Reducing thermal hotspots in microprocessors with expanded component sizing

Increasing on-chip temperature in SoC designs has reinforced the need for Dynamic Thermal Management (DTM). The conventional DTM techniques adopted in microprocessors based on DVFS are not suitable in the context of SoCs as they tend to have multiple voltage and frequency domains. In this paper we propose a reactive and a predictive DTM technique using bus arbitration. Based on the thermal profile the bus grants and hence the bus transactions are controlled. This regulates the data flow which reduces the activity in the functional units. The results show that the on-chip temperature can be maintained 3–5°C below the chip temperature threshold with a worst case performance penalty of 5% and a fast response time of at most 5 clock cycles. The hardware cost of implementing the proposed scheme is 3619.7μm2 in 45nm technology, which is less than 0.06% of the chip area. Apart from its simplicity, lower cost and effectiveness, the solution is non-intrusive on the design and scalable to many cores.

Performance evaluation metrics for ring-oscillator-based temperature sensors on FPGAs: A quality factor

A 128 K/spl times/8-b CMOS SRAM is described which achieves a 25-ns access time, less than 40-mA active current at 10 MHz, and 2-/spl mu/A standby current. The novel bit-line circuitry (loading-free bit line), using two kinds of NMOSFETs with different threshold voltages, improves bit-line signal speed and integrity. The two-stage local amplification technique minimizes the data-line delay. The dynamic double-word-line scheme (DDWL) allows the cell array to be divided into 32 sections along the word-line direction without a huge increase in chip area. This allows the DDWL scheme to reduce the core-area delay time and operating power to about half that of other conventional structures. A double-metal 0.8-/spl mu/m twin-tub CMOS technology has been developed to realize the 5.6/spl times/9.5-/spl mu//SUP 2/ cell size and the 6.86/spl times/15.37-mm/SUP 2/ chip size.

We describe application-specific extensions for fuzzy processing to a general purpose processor. The application-specific instruction set extensions were defined and evaluated using hardware/software codesign techniques. Based on this approach, we have extended the MIPS instruction set architecture with only a few new instructions to significantly speed up fuzzy computation with no increase of the processor cycle time and with only minor increase in chip area. The processor is implemented using a reconfigurable processor core which was designed as a starting point for application-specific processor designs to be used in embedded applications. Performance is presented for three representative applications of varying complexity.

In this paper, we present a complete chip design method which incorporates a soft-macro resynthesis method in interaction with chip floorplanning for area and timing improvements. We develop a timing-driven design flow to exploit the interaction between HDL synthesis and physical design tasks. During each design iteration, we resynthesize soft macros with either a relaxed or a tightened timing constraint which is guided by the post-layout timing information. The goal is to produce area-efficient designs while satisfying the timing constraints. Experiments on a number of industrial designs have demonstrated that by effectively relaxing the timing constraint of the non-critical modules and tightening the timing constraint of the critical modules, a design can achieve 13% to 30% timing improvements with little to no increase in chip area.

Long error detection latency, the time elapsed from the occurrence of an error caused by a bug to its manifestation as an observable failure, severely limits the effectiveness of existing post-silicon validation and debug techniques. Traditional post-silicon validation tests can incur very long error detection latencies of millions or even billions of clock cycles. An earlier technique called Quick Error Detection (QED) shortens error detection latencies to only few hundred (or thousand) clock cycles. However, software-only QED (i.e., QED implemented entirely in software) can result in significantly increased post-silicon validation test runtimes. We present a new technique called Fast QED that overcomes this drawback of software-only QED, while preserving the error detection latency and bug coverage benefits of software-only QED. Simulation results using an OpenSPARC T2-like multi-core SoC and bugs abstracted from multiple commercial multi-core SoCs demonstrate: 1. Fast QED achieves 4 orders of magnitude improvement in test runtime as compared to software-only QED, with only 0.4% increase in chip area; 2. Fast QED improves error detection latencies by up to 5 orders of magnitude compared to non-QED tests, and also achieves improved error detection latencies compared to software-only QED; and, 3. Fast QED improves bug coverage by up to 2-fold compared to non-QED tests (similar to software-only QED).

Due to technology advances and complexity of designs, thermal issue is a bottleneck in electronics designs. Various dynamic thermal management techniques have been proposed to address this issue. To effectively apply thermal management techniques, providing an accurate thermal map of chips is highly required. For this goal, a network of temperature sensors ought to be provided. There are various implementations for temperature sensors and network of sensors on Field Programmable Gate Arrays (FPGAs). This work defines and formulates four metrics and criteria, in terms of area, thermal, and power overheads and thermal map accuracy for exploring and evaluating efficiency of different implementations of Ring Oscillator-based Temperature Sensor (ROTS) networks on FPGAs and reports the comparison results for 12 networks with various sensor configurations. According to our metrics and experiments, the sensor that it is composed of NOT gates with open latches and RNS ring counter has lower thermal and power overheads compared to other configurations. Moreover, in this work, a new ROTS is presented that occupies 25% less resources than the most compact temperature sensor. Also, it provides 1.72 times higher sensitivity than the best sensitive ROTS design.

Designing temperature-aware microarchitectures for microprocessors at new technologies is becoming a critical requirement due to the exponentially increasing on-chip power density. Extremely high power density, thus the very high on-chip temperature, not only significantly increases the packaging and cooling costs, but also creates tremendous difficulties in chip leakage control and reliability. Being a major contributor to chip transistor budget and die area, caches account for a significant share of the overall processor power consumption, including both dynamic and leakage power. This work analyzes the thermal behavior of subarrays within a conventional data cache when running a set of applications from the SPEC2000 benchmark suite, and proposes two new subarraying schemes, namely, the separated scheme and the interleaved scheme, to improve the thermal behavior of subarrays in terms of more predictable behavior and reduced subarray temperatures. These optimizations can be also combined with dynamic thermal management (DTM) techniques to further improve the efficiency of thermal management. The impact of leakage control on the subarray thermal behavior is also evaluated.

The three-dimensional Network-on-Chip (3D NoC) has been proposed to solve the complex on-chip communication issues. However, the thermal problems become more exacerbated because of the larger power density and the heterogeneous thermal conductance in different silicon layer of 3D NoC. To regulate the system temperature, the Dynamic Thermal Management (DTM) techniques will be triggered when the device is thermal-emergent. However, these kinds of reactive DTM schemes result in significant system performance degradation. In this paper, we propose a proactive DTM with vertical throttling (PDTM-VT) scheme, which is controlled by the distributed Thermal Management Unit (TMU) of each NoC node. Based on the expected temperature resulted from the proposed thermal prediction model, the TMU can early control the temperature of the thermal-emergent device. The experimental results show that the proposed thermal prediction model has less than 0.25% prediction error against actual temperature measurement within 50ms. Besides, the PDTM-VT can reduce 11.84%~23.18% thermal-emergent nodes and improve 0.47%~47.90% network throughput.

As CMOS technology scales down towards nanometer regime and the supply voltage approaches the threshold voltage, increase in operating temperature results in increased circuit current, which in turn reduces circuit propagation delay. This paper exploits this new phenomenon, known as inverse thermal dependence (ITD) for power, performance, and temperature optimization in processor architecture. ITD changes the maximum achievable operating frequency of the processor at high temperatures. Dynamic thermal management techniques such as activity migration, dynamic voltage frequency scaling, and throttling are revisited in this paper, with a focus on the effect of ITD. Results are obtained using the predictive technology models of 7nm, 10nm 14nm and 20nm technology nodes and with extensive architectural and circuit simulations. The results show that based on the design goals, various design corners should be re-investigated for power, performance and energy-efficiency optimization. Architectural simulations for a multi-core processor and across standard benchmarks show that utilizing ITD-aware schemes for thermal management improves the performance of the processor in terms of speed and energy-delay-product by 8.55% and 4.4%, respectively.

in increased on-chip temperature leading to serious concerns about lifetime reliability of micro-processors. Though dynamic thermal management techniques can control peak temperature, they often fail to meet the reliability targets due to the complex interplay between temperature and reliability. In this paper, we propose a dynamic reliability management (DRM) technique that exploits architectural adaptation in conjunction with dynamic voltage/frequency scaling (DVFS). We employ an online Bayesian classifier that can efficiently detect the reliable configurations, while a performance prediction model selects the one with best performance among all the reliable configurations. We later extend our approach to meet both reliability and thermal constraints. Experimental results reveal that our adaptive DRM technique achieves reliability targets while reducing performance overhead by 42.30 % compared to DVFS and 28.68 % compared to DVFS with fetch gating. I.

Dynamic Thermal Management techniques have been widely accepted as a thermal solution for their low cost and simplicity. The techniques have been used to manage the heat dissipation and operating temperature to avoid thermal emergencies, but are not aware of application behavior in Chip Multiprocessors (CMPs). In this paper, we propose a temperature-aware scheduler based on applications' thermal behavior groups classified by a K-means clustering method in multicore systems. The application's thermal behavior group has similar thermal pattern as well as thermal parameters.With these thermal behavior groups, we provide thermal balances among cores with negligible performance overhead. We implement and evaluate our schemes in the 4-core (Intel Quad Core Q6600) and 8-core (two Quad Core Intel XEON E5310 processors) systems running several benchmarks. The experimental results show that the temperature-aware scheduler based on thermal behavior grouping reduces the peak temperature by up to 8degC and 5degC in our 4-core system and 8-core system with only 12% and 7.52% performance overhead, respectively, compared to L.inux standard scheduler.

The amazing integration densities achieved by current submicron technologies pay the price of increasing static power dissipation with the corresponding rise in heat density. Dynamic thermal management (DTM) techniques provide thermal-efficient solutions to balance or equally distribute possible on-chip hot spots. Accurate sensing of on-chip temperature is required by optimally allocating smart temperature sensors in the silicon. In this paper, we introduce an ultra low-power (1.05 - 65.5 nW at 5 samples/s) tiny (10250 mum2) CMOS smart temperature sensor based on the thermal dependency of the leakage current. The proposed sensor outperforms all previous works, as far as area and power consumption are concerned (more than 85% reduction in both cases), while still meeting the accuracy constraints imposed by target application domains. Furthermore, a specific interface based on the use of a logarithmic counter has been implemented to digitalize the temperature sensing. These facts, in conjunction with the full compatibility of the sensor with standard CMOS processes, allow the easy integration of many of these tiny sensors in any VLSI layout, making them specially suitable for modern DTM implementations.

Dynamic thermal management (DTM) techniques of three‐dimensional (3D) Network‐on‐Chips (NoCs) are employed to rescue the chip from thermal difficulties. Reactive routing algorithms, which utilise router throttling technique as a popular DTM, disregard distribution of heat generation of routers resulting in more throttled routers as well as long packet delays in throttled processing elements. This study proposes a reactive routing algorithm for 3D NoCs to (i) dynamically detour packets from hot zones containing throttled routers and (ii) minimise the number of required router throttling in the network. The proposed routing algorithm defines two virtual networks to enhance the path diversity for packets in each layer of 3D NoCs. The selection of diverse paths distributes heat generation to alleviate the thermal variance. The proposed routing algorithm is analysed by turn model to achieve deadlock freedom. Access Noxim simulator is also used to evaluate the performance and the thermal behaviour of the proposed routing algorithm in the variety of conditions. Results show that the proposed routing algorithm improves temperature variance by 9–39% and reduces number of throttled routers by 16–86%, which is achieved at the cost of one extra virtual channel per each physical channel in the XY ‐plane.

Multi-core processors have become an integral part of mainstream high performance computer systems. In parallel, exponentially increasing power density and packaging costs have necessitated system level thermal management solutions for multi-core systems. Dynamic thermal management (DTM) techniques monitor on-chip temperature continuously and typically employs dynamic voltage and frequency scaling (DVFS) to lower the temperature when it exceeds a pre-defined threshold. State-of-the-art DTM solutions for multi-core systems include distributed DVFS (where each core can scale the voltage/frequency individually) and global DVFS (where all cores scale voltage/frequency simultaneously). Distributed DVFS generally offers higher performance than global DVFS, but it is hard to implement and has major scalability issues.