram: Cube SRAM {
  style.fill: "#e0f7fa"
  style.stroke: "#00695c"
  style.border-radius: 6

  ipcq_slot_sram: IPCQ Slot Region {
    style.stroke-dash: 5
    style.fill: "#b2dfdb"
    style.stroke: "#00695c"
    style.border-radius: 3
  }
}

other_pe: Other PEs {
  style.fill: "#ede7f6"
  style.stroke: "#6a1b9a"
  style.border-radius: 6
}

other_cube: Other Cubes / SIPs {
  style.fill: "#ede7f6"
  style.stroke: "#6a1b9a"
  style.border-radius: 6
}

pe.fport <-> noc
noc <-> hbm
noc <-> sram
noc <-> other_pe
noc <-> other_cube