Packaging for eight-socket one-hop SMP topology

Patent metadata

Field	Value
Publication number	US-9456506-B2
Application number	US-201314136135-A
Country	US
Kind code	B2
Filing date	Dec 20, 2013
Priority date	Dec 20, 2013
Publication date	Sep 27, 2016
Grant date	Sep 27, 2016

Abstract

A mechanism is provided for packaging a multiple socket, one-hop symmetric multiprocessor topology. The mechanism connects each of a first plurality of processor modules to a first multiple-socket planar via a respective one of a first plurality of land grid array (LGA) connectors. The mechanism connects the first multiple-socket planar to a first side of a redistribution card via a second plurality of LGA connectors. The mechanism connects each of a second plurality of processor modules to a second multiple-socket planar via a respective one of a third plurality of LGA connectors. The mechanism connects the second multiple-socket planar to a second side of the redistribution card via a fourth plurality of LGA connectors.

First claim

What is claimed is:

1. A multiple socket, one-hop symmetric multiprocessor package, comprising:
a first multiple-socket planar;
a second multiple-socket planar;
a redistribution card;
a first plurality of processor modules connected to the first multiple-socket planar via a respective one of a first plurality of land grid array (LGA) connectors, wherein the first multiple-socket planar is connected to a first side of the redistribution card via a second plurality of LGA connectors; and
a second plurality of processor modules connected to the second multiple-socket planar via a respective one of a third plurality of LGA connectors, wherein the second multiple-socket planar is connected to a second side of the redistribution card via a fourth plurality of LGA connectors.

2. The package of claim 1 , further comprising
an inter-planar link from each socket of the first multiple-socket planar to each socket of the second multiple-socket planar through the redistribution card.

3. The package of claim 1 , further comprising:
an interconnect link from each socket of the first multiple-socket planar to each other socket of the first multiple-socket planar.

4. The package of claim 1 , further comprising:
an interconnect link from each socket of the second multiple-socket planar to each other socket of the second multiple-socket planar.

5. The package of claim 1 , wherein the redistribution card uses build-up laminate technology, high density interconnect (HDI) technology, or printed circuit board (PCB) technology.

6. The package of claim 1 , wherein the second plurality of LGA connectors and the fourth plurality of LGA connectors use opposite sides of the socket footprint and do not overlap in the stack.

7. The package of claim 1 , further comprising:
a first plurality of memory modules and a first plurality of voltage regulators connected to the first multiple-socket planar; and
a second plurality of memory modules and a second plurality of voltage regulators connected to the second multiple-socket planar.

8. A design structure embodied in a computer readable storage medium for designing and manufacturing a multiple socket, one-hop symmetric multiprocessor package, the design structure comprising:
a first multiple-socket planar;
a second multiple-socket planar;
a redistribution card;
a first plurality of processor modules connected to the first multiple-socket planar via a respective one of a first plurality of land grid array (LGA) connectors, wherein the first multiple-socket planar is connected to a first side of the redistribution card via a second plurality of LGA connectors; and
a second plurality of processor modules connected to the second multiple-socket planar via a respective one of a third plurality of LGA connectors, wherein the second multiple-socket planar is connected to a second side of the redistribution card via a fourth plurality of LGA connectors.

9. The design structure of claim 2 , wherein the design structure further comprises:
an inter-planar link from each socket of the first multiple-socket planar to each socket of the second multiple-socket planar through the redistribution card.

10. The design structure of claim 2 , wherein the design structure further comprises:
an interconnect link from each socket of the first multiple-socket planar to each other socket of the first multiple-socket planar.

11. The design structure of claim 2 , wherein the design structure further comprises:
an interconnect link from each socket of the second multiple-socket planar to each other socket of the second multiple-socket planar.

12. The design structure of claim 2 , wherein the redistribution card uses build-up laminate technology, high density interconnect (HDI) technology, or printed circuit board (PCB) technology.

13. The design structure of claim 2 , wherein the second plurality of LGA connectors and the fourth plurality of LGA connectors use opposite sides of the socket footprint and do not overlap in the stack.

Assignees

• IBM

Inventors

• Colbert John L
• Dreps Daniel M
• Harvey Paul M
• Mandrekar Rohan U

Classifications

• H10W90/00

  Package configurations · CPC title

• H10W70/635

  Through-vias · CPC title

• H10W70/60

  Insulating or insulated package substrates; Interposers; Redistribution layers (leadframes H10W70/40) · CPC title

• H10W40/10

  Arrangements for heating · CPC title

• H05K3/325 Primary

  by abutting or pinching; Mechanical auxiliary parts therefor · CPC title