Computing in 3D

3DIC technology refers to stacking and interconnecting chips and substrates (“interposers”) with Through Silicon Vias (TSVs). Industry is gearing up for widespread introduction of this technology with the 22 nm node. We have been pursuing a range of approaches to enable low power computing. As well as 3DIC these include heterogeneous computing, powered optimized SIMD units, optimized memory hierarchies, and MPI with post-silicon customized interconnect. Heterogeneous computing refers to the concept of building a mix of CPUs and memories that in turn enable in-situ tuning of the compute load to the compute resources. We introduce the concept of Fast Thread Migration using 3DIC technologies. We present the design of a power optimized SIMD unit in which over half of the power is employed in the FP units. A parallel computer is built using an MPI paradigm. Codes are analyzed so that the MPI interconnect can be power optimized post-silicon. Emerging 3D memories have potential to be employed as Level 2 and Level 3 caches, and this is explored using the Tezzaron 3D memory. As scaling and power optimization occurs, the main memory increasingly dominates the power consumption. Possible extensions to Cortical Processing are discussed.

[1]  Paul D. Franzon,et al.  Thermal requirements in future 3D processors , 2013, 2013 IEEE International 3D Systems Integration Conference (3DIC).

[2]  Shekhar Borkar.  The Exascale challenge , 2010, Proceedings of 2010 International Symposium on VLSI Design, Automation and Test.

[3]  Krishnendu Chakrabarty,et al.  Face-to-face bus design with built-in self-test in 3D ICs , 2013, 2013 IEEE International 3D Systems Integration Conference (3DIC).

[4]  Paul D. Franzon,et al.  Power comparison of 2D, 3D and 2.5D interconnect solutions and power optimization of interposer interconnects , 2013, 2013 IEEE 63rd Electronic Components and Technology Conference.

[5]  Rajat Mittal,et al.  Thermal implications of mobile 3D-ICs , 2014, 2014 International 3D Systems Integration Conference (3DIC).

[6]  Thomas Vogelsang,et al.  Understanding the Energy Consumption of Dynamic Random Access Memories , 2010, 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture.

[7]  Xi Chen,et al.  A 0.54pJ/b 20Gb/s ground-referenced single-ended short-haul serial link in 28nm CMOS for advanced packaging applications , 2013, 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[8]  Paul D. Franzon,et al.  Application Exploration for 3-D Integrated Circuits: TCAM, FIFO, and FFT Case Studies , 2009, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[9]  E. Beyne,et al.  Through-silicon via technology for three-dimensional integrated circuit manufacturing , 2012, 2012 35th IEEE/CPMT International Electronics Manufacturing Technology Conference (IEMT).

[10]  Eric Rotenberg,et al.  Rationale for a 3D heterogeneous multi-core processor , 2013, 2013 IEEE 31st International Conference on Computer Design (ICCD).

[11]  Eric Rotenberg,et al.  3D-enabled customizable embedded computer (3DECC) , 2014, 2014 International 3D Systems Integration Conference (3DIC).

[12]  Karthikeyan Sankaralingam,et al.  Dark Silicon and the End of Multicore Scaling , 2012, IEEE Micro.

[13]  E. Chang,et al.  Changes of Electrical Characteristics for AlGaN/GaN HEMTs Under Uniaxial Tensile Strain , 2009, IEEE Electron Device Letters.

[14]  Paul D. Franzon,et al.  A 10.35 mW/GFlop stacked SAR DSP unit using fine-grain partitioned 3D integration , 2012, Proceedings of the IEEE 2012 Custom Integrated Circuits Conference.