Dynamic On-Chip Thermal Optimization for Three-Dimensional Networks-On-Chip
TL;DR: An adaptive strategy to effectively diffuse heat throughout the 3D geometry that employs a dynamic programming network to select and optimize the direction of data manoeuvre in a network-on-chip (NoC).
Abstract: The complex thermal behaviour prohibits the advancement of three-dimensional (3D) very-large-scale integration system. Particularly, the high-density through-silicon via based integration could lead to ultra-high temperature hotspots and permanent silicon device damage. In this paper, we introduce an adaptive strategy to effectively diffuse heat throughout the 3D geometry. This strategy employs a dynamic programming network to select and optimize the direction of data manoeuvre in a network-on-chip (NoC). We also developed a tool, which is based on the accurate HotSpot thermal model and SystemC cycle accurate model, to simulate the thermal system and evaluate our approach. We found that the proposed approach can significantly diffuse the hotspots from a 3D geometry and overall temperature can be significantly reduced. Given the same thermal constraints, the throughput performance of an adaptive NoC can also be improved. This work enables a new avenue to explore the on-chip adaptability for the future large-scale 3D integration.
Citations
More filters
01 Oct 2014
TL;DR: A dynamic programming-based lifetime aware routing algorithm is proposed based on the lifetime budget metric, which has around 20%, 45%, 55% minimal MTTF improvement than XY routing, NoP routing, oddeven routing, respectively.
Abstract: Technology scaling leads to the reliability issue as a primary concern in Network-on-Chip (NoC) design. Due to the routing algorithms, some routers may age much faster than others, which becomes a bottleneck for system lifetime. In this paper, lifetime is modeled as a resource consumed over time. A metric lifetime budget is associated with each router, indicating the maximum allowed workload for current period. Since the heterogeneity in router lifetime reliability has strong correlation with the routing algorithm, we define a problem to optimize the lifetime by routing flits along the path with maximum lifetime budgets. A dynamic programming-based lifetime aware routing algorithm is proposed based on the lifetime budget metric. The dynamic programming network approach is employed to solve this problem with linear complexity. The experimental results show that the lifetime aware routing has around 20%, 45%, 55% minimal MTTF improvement than XY routing, NoP routing, oddeven routing, respectively.
13 citations
Additional excerpts
...The dynamic programming based adaptive routing has already been applied in congestion avoidance, fault tolerance [12], thermal management [13], etc....
[...]
TL;DR: A new runtime thermal management strategy to effectively diffuse and manage heat throughout 3D chip geometry for a better throughput performance in networks on chip (NoC), which outperforms conventional approaches in terms of computational efficiency and thermal stability.
Abstract: Complex thermal behavior inhibits the advancement of three-dimensional (3D) very-large-scale-integration (VLSI) system designs, as it could lead to ultra-high temperature hotspots and permanent silicon device damage. This article introduces a new runtime thermal management strategy to effectively diffuse and manage heat throughout 3D chip geometry for a better throughput performance in networks on chip (NoC). This strategy employs a dynamic programming-based runtime thermal management (DPRTM) policy to provide online thermal regulation. Reactive and proactive adaptive schemes are integrated to optimize the routing pathways depending on the critical temperature thresholds and traffic developments. Also, when the critical system thermal limit is violated, an urgent throttling will take place. The proposed DPRTM is rigorously evaluated through cycle-accurate simulations, and results show that the proposed approach outperforms conventional approaches in terms of computational efficiency and thermal stability. For example, the system throughput using the DPRTM approach can be improved by 33p when compared to other adaptive routing strategies for a given thermal constraint. Moreover, the DPRTM implementation presented in this article demonstrates that the hardware overhead is insignificant. This work opens a new avenue for exploring the on-chip adaptability and thermal regulation for future large-scale and 3D many-core integrations.
12 citations
TL;DR: Key ideas and research directions are classified, pointed out, and demonstrated with a reasonable amount of details that enables interested researchers to come up and grasp all research directions for thermal-aware NoC technologies.
8 citations
01 Nov 2014
TL;DR: This work proposes a cross-layer approach of optimizing the NoC topology to achieve a balanced traffic distribution and temperature-aware routing (TAR) scheme to avoid thermal hotspots and demonstrates that the proposed wireless NoC architecture is able to reduce temperature of NoC components and the TAR scheme is ability to restrict the temperatures near a target threshold value.
Abstract: Long-range wireless shortcuts in Network-on-Chip (NoC) architectures are shown to significantly improve energy-efficiency in on-chip data transfer. However, over-utilization of the wireless shortcuts and non-uniform traffic patterns may result in thermal hotpots in the NoC links or switches. In this work we propose a cross-layer approach of optimizing the NoC topology to achieve a balanced traffic distribution and temperature-aware routing (TAR) scheme to avoid thermal hotspots. We demonstrate that the proposed wireless NoC architecture is able to reduce temperature of NoC components and the TAR scheme is able to restrict the temperatures near a target threshold value.
7 citations
Cites background from "Dynamic On-Chip Thermal Optimizatio..."
...In [9], temperature-aware routing for 3D NoC architectures is proposed....
[...]
06 Oct 2014
TL;DR: This chapter proposes a dynamic programming-based lifetime-aware routing algorithm that has around 20 %, 45 %, 55 % minimal MTTF improvement than XY routing, NoP routing, and Oddeven routing, respectively.
Abstract: Technology scaling leads to the reliability issue as a primary concern in Networks-on-Chip (NoC) design. Due to routing algorithms, some routers may age much faster than others, which become a bottleneck for system lifetime. In this chapter, lifetime is modeled as a resource consumed over time. A metric lifetime budget is associated with each router, indicating the maximum allowed workload for current period. Since the heterogeneity in router lifetime reliability has strong correlation with the routing algorithm, we define a problem to optimize the lifetime by routing packets along the path with maximum lifetime budgets. A dynamic programming-based lifetime-aware routing algorithm is proposed to optimize the lifetime distribution of routers. The dynamic programming network approach is employed to solve this problem with linear complexity. The experimental results show that the lifetime-aware routing has around 20 %, 45 %, 55 % minimal MTTF improvement than XY routing, NoP routing, and Oddeven routing, respectively.
2 citations
Cites background from "Dynamic On-Chip Thermal Optimizatio..."
...[2] proposed to balance the temperature of NoC by a thermal-aware routing algorithm....
[...]
...Most prior studies consider thermal issues, with the objectives to balance the temperature or to take temperature as a constraint [2,13,23]....
[...]
...The dynamic programming based adaptive routing has already been applied in congestion avoidance [21], fault tolerance [35], thermal management [2], etc....
[...]
...Dynamic thermal management (DTM) techniques such as dynamic voltage and frequency scaling (DVFS) [13], adaptive routing [2] are employed to address the temperature issues....
[...]
References
More filters
TL;DR: Findings in this work indicate that dopaminergic neurons in the primate whose fluctuating output apparently signals changes or errors in the predictions of future salient and rewarding events can be understood through quantitative theories of adaptive optimizing control.
Abstract: The capacity to predict future events permits a creature to detect, model, and manipulate the causal structure of its interactions with its environment. Behavioral experiments suggest that learning is driven by changes in the expectations about future salient events such as rewards and punishments. Physiological work has recently complemented these studies by identifying dopaminergic neurons in the primate whose fluctuating output apparently signals changes or errors in the predictions of future salient and rewarding events. Taken together, these findings can be understood through quantitative theories of adaptive optimizing control.
8,163 citations
Book•
01 Mar 1998
TL;DR: In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.
Abstract: From the Publisher:
In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.
7,016 citations
TL;DR: In this article, a deadlock-free routing algorithm for arbitrary interconnection networks using the concept of virtual channels is presented, where the necessary and sufficient condition for deadlock free routing is the absence of cycles in a channel dependency graph.
Abstract: A deadlock-free routing algorithm can be generated for arbitrary interconnection networks using the concept of virtual channels. A necessary and sufficient condition for deadlock-free routing is the absence of cycles in a channel dependency graph. Given an arbitrary network and a routing function, the cycles of the channel dependency graph can be removed by splitting physical channels into groups of virtual channels. This method is used to develop deadlock-free routing algorithms for k-ary n-cubes, for cube-connected cycles, and for shuffle-exchange networks.
2,110 citations
Book•
01 Jun 1994
TL;DR: A deadlock-free routing algorithm can be generated for arbitrary interconnection networks using the concept of virtual channels, which is used to develop deadlocked routing algorithms for k-ary n-cubes, for cube-connected cycles, and for shuffle-exchange networks.
Abstract: A deadlock-free routing algorithm can be generated for arbitrary interconnection networks using the concept of virtual channels. A necessary and sufficient condition for deadlockfree routing is the absence of cycles in the channel dependency graph. Given an arbitrary network and a routing function, the cycles of the channel dependency graph can be removed by splitting physical channels into groups of virtual channels. This method is used to develop deadlock-free routing algorithms for k-ary n-cubes, for cube connected cycles, and for shuffle? exchange networks.
(This is a revised version of 5206-tr-86)
2,035 citations
01 May 2003
TL;DR: HotSpot is described, an accurate yet fast model based on an equivalent circuit of thermal resistances and capacitances that correspond to microarchitecture blocks and essential aspects of the thermal package that shows that power metrics are poor predictors of temperature, and that sensor imprecision has a substantial impact on the performance of DTM.
Abstract: With power density and hence cooling costs rising exponentially, processor packaging can no longer be designed for the worst case, and there is an urgent need for runtime processor-level techniques that can regulate operating temperature when the package's capacity is exceeded. Evaluating such techniques, however, requires a thermal model that is practical for architectural studies.This paper describes HotSpot, an accurate yet fast model based on an equivalent circuit of thermal resistances and capacitances that correspond to microarchitecture blocks and essential aspects of the thermal package. Validation was performed using finite-element simulation. The paper also introduces several effective methods for dynamic thermal management (DTM): "temperature-tracking" frequency scaling, localized toggling, and migrating computation to spare hardware units. Modeling temperature at the microarchitecture level also shows that power metrics are poor predictors of temperature, and that sensor imprecision has a substantial impact on the performance of DTM.
1,252 citations