Tiny Tapeout GF 26b · Die T26B on wafer.space Run 2

Asynchronous-AER Spike Router (4-phase REQ/ACK, 16-entry routing table, GF180)

096 · Other digital · 1 × 2 tiles

by Prof. Santhosh Sivasubramani, IIT Delhi

Rendered from the layout at 0.33 µm per pixel. Layers: NwellDiffusionPolysiliconMetal 1Metal 2Metal 3Metal 4Metal 5Top metalPad openings

Logic density

Core average
logic cells per mm²
14k (18% of buffer maximum)
Densest 0.1 mm square
logic cells per mm²
23k (30% of buffer maximum)
Core covered by logic49%
Transistor density
transistors per mm²
272k average, 344k in the 0.1 mm square with the most logic cells

Every figure here is measured from the public layout, the same way for every design on the chip: see data and method, and how its designs used the process.

GF180mcuD synchronous implementation of a 4-input / 4-output AER (address-event-representation) spike router. Time-multiplexed AER input and output buses each carry one event at a time as a 2-bit channel tag plus 6-bit address. Each incoming event is captured using a double-flop-synchronised 4-phase bundled-data REQ/ACK handshake, looked up in a 16-entry {dst_ch, dst_addr} routing table (or bypassed to pass through unchanged), queued in a 4-deep FIFO, and emitted out the output port with another 4-phase REQ/ACK handshake. Drops on FIFO overflow are counted in a 16-bit saturating drop counter with a sticky overflow_ever bit. Per-input 8-bit saturating event counters and IN_LAST / OUT_LAST debug latches are readable over SPI. 25 MHz signoff clock.

Size347 × 325 µm (0.113 mm²)
Macrott_um_santhosh_aer_router_gf
Filesdocumentation · licence · layout and netlist in Tiny Tapeout GF 26b
Tiles1 × 2 at column 4, row 10 of the tile grid
Mux address96
LanguageVerilog
Clock25 MHz
Built withLibreLane 3.0.3, open_pdks 54435919abff
Transistors31,441
Logic cells1,594 + 3,607 filler and tap cells
Libraries 7t-5V (2k)
SRAMNo SRAM

Process features

Which parts of the GF180MCU process this design uses: its transistor voltages and where they come from, its gate oxides, and any devices drawn by hand outside the standard cells, SRAM and pads.

5 V7t-5V standard cells
Gate oxidesThick only (5 V/6 V) in the design itself

Where the area went

How this project's area splits between logic cells, filler and tap cells and other.

49%
44%
  • Logic cells 0.06 mm² (49%)
  • Filler and tap cells 0.05 mm² (44%)
  • Other 0.01 mm² (7%)

Most used cells

The ten standard cells this design uses most.

CellLibraryInstancesWhat it does
dffrnq_17t-5V 299D flip-flop with reset
mux2_27t-5V 2262-input multiplexer (2x drive)
aoi22_17t-5V 146AND-OR-Invert (2x2 inputs)
dlyb_17t-5V 99Delay buffer
nand2_17t-5V 902-input NAND gate
clkbuf_27t-5V 68Clock buffer (2x drive)
buf_27t-5V 64Buffer (2x drive)
nor2_17t-5V 522-input NOR gate
aoi21_17t-5V 48AND-OR-Invert compound gate
oai21_17t-5V 33OR-AND-Invert compound gate

Logic density map

73 logic cells, 2,449 transistors 144 logic cells, 2,869 transistors 94 logic cells, 2,601 transistors 0 logic cells, 882 transistors 162 logic cells, 2,980 transistors 204 logic cells, 3,243 transistors 194 logic cells, 3,110 transistors 36 logic cells, 1,086 transistors 84 logic cells, 2,522 transistors 180 logic cells, 3,110 transistors 190 logic cells, 3,071 transistors 91 logic cells, 1,343 transistors 13 logic cells, 501 transistors 53 logic cells, 686 transistors 49 logic cells, 691 transistors 27 logic cells, 297 transistors Densest SRAM-free 0.1 mm square: 230 logic cells 7k 14k 9k 16k 20k 19k 8k 18k 19k

Logic cells per mm² in each 0.1 mm square of the project (counted in the square, scaled up to a mm²). Hatched outlines are SRAM macros; the red outline is the densest 0.1 mm square that avoids them (23k logic cells per mm²), found by sliding a 0.1 mm square over the project in 20 µm steps, so it can straddle the fixed squares and find more than any one of them. Squares at the edges are partial, so they read low.

Want your own design on a chip like this one?

Start with a tile: the next Tiny Tapeout GF180MCU chips take projects until 7 December 2026, for wafer.space Run 3. For a die of your own, wafer.space Run 3 takes orders until 9 December 2026.

Tiny Tapeout and wafer.space are independent companies that work together (announcement). Tiny Tapeout runs its own shuttles: it takes the projects, builds the die, and sells and supports the chips and boards. wafer.space has the dies manufactured on its GF180MCU runs, and these pages are wafer.space's measurements of them. For anything about a Tiny Tapeout project, chip or order, contact Tiny Tapeout.