IPCQ-DMA co-design HW design doc + fix IPCQ slot BW model

Add hardware design document (docs/ipcq-dma-codesign-hw.md) covering
PE_IPCQ high-level architecture, simulator verification, proposed HW
implementation, and alternatives analysis. Include D2 block diagrams
for baseline and proposed PE architectures.

Fix IPCQ slot-memory bandwidth parameters to match topology.yaml:
SRAM 128→512 GB/s (intrinsic BW, NoC-bottlenecked at 128),
HBM 32→256 GB/s (was per-channel, now per-PE aggregate).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docs/diagrams/pe_proposed.d2

@@ -0,0 +1,166 @@
+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: IPCQ Controller (NEW) {
+    style.fill: "#e1f5fe"
+    style.stroke: "#0277bd"
+    style.border-radius: 6
+    style.stroke-width: 2
+
+    ptrmgmt: Pointer Mgmt {
+      style.fill: "#b3e5fc"
+      style.stroke: "#0277bd"
+      style.border-radius: 4
+
+      qprf: QPair Reg File
+      bp: Backpressure
+      sag: Slot Addr Gen
+    }
+
+    sideband: Sideband {
+      style.fill: "#b3e5fc"
+      style.stroke: "#0277bd"
+      style.border-radius: 4
+
+      metax: Meta Extractor
+      crinj: Credit Injector
+      crrcv: Credit Receiver
+    }
+  }
+
+  dma: PE_DMA (MOD) {
+    style.fill: "#fff3e0"
+    style.stroke: "#e65100"
+    style.border-radius: 6
+
+    compute_port: compute port {
+      style.fill: "#ffe0b2"
+      style.stroke: "#e65100"
+      style.border-radius: 4
+    }
+    ipcq_port: IPCQ port {
+      style.fill: "#ffe0b2"
+      style.stroke: "#e65100"
+      style.border-radius: 4
+    }
+    wrr: WRR Arbiter (NEW) {
+      style.fill: "#ffcc80"
+      style.stroke: "#e65100"
+      style.border-radius: 4
+      style.stroke-width: 2
+    }
+
+    compute_port -> wrr
+    ipcq_port -> wrr
+  }
+
+  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
+
+    work: Kernel Working Memory {
+      style.fill: "#f8bbd0"
+      style.stroke: "#c62828"
+      style.border-radius: 4
+    }
+    slot: IPCQ Slot Region (rsv) {
+      style.fill: "#f48fb1"
+      style.stroke: "#c62828"
+      style.border-radius: 4
+      style.stroke-width: 2
+    }
+  }
+
+  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
+  cpu -> sched: cmd dispatch
+  cpu -> ipcq: MMIO
+
+  # Compute pipeline
+  sched -> dma.compute_port: TileToken
+  dma -> fs: TileToken
+  dma <-> tcm.work: DMA_READ/WRITE\n(HBM ↔ TCM)
+  fs <-> tcm.work: fetch/store\n(TCM ↔ reg)
+  fs -> gemm: TileToken
+  fs -> math: TileToken
+  gemm -> fs: TileToken
+  math -> fs: TileToken
+
+  # IPCQ data path
+  ipcq -> dma.ipcq_port: IpcqDmaToken {style.stroke: "#0277bd"}
+  dma -> ipcq.sideband.metax: IpcqMetaArrival {style.stroke: "#0277bd"}
+
+  # IPCQ slot R/W
+  dma <-> tcm.slot: slot read/write {
+    style.stroke: "#0277bd"
+    style.stroke-dash: 3
+  }
+
+  # Credit via fabric port
+  ipcq.sideband.crinj -> fport: credit out (16B) {
+    style.stroke: "#7b1fa2"
+    style.stroke-dash: 5
+  }
+  fport -> ipcq.sideband.crrcv: credit in (16B) {
+    style.stroke: "#7b1fa2"
+    style.stroke-dash: 5
+  }
+
+  # DMA ↔ Fabric
+  dma.wrr <-> fport
+}
+
+noc: NoC Router {
+  style.fill: "#f3e5f5"
+  style.stroke: "#6a1b9a"
+  style.border-radius: 6
+}
+
+ext: Other PEs / Cubes / SIPs {
+  style.fill: "#ede7f6"
+  style.stroke: "#6a1b9a"
+  style.border-radius: 6
+}
+
+pe.fport <-> noc
+noc <-> ext