Granted Patent B1

US 12,283,571 · App. 17/230,889 · Granted Apr 22, 2025

Inventors: Rajeev Kumar Dokania (Beaverton, OR); Sasikanth Manipatruni (Portland, OR); Amrita Mathuriya (Portland, OR); Debo Olaosebikan (San Francisco, CA)

Assignee: Kepler Computing Inc.

H01L25/0657H01L23/49811H01L23/49894H01L23/5389H10B41/42

Abstract

Claims (34)

1. An apparatus comprising:

an interposer;

a first die having a first surface and a second surface opposite to the first surface, the first surface on the interposer, wherein the first die comprises a dynamic random-access memory (DRAM) having bit-cells, wherein the first die includes first active devices closer to the second surface than the first surface, and wherein the first die does not have a matrix multiplier;

a second die stacked over the first die, wherein the second die substantially overlaps the first die, the second die having a third surface and a fourth surface opposite the third surface, wherein the third surface faces the second surface, wherein the second die comprises one or more controller circuitries coupled to the DRAM of the first die, wherein the second die includes second active devices, wherein the second active devices are closer to the fourth surface than the third surface, and wherein the second die does not have a matrix multiplier; and

a third die stacked over the second die, the third die being an uppermost die, wherein the third dies substantially overlaps the second die, the third die having a fifth surface and a sixth surface opposite to the fifth surface, wherein the fifth surface faces the fourth surface, wherein the third die comprises processing cores, wherein at least one processing core includes a matrix multiplier coupled to the DRAM of the first die, wherein the third die includes third active devices, and wherein the third active devices are closer to the fifth surface than the sixth surface.

2. The apparatus of claim 1 , wherein the first and second dies are wafer-to-wafer bonded or die-to-wafer bonded, and wherein the second and the third dies are wafer-to-wafer bonded or die-to-wafer bonded.

3. The apparatus of claim 1 , wherein the first and second dies are coupled via micro-bumps.

4. The apparatus of claim 3 , wherein the first die includes through-silicon-vias (TSVs), and wherein a number of TSVs is substantially less than a number of the micro-bumps.

5. The apparatus of claim 4 , wherein the TSVs include power and ground lines, and lines to couple a device external to the apparatus.

6. The apparatus of claim 4 , wherein the second die is independent of TSVs.

7. The apparatus of claim 1 , wherein the interposer comprises memory coupled to the second die.

8. The apparatus of claim 7 , wherein the memory in the interposer includes TSVs.

9. The apparatus of claim 7 , wherein the memory in the interposer includes DRAM, flash, eDRAM, MRAM, ReRAM, SRAM, or FeRAM.

10. The apparatus of claim 1 , wherein the matrix multiplier includes an array of multiplier cells, and wherein the DRAM includes an array of memory bit-cells, and wherein each multiplier cell is coupled to corresponding memory bit-cell.

11. The apparatus of claim 1 , wherein the second die comprises a logic circuitry coupled to the matrix multiplier.

12. The apparatus of claim 11 , wherein the second die comprises a buffer coupled to the logic circuitry, and wherein the buffer is coupled to a memory.

13. The apparatus of claim 11 , wherein each bit-cell comprises an access transistor and a capacitor.

14. The apparatus of claim 1 , wherein a heat sink is coupled to the second die.

15. The apparatus of claim 1 , wherein the first and second dies are coupled via at least one of: micro-bumps, copper-to-copper hybrid bond, or wire bond, wherein the first die includes through-silicon-vias (TSVs), and wherein a number of TSVs is substantially less than a number of the micro-bumps.

16. An apparatus comprising:

a substrate;

a first die having a first surface and a second surface opposite to the first surface, the first surface on the substrate, wherein the first die comprises a random-access memory (RAM) having bit-cells, wherein the first die includes first active devices closer to the second surface than the first surface, and wherein the first die does not have a matrix multiplier;

a second die stacked over the first die, wherein the second die substantially overlaps the first die, the second die having a third surface and a fourth surface opposite the third surface, wherein the third surface faces the second surface, wherein the second die comprises one or more controller circuitries coupled to the RAM of the first die, wherein the second die includes second active devices, wherein the second active devices are closer to the fourth surface than the third surface, and wherein the second die does not have a matrix multiplier; and

a third die stacked over the second die, the third die being an uppermost die, wherein the third die substantially overlaps the second die, the third die having a fifth surface and a sixth surface opposite to the fifth surface, wherein the fifth surface faces the fourth surface, wherein the third die comprises processing cores, wherein at least one processing core includes a matrix multiplier coupled to the RAM of the first die, wherein the third die includes third active devices, and wherein the third active devices are closer to the fifth surface than the sixth surface.

17. The apparatus of claim 16 , wherein:

the first die includes through-silicon-vias (TSVs), wherein a number of TSVs is substantially less than a number of micro-bumps; and

the RAM includes one of: DRAM, flash, eDRAM, MRAM, ReRAM, SRAM, or FeRAM.

18. An apparatus comprising:

a substrate;

a first die having a first surface and a second surface opposite to the first surface, the first surface on the substrate, wherein the first die comprises a ferroelectric random-access memory (FeRAM) having bit-cells, wherein the first die includes first active devices closer to the second surface than the first surface, and wherein the first die does not have a matrix multiplier;

a second die stacked over the first die, wherein the second die substantially overlaps the first die, the second die having a third surface and a fourth surface opposite the third surface, wherein the third surface faces the second surface, wherein the second die comprises one or more controller circuitries coupled to the FeRAM of the first die, wherein the second die includes second active devices, wherein the second active devices are closer to the fourth surface than the third surface, and wherein the second die does not have a matrix multiplier; and

a third die stacked over the second die, the third die being an uppermost die, wherein the third die substantially overlaps the second die, the third die having a fifth surface and a sixth surface opposite to the fifth surface, wherein the fifth surface faces the fourth surface, wherein the third die comprises processing cores, wherein at least one processing core, wherein the at least one processing core is coupled to the FeRAM of the first die, wherein the third die includes third active devices, and wherein the third active devices are closer to the fifth surface than the sixth surface.

19. The apparatus of claim 18 comprising a first silicon structure and a second silicon structure, wherein the first silicon structure is laterally next to the first die, and wherein the second silicon structure is laterally next to the second die opposite to the first silicon structure.

20. The apparatus of claim 18 , wherein the first and second dies are coupled via micro-bumps.

Assignments (1)

Continuity (1)

References Cited (273)