SearcharxivSearch

arXiv · 1605.00045

Routability in 3D IC Design: Monolithic 3D vs. Skybridge 3D CMOS

Abstract

Conventional 2D CMOS technology is reaching fundamental scaling limits, and interconnect bottleneck is dominating integrated circuit (IC) power and performance. While 3D IC technologies using Through Silicon Via or Monolithic Inter-layer Via alleviate some of these challenges, they follow a similar layout and routing mindset as 2D CMOS. This is insufficient to address routing requirements in high-density 3D ICs and even causes severe routing congestion at large-scale designs, limiting their benefits and scalability. Skybridge is a recently proposed fine-grained 3D IC fabric relying on vertical nanowires that presents a paradigm shift for scaling, while addressing associated 3D connectivity and manufacturability challenges. Skybridge's core fabric components enable a new 3D IC design approach with vertically-composed logic gates, and provide a greater degree of routing flexibility compared to conventional 2D and 3D ICs leading to much larger benefits and future scalability. In this paper, we present a methodology using relevant metrics to evaluate and quantify the benefits of Skybridge vs. state-of-the-art transistor-level monolithic 3D IC (T-MI) and 2D in terms of routability and its impact on large-scale circuits. This is enabled by a new device-to-system design flow with commercial CAD tools that we developed for large-scale Skybridge IC designs in 16nm node. Evaluation for standard benchmark circuits shows that Skybridge yields up to 1.6x lower routing demand against T-MI with no routing congestion (routing demand to resource ratio < 1) at all metal layers. This 3D routability in conjunction with compact vertical gate design in Skybridge translate into benefits of up to 3x lower power and 11x higher density over 2D CMOS, while TLM-3DIC approach only has up to 22% power saving and 2x density improvement over 2D CMOS.

Explore related subjects

Keep this discovery

BibTeXRIS

Jiajun Shi, Mingyu Li, Santosh Khasanvis, Mostafizur Rahman, Csaba Andras Moritz. 2016-04-29. Routability in 3D IC Design: Monolithic 3D vs. Skybridge 3D CMOS. https://arxiv.org/abs/1605.00045

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

From Grid to Chip: Power Architecture, Stability, and Flexibility of AI Data Centers

The rapid growth of artificial intelligence (AI) computing is transforming data centers into large, dynamic electrical loads. Their deployment is primarily constrained by energy availability and grid-connection capacity, which is further aggravated by the ability of power-delivery architectures, control systems, and computing workloads to operate reliably during fast grid disturbances. This article presents a technological perspective on AI data centers as grid-interactive computing systems. First, it reviews grid-integration bottlenecks, evolving connection policies, grid-code requirements, which has fostered new technological trends via spatio-temporal flexibility available through workload orchestration, cooling systems, on-site resources, and energy storage. Second, it maps the evolution of power-delivery architectures from medium-voltage grid interfaces to chip-level, discussing higher-voltage DC distribution, solid-state transformers, wide-bandgap devices, advanced chip-level power delivery, and liquid cooling. Third, it establishes a three-level stability framework spanning rack-level DC-bus dynamics, facility-level converter interactions, and system-level grid-coupled behavior. The framework connects dominant instability mechanisms, including constant power load effects, impedance interactions, forced oscillations, and operating-mode transitions, with suitable modeling, assessment, and mitigation approaches. Synthesizing these topics, this article highlights grid-to-chip co-design as a central requirement for scalable AI infrastructure, linking computing workloads, power-delivery systems, energy buffers, and grid operation.

cs.ET

A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs

Artificial neural networks rely on vector-matrix multiplications (VMMs), whose implementation in von Neumann architectures is dominated by costly data movement between memory and processing units. Spiking neural networks (SNNs) mitigate this bottleneck by performing in-memory, analog VMMs using memristive crossbar arrays. However, conventional current-mode readout circuits incur significant area and power overhead. This work proposes a fully analog readout architecture based on voltage-to-time conversion of the VMM output. By sensing the column voltage, the proposed approach avoids current-mode summing and scaling circuitry, improving area and energy efficiency. Post-layout simulations of a 10x1 SNN implemented in a 130 nm CMOS technology validate the proposed architecture, while application to a trained 64x10 SNN for digit classification further demonstrates its feasibility for SNN inference.

cs.ET

Fractional-order hardware for neuromorphic computing: Is the order really the problem?

Does a neuromorphic system need a true power-law memory kernel, and if so, can anyone build one? Neuromorphic systems process signals spanning many timescales at once, from milliseconds to tens of seconds. Integer-order circuits buy each additional timescale with an additional state variable. Fractional-order dynamics offer a different bargain: one operator whose power-law kernel carries a continuum of timescales, tuned by one parameter, the order alpha. A fractional derivative is non-local, so evaluating it costs storage and arithmetic that grow with the retained history, where an integer-order derivative costs a constant. This review organizes the hardware literature around that cost. We derive the retained history needed to hold the truncation error below a tolerance epsilon, show that it scales as epsilon^(-1/alpha), and set beside it a second and independent limit on the direct form: in fixed point the weights themselves underflow, so word length caps the usable history however long the buffer is. The two limits move at very different rates with the order, and where they cross decides whether a word length can serve an order at all. We use both to sort published hardware into three strategies, note a fourth the numerical literature has developed and this hardware has not, and survey digital, analog and device work. Along the way we ask whether the field is worried about the right obstacle. It is not. Fabricated constant-phase devices already span the orders two groups identify as task-optimal, so the order gap has largely closed, leaving a residual gap near 0.1 and at the lower order describing cortical adaptation. What remains is a frequency-band gap of about three decades at the low end. That corner is not empty, since double-layer electrodes work there, but every device in it is discrete, and no integrable thin-film element has been characterized there.

cs.ET