IP Library › Granted Patent US 12,451,436
Granted Patent B2
US 12,451,436 · App. 18/671,478 · Granted Oct 21, 2025

Interconnecting a plurality of dies having spare input/output circuit

Inventors: Sanjay Dabral (Cupertino, CA); Jun Zhai (Cupertino, CA)
Assignee: Apple Inc.
H01L23/5389H01L22/32H01L23/488H01L23/49838H01L23/522H01L23/5283H01L23/58H01L24/19H01L24/20H01L24/24H01L24/73H01L24/92H01L25/18H01L22/34H01L24/06
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,451,436
App. No.
18/671,478
Granted
Oct 21, 2025
Kind
B2
Abstract

Stitched die structures, and methods for interconnecting die are described. In an embodiment, a stitched die structure includes a semiconductor substrate that includes a first die area of a first die and a second die area of a second die separate from the first die area. A back-end-of-the-line (BEOL) build-up structure spans over the first die area and the second die area, and includes a first metallic seal directly over a first peripheral area of the first die area, a second metallic seal directly over a second peripheral area of the second die area, and a die-to-die routing extending through the first metallic seal and the second metallic seal to electrically connect the first die to the second die.

Claims (21)

1. A die structure comprising:

a semiconductor substrate;

a first front-end-of-the-line (FEOL) die area of a first die patterned into the semiconductor substrate, the first FEOL die area including a plurality of input/output (I/O) circuits; and

a back-end-of-the-line (BEOL) build-up structure spanning over the first FEOL die area, the BEOL build-up structure including a plurality of die I/O connections coupled to the plurality of I/O circuits with a plurality of routings, wherein an I/O circuit of the plurality of I/O circuits is not coupled to a die I/O connection.

2. The die structure of claim 1 , wherein each die I/O connection is selected from the group consisting of a pad and a pin.

3. The die structure of claim 1 , comprising a first group of the plurality of routings with a first characteristic routing pattern, and a second group of the plurality of routings with a second characteristic routing pattern, wherein a difference in the first characteristic routing pattern and the second characteristic routing pattern is correlated with the I/O circuit not being coupled to a die I/O connection.

4. The die structure of claim 1 , wherein each input/output circuit of the plurality of input/output circuits includes a digital I/O component and an analog I/O component.

5. The die structure of claim 1 , wherein the I/O circuit of the plurality of I/O circuits that is not coupled to a die I/O connection is a spare I/O circuit or a bad I/O circuit.

6. The die structure of claim 1 , wherein the plurality of I/O circuits is arranged in series.

7. The die structure of claim 6 , wherein the I/O circuit that is not coupled to a die I/O connection is at an end of the series.

8. The die structure of claim 6 , wherein the I/O circuit that is not coupled to a die I/O connection is within the series.

9. The die structure of claim 1 further comprising:

a second FEOL die area of a second die patterned into the semiconductor substrate

wherein the BEOL build-up structure spans over the second die area, the BEOL build-up structure comprising a die-to-die routing electrically connecting the first die to the second die.

10. The die structure of claim 9 , further comprising a metallic seal around the first die area, the second die area and the die-to die routing.

11. The die structure of claim 9 , further comprising one or more barrier layers including a substantially uniform thickness spanning along die edges of the die structure substantially orthogonal to metal layers of the BEOL build-up structure.

12. The die structure of claim 11 , wherein the one or more barrier layers includes an oxide layer.

13. The die structure of claim 11 , wherein the one or more barrier layers includes a nitride layer.

14. The die structure of claim 9 , wherein the first die and the second die are each selected from the group consisting of a graphics processing unit (GPU) and a central processing unit (CPU).

15. The die structure of claim 9 , wherein the die-to-die routing includes a first die routing within the first die area, a second die routing within the second die area, and a stitch routing physically connecting the first die routing to the second die routing.

16. The die structure of claim 15 , wherein the stitch routing has a wider line width than the first die routing and the second die routing, and the stitch routing has a coarser line pitch than the first die routing and the second die routing.

Continuity (6)
Continuation 17931343 · Sep 12, 2022
Continuation 17216278 · Mar 29, 2021
Continuation 16583082 · Sep 25, 2019
Continuation 15801163 · Nov 1, 2017
Provisional Application 62484330 · Apr 11, 2017
Related Publication 20240387390A1 · Nov 21, 2024
References Cited (33)
US 7482675B2 · Adkisson et al. · 2009 [cited by applicant]
US 7518229B2 · Cotte et al. · 2009 [cited by applicant]
US 8164171B2 · Lin et al. · 2012 [cited by applicant]
US 8785246B2 · Vu et al. · 2014 [cited by applicant]
US 10438896B2 · Dabral et al. · 2019 [cited by applicant]
US 10985107B2 · Dabral et al. · 2021 [cited by applicant]
US 11476203B2 · Dabral et al. · 2022 [cited by applicant]
US 11728266B2 · Dabral et al. · 2023 [cited by applicant]
US 12021035B2 · Dabral · 2024 [cited by examiner]
US 20090160029A1 · Pitts et al. · 2009 [cited by applicant]
US 20100193931A1 · Do et al. · 2010 [cited by applicant]
US 20110068449A1 · Kook · 2011 [cited by examiner]
US 20120326146A1 · Hui et al. · 2012 [cited by applicant]
US 20130020674A1 · Leal et al. · 2013 [cited by applicant]
US 20130256659A1 · Tsai et al. · 2013 [cited by applicant]
US 20130307143A1 · Lin · 2013 [cited by examiner]
US 20140120696A1 · Aleksov et al. · 2014 [cited by applicant]
US 20140319522A1 · Daubenspeck et al. · 2014 [cited by applicant]
US 20150162259A1 · Bartley · 2015 [cited by examiner]
US 20150194391A1 · Tsutsue et al. · 2015 [cited by applicant]
US 20150200146A1 · Reber et al. · 2015 [cited by applicant]
US 20150262844A1 · Meyer et al. · 2015 [cited by applicant]
US 20150294954A1 · Leung et al. · 2015 [cited by applicant]
US 20170325774A1 · Mentrup et al. · 2017 [cited by applicant]
US 20180294230A1 · Dabral et al. · 2018 [cited by applicant]
US 20190181170A1 · Oishi et al. · 2019 [cited by applicant]
US 20190206809A1 · Tatour et al. · 2019 [cited by applicant]
US 20200105682A1 · Liu et al. · 2020 [cited by applicant]
US 20210217702A1 · Dabral et al. · 2021 [cited by applicant]
Wafer-Scale Integration of Systolic Arrays, Tom Leighton, Charles E. Leiserson, IEEE Transactions on Computers, vol. c-34, No. 5, May 1985. [cited by applicant]
Wafer scale Integration (WSI) of Programmable Gate Arrays (PGA's), J.F. McDonald, S. Dabral, R. Philhower, M.E. Russinovich, Wafer Scale Integration, 1990. Proceedings., [2nd] International Conference on Wafer Scale Int… [cited by applicant]
3D Technology Trends & Key Manufacturing Challenges, Focus on Lithography. From Technologies to Market. IMAPS—Lunch Keynote. Yole Development. May 2015. Retrieved on Oct. 8, 2017 from: http://www.imapsne.net/2015%20Pres… [cited by applicant]
VPG series, High Speed Pattern Generator. Heidelberg Instruments, (n.d.). Retrieved on Oct. 8, 2017 from: http://www.himt.de/files/Factshe1e8t%20Download/HIMT%20Fact%20Sheet%20VPG%20Series%20200-400.pdf. [cited by applicant]