wafer.space Run 1

30 public designs on one GF180MCU reticle

Reserve a slot on wafer.space Run 3 Or start with Tiny Tapeout

What was built

The run as a whole: what its designs add up to.

30

Public designs

in 38 of the reticle's 40 slot positions

27

Open source

with a public repository and an open licence

52.8M

Transistors

across the unique designs

2.1M

Logic cells

gates and flip-flops

79 KiB

SRAM

in foundry and custom macros

26

Whole dies

and 12 half and quarter slots

Private designs on the reticle are not in the public layout and are not counted. Designs placed more than once are counted once.

Make a chip of your own

Start small with a Tiny Tapeout tile, or go straight to a whole die on the next wafer.space run.

Make a whole chip of your own

Book a die to itself on wafer.space Run 3: orders close 9 December 2026.

Reserve a slot
Or start with a Tiny Tapeout tile

Tiny Tapeout GF 26c and 26d take projects until 7 December 2026, to be made on wafer.space Run 3.

Submit a project
Get a Tiny Tapeout chip

Every Tiny Tapeout chip comes on a board you can plug in, with all of its projects ready to try.

Buy a chip and board

The reticle

Every design rendered from the layout at the same scale and placed where it sits on the 30 × 23.4 mm reticle. Dark gaps are private designs or empty slots. Point at a die to see its name, and select it for its details.Every die is listed further down.

Slots

How much of the reticle each design took: a 1 × 1 slot is a whole die of its own, and the ½ sizes are halves and quarters of one. Some designs are placed more than once, so 30 designs fill 38 slots.

1 × 126
1 × ½7
½ × 14
½ × ½1
Total38

Layout on GitHub The run on Crowd Supply

Shuttle status

Where this run is now, from opening orders to shipping parts.

Done so far

  • 28 November 2025, 23:59 AoE Purchase deadline Final deadline to purchase manufacturing slots
  • 3 December 2025, 23:59 AoE Design submission Final deadline to submit GDS files for fabrication
  • 8 January 2026 Tape-out to GlobalFoundries GDS files delivered to GlobalFoundries for fabrication
  • 6 April 2026 Wafers returned Wafers back from GlobalFoundries
  • 10 April 2026 First wafers diced The first wafers cut into individual dies
  • 17 April 2026 Remaining wafers diced The rest of the wafers diced
  • 20 April 2026 First dies sorted Dies picked from the first wafers for the first shipments
  • 21 April 2026 First bare dies shipped Initial bare dies shipped to customers
  • 25 April 2026 First packaged parts shipped Initial chip-on-board packaged parts shipped
  • 4 May 2026 Bare dies shipped Sorted dies from the main batch of wafers shipped

Still to come

  • Today, 24 October 2026
  • 31 October 2026 (expected) Packaged parts shipped Chip-on-board packaged parts from the main batch of wafers shipped
  • 5 November 2026 (expected) Last bare dies shipped Sorted dies from the last wafers shipped
  • 5 December 2026 (expected) Last packaged parts shipped Chip-on-board packaged parts from the last wafers shipped

Missed this run? wafer.space Run 3 takes orders until 9 December 2026: reserve a slot.

From the wafer.space run schedule.

How people used their silicon

Where the area of 30 dies (507 mm² of silicon) actually went

12%
27%
16%
39%
  • Logic cells 12% — gates and flip-flops doing the design's actual work
  • SRAM 6% — memory macros
  • Filler and tap cells 27% — inserted by the tools to keep rows continuous and wells tied
  • Other 16% — routing channels, analog and custom layout, power grid and empty space
  • Pad ring 39% — the 442 µm border of I/O cells and bond pads

Standard cell libraries

The ready-made gate libraries the designs were built from: how many tracks tall each cell is, and the voltage it runs at.

Standard cell libraryLogic cellsShare
7t-5V gf180mcu_fd_sc_mcu7t5v0 1.7M 77%
9t-5V gf180mcu_fd_sc_mcu9t5v0 443k 21%
AS 7t-3.3V gf180mcu_as_sc_mcu7t3v3 35k 2%
AS extra 7t-5V gf180mcu_as_ex_mcu7t5v0 5k <1%

Area budget of every design

Each bar is one die, split the same way as above. Sorted by how much of the die is logic.

Show all 30 dies

Which parts of the process were used

Transistor voltages and optional devices across the 30 designs

Transistor voltages

3.3 V 8
5 V 29
6 V 5

A design counts for a voltage when its standard cells, SRAM or its own transistors use it. 5 V and 6 V transistors share the thick gate oxide; a marker layer in the layout tells them apart.

Licences

The licence each designer declared when submitting.

Declared licenceDesigns
Apache-2.022
proprietary3
GPL-3.0-only1
CERN-OHL-S-2.01
BSD-3-Clause1
MIT1
CERN-OHL-W-2.01

Some repositories carry a different licence file from the one declared at submission, or none: check a design's repository, and its page here, before reusing it.

Packaging and precheck

How the designs will be packaged, and whether they passed the design-rule checks before manufacture.

  • Which designs chose chip-on-board packaging was not recorded for this run; 11 dies have bonding results.
  • 29 of 30 designs passed the platform precheck they were accepted on (2025-12-10 to 2026-01-04), and 29 pass their latest re-run; RBOY has no finished precheck recorded.
  • The KLayout DRC, the sign-off check, is clear in every one of these checks.
  • The advisory Magic DRC reported errors for BRWN, CHES, GD04, KIAN, TRID.
  • The platform no longer stores the step results of the checks TTP2, TTPG were accepted on; their pages show the latest re-run.

What fits on 1 mm² of GF180MCU silicon?

Theoretical maximum against what designers achieved

The maximum packs one cell type edge to edge with no room for wiring. Real designs need the wiring. Each box gives the most of a cell that fits with any GF180MCU library, then with the libraries this run used.

~114k

Inverters per mm²

GF180MCU maximum,
with AS 7t-3.3V inv_2

With this run's libraries:

7t-5V: 114k inv_1

9t-5V: 89k inv_1

AS 7t-3.3V: 114k inv_2

~91k

NAND gates per mm²

GF180MCU maximum,
with 7t-5V nand2_1

With this run's libraries:

7t-5V: 91k nand2_1

9t-5V: 71k nand2_1

AS 7t-3.3V: 65k nand2_2

~76k

Buffers per mm²

GF180MCU maximum,
with AS 7t-3.3V buff_2

With this run's libraries:

7t-5V: 76k buf_1

9t-5V: 59k buf_1

AS 7t-3.3V: 76k buff_2

~17k

Flip-flops per mm²

GF180MCU maximum,
with AS 7t-3.3V dfxtp_2

With this run's libraries:

7t-5V: 16k dffq_1

9t-5V: 13k dffq_1

AS 7t-3.3V: 17k dfxtp_2

AS extra 7t-5V: 14k dfxtp_2

25k

Best core average

logic cells/mm² of core — 32% of the buffer maximum

Cloneless1

40k

Densest mm²

logic cells — 52% of the buffer maximum

gf180mcu-jku-projects

7k

Typical die

median logic cells/mm² of core across 26 digital dies (1,000 or more logic cells)

20% of the core covered by logic cells

Percentages compare with the buffer maximum for each design's own library: buffers are among the smallest and most common logic cells, so a design made only of buffers, packed edge to edge with no wiring, would reach 100%.

Sizing your own design

What each slot size held on this run, and what it would hold at its densities

Logic cells in its digital designs1,000 or more logic cells Logic cells at this run's density Theoretical maximum, 7t-5V cells
Slot Die  Core area Designs  Most Median  Typical7k / mm²Best25k / mm² Densest40k / mm² NAND gatesnand2_1Flip-flopsdffq_1
1 × 13.93 × 5.12 mm 12.9 mm²21 316k87k 89k 316k 512k 1.2M 203k
1 × ½3.93 × 2.53 mm 5.0 mm²4 36k36k 34k 123k 199k 457k 79k
½ × 11.94 × 5.12 mm 4.5 mm²4 35k35k 31k 109k 177k 406k 70k
½ × ½1.94 × 2.53 mm 1.7 mm²1 36k36k 12k 42k 69k 158k 27k

Swipe the table sideways for more columns.

Core area is each design's CORE_AREA, read from its own LibreLane config at the commit that was checked; where that could not be read, the project template's, 442 µm in from each edge of the die. Density inside the seal ring is over the whole die less its 26 µm seal ring: all the silicon a slot gives its designer, pad ring included. "Typical" and "best" multiply the core area by this run's median and best core densities, and "densest" by the densest 1 mm² any design on this run reached; SRAM and analog blocks take their area out of that. The theoretical maxima fill the core with nothing but that one cell of 7t-5V, the library most used on this run, edge to edge with no routing.

Pick the slot size your design needs on wafer.space Run 3: orders close 9 December 2026.

Logic density of every digital design

A digital die here is one with 1,000 or more logic cells. Solid bar: average over the core. Dark line inside it: average over all the silicon inside the seal ring, pad ring included. Outlined bar: the densest mm² outside SRAM (a dash where memory covers most of the design). The scale ends at the buffer theoretical maximum (76k cells/mm²). The numbers are core / seal ring / densest, in logic cells per mm².

Show all 26 digital dies
Every digital die's densities as a table
DesignSlotLibraryLogic cells Inside core
per mm²
Inside seal ring
per mm²
Densest mm²
per mm²
Core coveredCore
mm²
Cloneless1 2975 1 × 17t-5V 316,440 24,525 16,101 31,548 56% 12.90*
TinyQV - Crowdsourced RISC-V SoC TQVA ½ × ½7t-5V 35,711 20,611 7,633 22,636 47% 1.73
Tiny Tapeout GF 0.2, standard TTP2 1 × 1mixed 203,781 15,793 10,369 26,088 46% 12.90*
Tiny Tapeout GF 0.2, power-gated TTPG 1 × 1mixed 203,780 15,793 10,369 26,088 46% 12.90*
FABulous FPGA MOLE 1 × 17t-5V 203,757 15,774 10,367 27,014 49% 12.92
gf180mcu-jku-projects JKU1 1 × 17t-5V 174,469 13,506 8,877 39,690 29% 12.92
chess-move-generator CHES 1 × 19t-5V 145,076 11,231 7,382 12,616 35% 12.92
TinyQV - Crowdsourced RISC-V SoC (0.5x1) TQVB ½ × 17t-5V 35,416 7,944 3,701 23,580 18% 4.46
FazyRV Hachure CAFE 1 × 17t-5V 100,546 7,784 5,116 21,486 26% 12.92
Racquet Half r1p0 (1/2 slot) GD02 ½ × 17t-5V 34,564 7,753 3,612 11,735 21% 4.46
TinyQV - Crowdsourced RISC-V SoC (1x0.5) TQVC 1 × ½7t-5V 36,116 7,194 3,758 16,157 16% 5.02
Racquet Wide 1x0.5 GD04 1 × ½9t-5V 35,525 7,077 3,697 18,167 28% 5.02
KianV: A 32-bit RISC-V Linux SoC taped out on GF180MCU KIAN 1 × 19t-5V 88,941 6,885 4,525 12,888 24% 12.92
LGN FashionMNIST - Logic Gate Network trained on FashionMNIST RZML 1 × 17t-5V 88,407 6,852 4,498 8,379 23% 12.90*
WS-Multi AS03 1 × 1mixed 86,629 6,706 4,408 21,295 19% 12.92
Racquet r2p0 - 23 core SoC GD03 1 × 17t-5V 78,208 6,054 3,979 — 17% 12.92
RISCBoy-180 RBOY 1 × 19t-5V 69,949 5,415 3,559 13,571 23% 12.92
TillitisZedulo-testchip2025 TZ01 1 × 17t-5V 58,018 4,491 2,952 18,145 13% 12.92
gf180mcu-jku-atbs-adc JKU2 1 × ½9t-5V 22,476 4,477 2,339 8,798 19% 5.02
BreakingTTAPs BTAP 1 × 19t-5V 43,225 3,346 2,199 20,600 9% 12.92
openframe_caravel_picorv32 OCD1 1 × 1AS 7t-3.3V 34,431 2,668 1,752 10,353 7% 12.90*
MOSbiusV3 MOSB 1 × 19t-5V 17,889 1,386 910 4,932 5% 12.90*
FOSSi open-source replacement for Z80 classic 8-bit CPU (0.5 x 1 slot) HZ80 ½ × 19t-5V 5,143 1,154 537 4,951 4% 4.46
wafer.space Logo WSLG 1 × 1mixed 14,290 1,106 727 11,110 4% 12.92
FOSSi open-source replacement for Z80 classic 8-bit CPU RZ80 1 × 19t-5V 5,209 403 265 4,684 1% 12.92
FA25_Engn2912e_Saligane_Brown BRWN 1 × 17t-5V 4,379 339 223 2,590 1% 12.90*

* The project template's core: the design's own config could not be read.

The projects

Every design on this run: an index, then grouped by what it does. Select one for its layout, its measurements and any die photographs.

Design index

All 30 public designs by their code, with the slot each took and how much logic it packs.

CodeDesignSlot What it isLogic cells Cells per mm²
2975 Cloneless1 1 × 1 Security 316,440 25k
AS03 WS-Multi 1 × 1 Multi-project die 86,629 7k
BRWN FA25_Engn2912e_Saligane_Brown 1 × 1 Other digital 4,379 <1k
BTAP BreakingTTAPs 1 × 1 RISC-V and CPUs 43,225 3k
CAFE FazyRV Hachure 1 × 1 RISC-V and CPUs 100,546 8k
CHES chess-move-generator 1 × 1 Accelerators 145,076 11k
GD02 Racquet Half r1p0 (1/2 slot) ½ × 1 RISC-V and CPUs 34,564 8k
GD03 Racquet r2p0 - 23 core SoC 1 × 1 RISC-V and CPUs 78,208 6k
GD04 Racquet Wide 1x0.5 1 × ½ RISC-V and CPUs 35,525 7k
HZ80 FOSSi open-source replacement for Z80 classic 8-bit CPU (0.5 x 1 slot) ½ × 1 Retro computing 5,143 1k
ISHI ISHI-KAI's Multiple Users Project 1 × 1 Multi-project die 0
JKU1 gf180mcu-jku-projects 1 × 1 Multi-project die 174,469 14k
JKU2 gf180mcu-jku-atbs-adc 1 × ½ Analog and mixed-signal 22,476 4k
KIAN KianV: A 32-bit RISC-V Linux SoC taped out on GF180MCU 1 × 1 RISC-V and CPUs 88,941 7k
MOLE FABulous FPGA 1 × 1 FPGA 203,757 16k
MOS2 AutoMOS-Chipathon-2025 full size 1 × 1 Analog and mixed-signal 0
MOSB MOSbiusV3 1 × 1 Analog and mixed-signal 17,889 1k
OCD1 openframe_caravel_picorv32 1 × 1 RISC-V and CPUs 34,431 3k
OCD2 ocd_sram_test 1 × ½ Memory test chip 122 <1k
RBOY RISCBoy-180 1 × 1 Retro computing 69,949 5k
RZ80 FOSSi open-source replacement for Z80 classic 8-bit CPU 1 × 1 Retro computing 5,209 <1k
RZML LGN FashionMNIST - Logic Gate Network trained on FashionMNIST 1 × 1 Accelerators 88,407 7k
TQVA TinyQV - Crowdsourced RISC-V SoC ½ × ½ RISC-V and CPUs 35,711 21k
TQVB TinyQV - Crowdsourced RISC-V SoC (0.5x1) ½ × 1 RISC-V and CPUs 35,416 8k
TQVC TinyQV - Crowdsourced RISC-V SoC (1x0.5) 1 × ½ RISC-V and CPUs 36,116 7k
TRID gf180mcu-project-trident-gf180-teststructure ½ × 1 Test structures 0
TTP2 Tiny Tapeout GF 0.2, standard 1 × 1 Multi-project die 203,781 16k
TTPG Tiny Tapeout GF 0.2, power-gated 1 × 1 Multi-project die 203,780 16k
TZ01 TillitisZedulo-testchip2025 1 × 1 Memory test chip 58,018 4k
WSLG wafer.space Logo 1 × 1 Art and logos 14,290 1k

Swipe the table sideways for more columns.

Designs that grew

These designs have been made more than once: first as a Tiny Tapeout tile or on a Google shuttle, then on wafer.space, or improved and made again on a later run. Start small, then come back bigger. The ringed marker is this run.

Tiny Tapeout tile Google shuttle wafer.space die this run
Each marker is one version of the design: hover over it or focus it for details, and select it to open its page. On a phone, the table below lists every one.

As a table
DesignMade onWhenVersionSize
FABulous FPGA Google GFMPW-0Dec 2022 56C6 One-hot FABulous FPGACaravel chip
wafer.space Run 1Dec 2025 MOLE FABulous FPGA1 × 1 slot
Tiny Tapeout IHP 26aMar 2026 Tiny FABulous FPGA8 × 4 tiles
Tiny Tapeout SKY 26aMay 2026 Tiny FABulous FPGA8 × 4 tiles
Tiny Tapeout SKY 26bMay 2026 Tiny FABulous FPGA8 × 4 tiles
Tiny Tapeout GF 0.3Jun 2026 Tiny FABulous FPGA; Tiny FABulous FPGA (3.3V version)4 × 4 tiles
wafer.space Run 2Jul 2026 MOLE FABulous FPGA1 × 1 slot
Tiny Tapeout SKY 26cSep 2026 Tiny FABulous FPGA8 × 4 tiles
Tiny Tapeout IHP 26bSep 2026 Tiny FABulous FPGA6 × 4 tiles
TinyQV RISC-V SoC Tiny Tapeout 6Apr 2024 TinyQV RISC-V SoC2 × 2 tiles
Tiny Tapeout IHP 0.2Nov 2024 TinyQV RISC-V SoC2 × 2 tiles
Tiny Tapeout IHP 25aMar 2025 TinyQV RISC-V SoC3 × 2 tiles
Tiny Tapeout IHP 25bSep 2025 TinyQV - Crowdsourced RISC-V SoC5 × 4 tiles
Tiny Tapeout SKY 25aSep 2025 TinyQV 'Asteroids' - Crowdsourced RISC-V SoC; TinyQV 'Berzerk' - Crowdsourced RISC-V SoC8 × 4 tiles, 4 × 4 tiles
Tiny Tapeout SKY 25bNov 2025 TinyQV RISC-V SoC3 × 2 tiles
Tiny Tapeout GF 0.1Nov 2025 TinyQV RISC-V SoCin a shared block
Tiny Tapeout GF 0.2Nov 2025 TinyQV RISC-V SoC3 × 4 tiles
wafer.space Run 1Dec 2025 TQVA TinyQV - Crowdsourced RISC-V SoC; TQVB TinyQV - Crowdsourced RISC-V SoC (0.5x1); TQVC TinyQV - Crowdsourced RISC-V SoC (1x0.5)TQVA ½ × ½ slot, TQVB ½ × 1 slot, TQVC 1 × ½ slot
Tiny Tapeout GF 0.3Jun 2026 TinyQV RISC-V SoC4 × 2 tiles
wafer.space Run 2Jul 2026 TQVA TinyQV - Crowdsourced RISC-V SoC; TQVC TinyQV - Crowdsourced RISC-V SoC (1x0.5); TQVD TinyQV - RISC-V SoC with HDMI output; TQVE TinyQV - RISC-V SoC with experimental pad setupTQVA ½ × ½ slot, TQVC 1 × ½ slot, TQVD ½ × ½ slot, TQVE ½ × ½ slot
KianV RISC-V Linux SoC Tiny Tapeout 5Nov 2023 KianV uLinux SoC8 × 2 tiles
Tiny Tapeout 6Apr 2024 KianV uLinux SoC8 × 2 tiles
Tiny Tapeout 7Jun 2024 KianV RISC-V RV32E Baremetal SoC3 × 2 tiles
Tiny Tapeout IHP 0.2Nov 2024 KianV RISC-V RV32E Baremetal SoC4 × 2 tiles
Tiny Tapeout GF 0.1Nov 2025 KianV uLinux SoCin a shared block
Tiny Tapeout GF 0.2Nov 2025 KianV uLinux SoC4 × 4 tiles
wafer.space Run 1Dec 2025 KIAN KianV: A 32-bit RISC-V Linux SoC taped out on GF180MCU1 × 1 slot
Tiny Tapeout IHP 26aMar 2026 KianV SV32 TT Linux SoC8 × 4 tiles
Tiny Tapeout GF 0.3Jun 2026 KianV uLinux SoC4 × 4 tiles
wafer.space Run 2Jul 2026 KIAN KianV: A 32-bit RISC-V Linux SoC taped out on GF180MCU Run 21 × 1 slot
Open-source Z80 Tiny Tapeout 7Jun 2024 Zilog Z802 × 2 tiles
Tiny Tapeout IHP 0.2Nov 2024 Zilog Z802 × 2 tiles
Tiny Tapeout 9Nov 2024 Zilog Z802 × 2 tiles
Tiny Tapeout IHP 25aMar 2025 Zilog Z802 × 2 tiles
Tiny Tapeout GF 0.2Nov 2025 Zilog Z802 × 2 tiles
wafer.space Run 1Dec 2025 HZ80 FOSSi open-source replacement for Z80 classic 8-bit CPU (0.5 x 1 slot); RZ80 FOSSi open-source replacement for Z80 classic 8-bit CPUHZ80 ½ × 1 slot, RZ80 1 × 1 slot
wafer.space Run 2Jul 2026 HZ80 FOSSi open-source replacement for Z80 classic 8-bit CPU (0.5 x 1 slot); QZ80 FOSSi open-source replacement for Z80 classic 8-bit CPU (0.5 x 0.5 slot)HZ80 ½ × 1 slot, QZ80 ½ × ½ slot
Avalon Semiconductors' retro-computing family Tiny Tapeout 2Dec 2022 Avalon Semiconductors '5401' 4-bit Microprocessor; Avalon Semiconductors 'TBB1143' Programmable Sound Generator1 × 1 tile
Google GFMPW-0Dec 2022 105A AS2650Caravel chip
Tiny Tapeout 3Apr 2023 Avalon Semiconductors '5401' 4-bit Microprocessor; Avalon Semiconductors 'TBB1143' Programmable Sound Generator1 × 1 tile
wafer.space Run 1Dec 2025 AS03 WS-Multi1 × 1 slot
wafer.space Run 2Jul 2026 AS04 Multi-Project die using 3.3V SCL1 × 1 slot
SERV multi-core RISC-V SoC Tiny Tapeout 2Dec 2022 serv - Serial RISC-V CPU1 × 1 tile
Google GFMPW-0Dec 2022 6079 Serv tri-core (GF180 MPW0 Serv)Caravel chip
Tiny Tapeout 3Apr 2023 serv - Serial RISC-V CPU1 × 1 tile
wafer.space Run 1Dec 2025 GD02 Racquet Half r1p0 (1/2 slot); GD03 Racquet r2p0 - 23 core SoC; GD04 Racquet Wide 1x0.5GD02 ½ × 1 slot, GD03 1 × 1 slot, GD04 1 × ½ slot
wafer.space Run 2Jul 2026 GD04 Racquet Wide 1x0.51 × ½ slot
ocd_sram_test wafer.space Run 1Dec 2025 OCD2 ocd_sram_test1 × ½ slot
wafer.space Run 2Jul 2026 OCD3 3.3V SRAM test 21 × ½ slot
wafer.space Logo wafer.space Run 1Dec 2025 WSLG wafer.space Logo1 × 1 slot
wafer.space Run 2Jul 2026 WSLG wafer.space Logo1 × 1 slot
FazyRV Tiny Tapeout 6Apr 2024 FazyRV-ExoTiny2 × 2 tiles
Tiny Tapeout IHP 0.2Nov 2024 FazyRV-ExoTiny3 × 2 tiles
wafer.space Run 1Dec 2025 CAFE FazyRV Hachure1 × 1 slot
Chess move generator Tiny Tapeout 7Jun 2024 Chess3 × 2 tiles
Tiny Tapeout IHP 0.2Nov 2024 Chess3 × 2 tiles
wafer.space Run 1Dec 2025 CHES chess-move-generator1 × 1 slot
TinyWhisper Tiny Tapeout SKY 25bNov 2025 Tiny Whisper2 × 2 tiles
wafer.space Run 1Dec 2025 JKU1 gf180mcu-jku-projects1 × 1 slot

2 dies are Tiny Tapeout chips

Tiny Tapeout GF 0.2, standard (TTP2) and Tiny Tapeout GF 0.2, power-gated (TTPG) each hold dozens of small projects from Tiny Tapeout, the cheaper way to make a first chip. Each has pages of its own, project by project.

Tiny Tapeout chips on wafer.space Submit to the next one, by 7 December 2026

RISC-V and CPUs 10

Multi-project die 5

Analog and mixed-signal 3

Retro computing 3

Memory test chip 2

Accelerators 2

Art and logos 1

FPGA 1

Security 1

Test structures 1

Other digital 1

The real silicon

Optical micrographs of the fabricated dies © 2026 InfoSecDJ, CC BY-SA 4.0

Microscope images © 2026 InfoSecDJ, CC BY-SA 4.0. Each project page links to a zoomable viewer of its die. The full-resolution images are online too.

Chip-on-board bonding

Wire bonding results for the dies packaged directly onto PCBs

Select a die for its bonding results on its page, or see the whole chip-on-board results page.

Data and method

Everything on this page is measured from the public layout; the dates come from the published schedules.

  • Logic cells are standard cell instances, excluding fillers, taps, antenna diodes and tie cells.
  • Transistors are places where gate polysilicon crosses diffusion, not counting dummy fill.
  • Core area is each design's CORE_AREA, read from its own LibreLane config at the commit that was checked; where that could not be read, the project template's, 442 µm in from each edge of the die. Density inside the seal ring is over the whole die less its 26 µm seal ring: all the silicon a slot gives its designer, pad ring included.
  • Bond pads are the pad openings in the pad ring, or in a second ring of pads inside it for chip-on-board bonding; probe pads are the others, next to the blocks they test. Letters and logos on the pad layer are not pads.
  • Theoretical maximum tiles one cell at its placement boundary with no routing.
  • Densest mm² is the best 1 mm square anywhere in each die, sliding in 0.1 mm steps and avoiding SRAM.