Search for: All records

The variety of new electronic packaging technologies has grown significantly over the last 20 years as a result of market demands for higher device performance at lower costs and in less space. Those demands have pushed for heterogeneous packaging, where computer chips with different stack heights are closely packed, creating nonuniform heat flux and temperature and additional challenges for thermal management. Without implementing an appropriate thermal management strategy for heterogeneous packages, large temperature gradients can be observed within the package, which would increase the thermal stresses on the chip and raise reliability issues. To mimic this real-life scenario of such packaging, an experimental setup was designed and built. The design of the new experimental setup consists of four identical 1.2 cm × 1.2 cm ceramic heaters, each of which is connected to a separate power supply and can reach a heat flux of 140 W/cm2. Accordingly, this mock package is capable of delivering different power levels to mimic different multicore microprocessor conditions. To give the heater the ability to move precisely in the x-, y-, and z-directions, each heater is mounted to an XYZ linear stage. Deionized water (DI) was used as the working fluid, and a pin-fin heat sink was used to run the initial steady-state tests on the experimental rig. The tests showed how different flow rates at a constant fluid temperature and input power affect the temperatures of the heaters and the thermohydraulic performance of the heat sink. In addition, a three-dimensional numerical model has been developed and validated with experimental data in terms of heat sink pressure drop and the temperatures of the heaters. 

The ability of traditional room-conditioning systems to accommodate expanding information technology loads is limited in contemporary data centers (DCs), where the storage, storing, and processing of data have grown quickly as a result of evolving technological trends and rising demand for online services, which has led to an increase in the amount of waste heat generated by IT equipment. Through the implementation of hybrid air and liquid cooling technologies, targeted, on-demand cooling is made possible by employing a variety of techniques, which include but are not limited to in-row, overhead, and rear door heat exchanger (HX) cooling systems. One of the most common liquid cooling techniques will be examined in this study based on different conditions for high-power density racks (+50 kW). This paper investigates the cooling performance of a liquid-to-air in-row coolant distribution unit (CDU) in test racks containing seven thermal test vehicles (TTVs) under various conditions, focusing on cooling capacity and HX effectiveness under different supply air temperatures (SAT). This test rig has the necessary instruments to monitor and analyze the experiments on both the liquid coolant and the air sides. Moreover, another experiment is conducted to assess the performance of the CDU that runs under different control fan schemes, as well as how the change of the control type will affect the supply fluid temperature and the TTV case temperatures at 10%, 50%, and 100% of the total power. Finally, suggestions for the best control fan scheme to use for these systems and units are provided at the conclusion of the study. 

Abstract Demand is growing for the dense and high-performing IT computing capacity to support artificial intelligence, deep learning, machine learning, autonomous cars, the Internet of Things, etc. This led to an unprecedented growth in transistor density for high-end CPUs and GPUs, creating thermal design power (TDP) of even more than 700 watts for some of the NVIDIA existing GPUs. Cooling these high TDP chips with air cooling comes with a cost of the higher form factor of servers and noise produced by server fans close to the permissible limit. Direct-to-chip cold plate-based liquid cooling is highly efficient and becoming more reliable as the advancement in technology is taking place. Several components are used in the liquid-cooled data centers for the deployment of cold plate-based direct-to-chip liquid cooling like cooling loops, rack manifolds, CDUs, row manifolds, quick disconnects, flow control valves, etc. Row manifolds used in liquid cooling are used to distribute secondary coolant to the rack manifolds. Characterizing these row manifolds to understand the pressure drops and flow distribution for better data center design and energy efficiency is important. In this paper, the methodology is developed to characterize the row manifolds. Water-based coolant Propylene glycol 25% was used as the coolant for the experiments and experiments were conducted at 21 °C coolant supply temperature. Two, six-port row manifolds' P-Q curves were generated, and the value of supply pressure and the flowrate were measured at each port. The results obtained from the experiments were validated by a technique called flow network modeling (FNM). FNM technique uses the overall flow and thermal characteristics to represent the behavior of individual components. 

Data center cooling systems have undergone a major transformation in the persistent pursuit of better performance and lower energy use. Liquid cooling systems, particularly direct-to-chip systems, have emerged as a promising solution to address the increasing heat dissipation challenges. One critical component of such systems is the filtration mechanism, responsible for safeguarding the integrity and efficiency of the cooling process. These factors are pivotal in ensuring the reliable and sustainable operation of liquid cooling systems in high-demand applications, where electronic components continually push the boundaries of heat generation. This study undertakes a thorough examination of filters of different mesh size used in direct-to-chip liquid cooling systems. The research is multifaceted, encompassing the evaluation of filter performance, pressure drop characteristics, and long-term durability. The methodology employed in this research combines testing with a coolant distribution unit and rack setup to provide a holistic perspective on filter functionality. Findings from this study shed light on the key parameters that influence filter performance. Ultimately, the results of this research promise to contribute significantly to the advancement of direct-to-chip liquid cooling systems, facilitating the continued evolution of electronics in diverse fields, such as high-performance computing, data centers, and emerging technologies. With a focus on enhancing system reliability, efficiency, and sustainability, this study seeks to provide a valuable resource for engineers and researchers in the pursuit of effective cooling solutions for cutting-edge electronic applications. 

Owing to the dramatic increase in IT power density and energy consumption, the data center (DC) sector has started adopting thermally- and energy-efficient liquid cooling methods. This study examines a single-phase direct-to-chip liquid cooling approach for three high-heat-density racks, utilizing two liquid-to-air (L2A) cooled coolant distribution units (CDUs) and a combined total heat load of 128 kW. An experimental setup was developed to test different types of CDUs, cooling loops, and thermal testing vehicles (TTVs) for different operating conditions. IR images and the collected data were used to investigate the effect of air recirculation between cold and hot aisle containments on the CDU’s performance and stability of supply air temperature (SAT). Three different types of cooling loops (X, Y, and Z) were characterized thermally and hydraulically. Results show that Type Y has the lowest cold plate thermal resistance and pressure drop, among others. In a later test that included a single rack at a heat load of 53 kW and a single CDU, the heat capture ratio for fluid was found to be 94%. Experiments show that using blanking panels on the back of the racks limits hot air recirculation and maintains a steady SAT in the cold aisle. Finally, the CDU performance was evaluated at a high heat load for the three racks at 128 kW, and the average cooling capacity of the units is 58.6 kW, and the effectiveness values for CDU 1 and CDU 2 are 0.83 and 0.82, respectively. 

As the online frameworks and services are growing rapidly with the evolution of web-based Artificial Intelligence (AI) applications, server rooms are upgrading in computational capacity and size to keep up with these demands. Enterprise companies with their limited capacity server rooms struggle to keep up with these increasing computational demands. Hence, some of them end up outsourcing their servers to co-located facilities (Co-Lo) and the others choose to upgrade their existing server rooms. Correspondingly, the thermal load associated with such upgrades is typically tremendous. Approximately around 40% of the power consumed by datacentres is dissipated as heat. Conventional HVAC systems fail to satisfy the requirements of such server capacities. Not only do they struggle to fulfil the cooling load, but their maldistribution of cool air into the server room forms a major cause for hotspots formation. To tackle this issue, Liquid-to-Air (L2A) Coolant Distribution Units (CDUs) are being used as a liquid-based cooling solution for rack-level cooling. This type of CDUs provide efficient cooling for servers through liquid coolant that is distributed into cooling loops mounted on top of each server board. The generated heat is curried away using this liquid coolant back to the CDU, which then dissipates it into the surrounding air using dedicated pumps, fans, and heat exchanger, hence the name Liquid-to-Air. In the present work, one of the most popular liquid cooling strategies is explored based on various scenarios. the performance of a 24-kW liquid to Air (L2A) CDU is judged based on cooling effect, stability, and reliability. The study is curried out experimentally, in which a test rack with three thermal test vehicles (TTVs) are used to investigate various operation scenarios. Both liquid coolant and air sides of this experimental setup are equipped with the required instrumentations to monitor and analyse the tests. All test cases were taken in a room with limited air conditioning to resemble the environment of upgraded server rooms with conventional AC systems. Moreover, the impact of using such high-power density cooling unit on the server room environment with restricted HVAC system is also brought to light. Environmental and human comfort parameters such as noise, air velocity, and ambient temperature are measured under various operation conditions and benchmarked against their ranges for human comfort as listed in ASHREE standards. At the end of this research, recommendations for best practice are provided along with areas of enhancement for the selected system. 

Effective cooling is crucial for high-power liquid-cooled servers to ensure optimal performance and reliability ofcomponents. Thermal characterization is necessary to ensure that the cooling system functions as intended, is energy efficient, and minimizes downtime. In this study, a proposed methodology for thermal characterization of a high-powerliquid-cooled server/TTV [server and TTVs (thermal test vehicle) are used interchangeably] is presented. The server layout includes multiple thermal test vehicle setups equipped with direct-to-chip cold plates, with two or more connected in series to form a TTV cooling loop. These cooling loops are connected in parallel to the supply and return plenums of the cooling loop manifold, which includes a chassis-level flow distribution manifold. To obtain accurate measurements, two identical server/TTV prototypes are instrumented with sensors for coolant flow rate and temperature measurements for every TTV cooling loop. Four ultrasonic flow sensors are installed in the flow verification server/TTV to measure the coolant flow rate to each TTV cooling loop. In the thermal verification server, thermistors are installed at the outlet of each GPU heater of TTV cooling loop to log temperature measurements. The amount of heat captured by the coolant in each TTV cooling loop is subsequently estimated based on the flow rates determined from the flow verification server.This methodology enables precise characterization of the thermal performance of high-power liquid-cooled servers,ensuring optimal functionality, energy efficiency, and minimized downtime. 

Abstract Direct Liquid Cooling (DLC) has emerged as a promising technology for thermal management of high-performance computing servers, enabling efficient heat dissipation and reliable operation. Thermal performance is governed by several factors, including the coolant physical properties and flow parameters such as coolant inlet temperature and flow rate. The design and development of the coolant distribution manifold to the Information Technology Equipment (ITE) can significantly impact the overall performance of the computing system. This paper aims to investigate the hydraulic characterization and design validation of a rack-level coolant distribution manifold or rack manifold. To achieve this goal, a custom-built high power-density liquid-cooled ITE rack was assembled, and various cooling loops were plugged into the rack manifold to validate its thermal performance. The rack manifold is responsible for distributing the coolant to each of these cooling loops, which is pumped by a CDU (Coolant Distribution Unit). In this study, pressure drop characteristics of the rack manifold were obtained for flow rates that effectively dissipate the heat loads from the ITE. The pressure drop is a critical parameter in the design of the coolant distribution manifold since it influences the flow rate and ultimately the thermal performance of the system. By measuring the pressure drop at various flow rates, the researchers can accurately determine the optimum flow rate for efficient heat dissipation. Furthermore, 1D flow network and CFD models of the rack-level coolant loop, including the rack manifold, were developed, and validated against experimental test data. The validated models provide a useful tool for the design of facility-level modeling of a liquid-cooled data center. The CFD models enable the researchers to simulate the fluid flow and heat transfer within the cooling system accurately. These models can help to design the coolant distribution manifold at facility level. The results of this study demonstrate the importance of the design and development of the coolant distribution manifold in the thermal performance of a liquid-cooled data center. The study also highlights the usefulness of 1D flow network and CFD models for designing and validating liquid-cooled data center cooling systems. In conclusion, the hydraulic characterization and design validation of a rack-level coolant distribution manifold is critical in achieving efficient thermal management of high-performance computing servers. This study presents a comprehensive approach for hydraulic characterization of the coolant distribution manifold, which can significantly impact the overall thermal performance and reliability of the system. The validated models also provide a useful tool for the design of facility-level modeling of a liquid-cooled data center. 

Abstract Due to the increasing computational demand driven by artificial intelligence, machine learning, and the Internet of Things (IoT), there has been an unprecedented growth in transistor density for high-end CPUs and GPUs. This growth has resulted in high thermal dissipation power (TDP) and high heat flux, necessitating the adoption of advanced cooling technologies to minimize thermal resistance and optimize cooling efficiency. Among these technologies, direct-to-chip cold plate-based liquid cooling has emerged as a preferred choice in electronics cooling due to its efficiency and cost-effectiveness. In this context, different types of single-phase liquid coolants, such as propylene glycol (PG), ethylene glycol (EG), DI water, treated water, and nanofluids, have been utilized in the market. These coolants, manufactured by different companies, incorporate various inhibitors and chemicals to enhance long-term performance, prevent biogrowth, and provide corrosion resistance. However, the additives used in these coolants can impact their thermal performance, even when the base coolant is the same. This paper aims to compare these coolant types and evaluate the performance of the same coolant from different vendors. The selection of coolants in this study is based on their performance, compatibility with wetted materials, reliability during extended operation, and environmental impact, following the guidelines set by ASHRAE. To conduct the experiments, a single cold plate-based benchtop setup was constructed, utilizing a thermal test vehicle (TTV), pump, reservoir, flow sensor, pressure sensors, thermocouple, data acquisition units, and heat exchanger. Each coolant was tested using a dedicated cold plate, and thorough cleaning procedures were carried out before each experiment. The experiments were conducted under consistent boundary conditions, with a TTV power of 1000 watts and varying coolant flow rates (ranging from 0.5 lpm to 2 lpm) and supply coolant temperatures (17°C, 25°C, 35°C, and 45°C), simulating warm water cooling. The thermal resistance (Rth) versus flow rate and pressure drop (ΔP) versus flow rate graphs were obtained for each coolant, and the impact of different supply coolant temperatures on pressure drop was characterized. The data collected from this study will be utilized to calculate the Total Cost of Ownership (TCO) in future research, providing insights into the impact of coolant selection at the data center level. There is limited research available on the reliability used in direct-to-chip liquid cooling, and there is currently no standardized methodology for testing their reliability. This study aims to fill this gap by focusing on the reliability of coolants, specifically propylene glycols at concentrations of 25%. To analyze the effectiveness of corrosion inhibitors in these coolants, ASTM standard D1384 apparatus, typically used for testing engine coolant corrosion inhibitors on metal samples in controlled laboratory settings, was employed. The setup involved immersing samples of wetted materials (copper, solder coated brass, brass, steel, cast iron, and cast aluminum) in separate jars containing inhibited propylene glycol solutions from different vendors. This test will determine the reliability difference between the same inhibited solutions from different vendors. 

Semiconductor thermal management is becoming a bottleneck challenge that restricts further development in the electronics industry. Compromising processor thermal requirements will impact the processor performance and reliability. Heat sinks are designed to increase the available surface area of an electronic component and allow for more heat to be easily dissipated. As a result, the thermal characterization of the heat sinks plays a critical role in electronics thermal management. In this study, a flexible experimental apparatus is designed, built, and assembled to characterize and test various electronics components in different aerodynamics and thermal conditions. This novel experimental apparatus allows for controlled characterization of the various heat sinks with different heights as well as realistic scenarios with air bypass at server level. Moreover, a general guideline on precise experimental procedure to characterize air cooled heat sinks is developed. The results show that introduced method reduces the experimental error by 26%.