Kanad Ghose
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kanad Ghose has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Bahgat Sammakia
Department of Mechanical Engineering, Binghamton University-SUNY, Binghamton, NY 13902
3 shared publications - Dereje Agonafer
Department of Mechanical and Aerospace Engineering, The University of Texas at Arlington , Arlington, TX 76019
3 shared publications Bahgat Sammakia
Mechanical Engineering Department , State University of New York at Binghamton , Binghamton , New York , USA
2 shared publications- Cristina Amon
University of Toronto, Toronto, ON, M5S3G8, Canada
2 shared publications - Gamal Refai-Ahmed
Advanced Micro Devices, Inc., Markham, ON, L3t 7X6, Canada
2 shared publications - Saket Karajgikar
The University of Texas at Arlington, Arlington, TX
2 shared publications
Latest Publications
- 9 May 2018
- Published by ASME International in Journal of Electronic Packaging
- Vol. 140 (2)
Failure Analysis of Direct Liquid Cooling System in Data Centers
In this paper, the impact of direct liquid cooling (DLC) system failure on the information technology (IT) equipment is studied experimentally. The main factors that are anticipated to affect the IT equipment response during failure are the central processing unit (CPU) utilization, coolant set point temperature (SPT), and the server type. These factors are varied experimentally and the IT equipment response is studied in terms of chip temperature and power, CPU utilization, and total server power. It was found that failure of this cooling system is hazardous and can lead to data center shutdown in less than a minute. Additionally, the CPU frequency throttling mechanism was found to be vital to understand the change in chip temperature, power, and utilization. Other mechanisms associated with high temperatures were also observed such as the leakage power and the fans' speed change. Finally, possible remedies are proposed to reduce the probability and the consequences of the cooling system failure.
- 9 May 2018
- Published by ASME International in Journal of Electronic Packaging
- Vol. 140 (2)
Failure Analysis of Direct Liquid Cooling System in Data Centers
In this paper, the impact of direct liquid cooling (DLC) system failure on the information technology (IT) equipment is studied experimentally. The main factors that are anticipated to affect the IT equipment response during failure are the central processing unit (CPU) utilization, coolant set point temperature (SPT), and the server type. These factors are varied experimentally and the IT equipment response is studied in terms of chip temperature and power, CPU utilization, and total server power. It was found that failure of this cooling system is hazardous and can lead to data center shutdown in less than a minute. Additionally, the CPU frequency throttling mechanism was found to be vital to understand the change in chip temperature, power, and utilization. Other mechanisms associated with high temperatures were also observed such as the leakage power and the fans' speed change. Finally, possible remedies are proposed to reduce the probability and the consequences of the cooling system failure.
- 5 November 2013
- Published by ASME International in Journal of Electronic Packaging
- Vol. 135 (4) , 041006
Solving Thermal Issues in a Three-Dimensional-Stacked-Quad-Core Processor by Microprocessor Floor Planning, Microchannel Cooling, and Insertion of Through-Silicon-Vias
The electronics industry is heading toward the three-dimensional (3D) microprocessor to cope with higher computing workloads. The 3D stacking of the processor and the memory components reduces the communication delay in multicore system-on-a-chip (SoCs), owing to reduced system size and shorter interconnects. The shorter interconnects in a multicore system lowers the memory access latencies and contributes to improvements in memory access bandwidth. The shorter interconnects in stacked architectures also enables small drivers for interconnections which further reduce interconnection-level-energy dissipations. On the down side, the 3D-stacked architectures have high thermal resistance, which in conjunction with poor thermal management techniques, poses a thermal threat to the reliability of the device. This paper establishes the significance of the microprocessor floor planning and single-phase microchannel cooling for solving the thermal issues arising in the 3D-stacked-quad-core processor. The 3D-stacked-quad-core processor considered in this study comprises of symmetric nonuniformly powered quad-core processor, liquid-cooled microchannel heat sink, dynamic random access memory (DRAM), thermal interface material (TIM), and heat spreader. The electrical through-silicon-vias (TSVs) between the processor and DRAM serve as interconnects, while the thermal TSVs reduce the internal thermal resistance. The effective cooling of the 3D-stacked-quad-core processor depends on the TSVs, quad-core layout and the optimized design of the microchannel heat sink for the desired coolant. The microchannel cooling of the 3D-stacked processor is done both by planar flow and impingement flow. The thermal efficiency of the cooling techniques is evaluated on the basis of hot spot temperature, hot spot spread, and number of hot spots.
- 5 November 2013
- Published by ASME International in Journal of Electronic Packaging
- Vol. 135 (4) , 041006
Solving Thermal Issues in a Three-Dimensional-Stacked-Quad-Core Processor by Microprocessor Floor Planning, Microchannel Cooling, and Insertion of Through-Silicon-Vias
The electronics industry is heading toward the three-dimensional (3D) microprocessor to cope with higher computing workloads. The 3D stacking of the processor and the memory components reduces the communication delay in multicore system-on-a-chip (SoCs), owing to reduced system size and shorter interconnects. The shorter interconnects in a multicore system lowers the memory access latencies and contributes to improvements in memory access bandwidth. The shorter interconnects in stacked architectures also enables small drivers for interconnections which further reduce interconnection-level-energy dissipations. On the down side, the 3D-stacked architectures have high thermal resistance, which in conjunction with poor thermal management techniques, poses a thermal threat to the reliability of the device. This paper establishes the significance of the microprocessor floor planning and single-phase microchannel cooling for solving the thermal issues arising in the 3D-stacked-quad-core processor. The 3D-stacked-quad-core processor considered in this study comprises of symmetric nonuniformly powered quad-core processor, liquid-cooled microchannel heat sink, dynamic random access memory (DRAM), thermal interface material (TIM), and heat spreader. The electrical through-silicon-vias (TSVs) between the processor and DRAM serve as interconnects, while the thermal TSVs reduce the internal thermal resistance. The effective cooling of the 3D-stacked-quad-core processor depends on the TSVs, quad-core layout and the optimized design of the microchannel heat sink for the desired coolant. The microchannel cooling of the 3D-stacked processor is done both by planar flow and impingement flow. The thermal efficiency of the cooling techniques is evaluated on the basis of hot spot temperature, hot spot spread, and number of hot spots.
- 1 June 2010
- Published by ASME International in Journal of Electronic Packaging
- Vol. 132 (2) , 021008
Multi-Objective Optimization to Improve Both Thermal and Device Performance of a Nonuniformly Powered Micro-Architecture
Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, and memory controller has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional units dissipate little or no power. This highly nonuniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effects on computer performance, product reliability, and yield. Moving the functional units may reduce the junction temperature but can affect performance by a factor as much as 30%. In this paper, a multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. The analysis was performed for 90 nm Pentium IV Northwood architecture operating at 3 GHz clock speed. Each functional unit on the die has a specific role, so functional units with similar roles were grouped together. Thus, the actual Pentium IV die was divided into four groups (front end, execution cores, bus and L2, and out-of-order engine). Repositioning constraints were determined using circuit delay models of major functional units in a micro-architectural simulator. Thus, depending on the scenario, relocating functional units can result in virtually no performance loss (less than 2% is assumed to be minimal and is reported as 0%) to as much as 30% performance loss. From the results, the minimum and the maximum temperatures were and . This corresponds to thermal design power of 60.2 W. For microprocessors with higher thermal design power (115 W) and operating at higher clock speed, higher can be realized. Based on this paper’s analysis, the optimized scenario resulted in a junction temperature of at the cost of a 14% performance loss.- 1 June 2010
- Published by ASME International in Journal of Electronic Packaging
- Vol. 132 (2) , 021008
Multi-Objective Optimization to Improve Both Thermal and Device Performance of a Nonuniformly Powered Micro-Architecture
Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, and memory controller has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional units dissipate little or no power. This highly nonuniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effects on computer performance, product reliability, and yield. Moving the functional units may reduce the junction temperature but can affect performance by a factor as much as 30%. In this paper, a multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. The analysis was performed for 90 nm Pentium IV Northwood architecture operating at 3 GHz clock speed. Each functional unit on the die has a specific role, so functional units with similar roles were grouped together. Thus, the actual Pentium IV die was divided into four groups (front end, execution cores, bus and L2, and out-of-order engine). Repositioning constraints were determined using circuit delay models of major functional units in a micro-architectural simulator. Thus, depending on the scenario, relocating functional units can result in virtually no performance loss (less than 2% is assumed to be minimal and is reported as 0%) to as much as 30% performance loss. From the results, the minimum and the maximum temperatures were and . This corresponds to thermal design power of 60.2 W. For microprocessors with higher thermal design power (115 W) and operating at higher clock speed, higher can be realized. Based on this paper’s analysis, the optimized scenario resulted in a junction temperature of at the cost of a 14% performance loss.- 1 January 2009
- Published by ASME International
- p. 111-118
Development of a Numerical Model for Non-Uniformly Powered Die to Improve Both Thermal and Device Clock Performance
Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, memory controller, etc. has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional blocks dissipate little or no power. This highly non-uniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effect on computer performance and product reliability as well as yield. Moving the functional blocks may reduce the junction temperature but can also affect the performance by a factor as high as 35%. In this paper, multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. From the results, the minimum and the maximum temperature was 82.4°C and 94.5°C with a corresponding penalty on the performance of 35% and 0% respectively. The optimized location of the functional blocks resulted in a temperature of 83.2°C for a performance loss of 5%.
- 1 January 2009
- Published by ASME International
- p. 111-118
Development of a Numerical Model for Non-Uniformly Powered Die to Improve Both Thermal and Device Clock Performance
Integration of different functional components such as level two (L2) cache memory, high-speed I/O interfaces, memory controller, etc. has enhanced microprocessor performance. In this architecture, certain functional units on the microprocessor dissipate a significant fraction of the total power while other functional blocks dissipate little or no power. This highly non-uniform power distribution results in a large temperature gradient with localized hot spots that may have detrimental effect on computer performance and product reliability as well as yield. Moving the functional blocks may reduce the junction temperature but can also affect the performance by a factor as high as 35%. In this paper, multi-objective optimization is performed to minimize the junction temperature without significantly altering the computer performance. From the results, the minimum and the maximum temperature was 82.4°C and 94.5°C with a corresponding penalty on the performance of 35% and 0% respectively. The optimized location of the functional blocks resulted in a temperature of 83.2°C for a performance loss of 5%.
- 1 January 2009
- Published by Taylor & Francis in Heat Transfer Engineering
- Vol. 30 (1-2) , 43-53
Comparative Analysis of Microchannel Heat Sink Configurations Subject to a Pressure Constraint
Leakage losses and ever-increasing power dissipation in the microprocessor are causing significant thermal, mechanical, and reliability problems. Conventional cooling methods are reaching their practical limits, and new methods of lowering the operating temperature of microprocessors are being explored. Microfluidics-based cooling schemes are one approach being considered. The implementation of microchannels for forced convection at the chip level shows much promise, as the effective heat transfer surface area and attainable heat flux are very favorable. A major design limitation to such an implementation is the pressure developed within such micro-flows and the stresses that could result. In this study, multiple discrete microchannel heat sink configurations are analyzed computationally and compared in a cooling capability sense, while total pressure drop across the flows is carefully considered. A single cooling channel over an energy source is split into two smaller channels, and so on, while total pressure drop is maintained constant, and specified such that all flows remain in the laminar regime. It is shown that for the configurations analyzed, there exists multiple-dependence optimum cooling configurations. In addition, it is shown that a slimmer design may be implemented with a relatively small effect on cooling capability. Furthermore, cooling capability dependence on total pressure drop of the flows is shown to be minimal for high-performing microchannel configurations.
- 1 January 2009
- Published by Taylor & Francis in Heat Transfer Engineering
- Vol. 30 (1-2) , 43-53
Comparative Analysis of Microchannel Heat Sink Configurations Subject to a Pressure Constraint
Leakage losses and ever-increasing power dissipation in the microprocessor are causing significant thermal, mechanical, and reliability problems. Conventional cooling methods are reaching their practical limits, and new methods of lowering the operating temperature of microprocessors are being explored. Microfluidics-based cooling schemes are one approach being considered. The implementation of microchannels for forced convection at the chip level shows much promise, as the effective heat transfer surface area and attainable heat flux are very favorable. A major design limitation to such an implementation is the pressure developed within such micro-flows and the stresses that could result. In this study, multiple discrete microchannel heat sink configurations are analyzed computationally and compared in a cooling capability sense, while total pressure drop across the flows is carefully considered. A single cooling channel over an energy source is split into two smaller channels, and so on, while total pressure drop is maintained constant, and specified such that all flows remain in the laminar regime. It is shown that for the configurations analyzed, there exists multiple-dependence optimum cooling configurations. In addition, it is shown that a slimmer design may be implemented with a relatively small effect on cooling capability. Furthermore, cooling capability dependence on total pressure drop of the flows is shown to be minimal for high-performing microchannel configurations.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Securing Grid Data Transfer Services with Active Network Portals
Widely available and utilized grid servers are vulnerable to a variety of threats from denial of service (DoS) attacks, overloading caused by flash crowds, and compromised client machines. The focus of our paper is the design, implementation and evaluation of a set of admission control policies that permit the server to maintain sustained throughput to legitimate clients even in the face of such overloads and attacks. We propose several schemes to effectively, and importantly in an automated fashion, deal with these attacks and overloads. We discuss how these schemes can be efficiently implemented on an active network adapter based gateway that controls access to a pool of backend data servers. Performance tests conducted on a system based on a dual-ported active NIC demonstrate that efficient optimization schemes can be implemented on such a gateway to minimize the grid service response time and to improve server throughputs under heavy loads and DoS attacks. Our results, using the gridFTP server available with Globus Toolkit 4.0.1, demonstrate that even in adverse load conditions, the response times can be maintained at a level similar to normal, low-load conditions.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Securing Grid Data Transfer Services with Active Network Portals
Widely available and utilized grid servers are vulnerable to a variety of threats from denial of service (DoS) attacks, overloading caused by flash crowds, and compromised client machines. The focus of our paper is the design, implementation and evaluation of a set of admission control policies that permit the server to maintain sustained throughput to legitimate clients even in the face of such overloads and attacks. We propose several schemes to effectively, and importantly in an automated fashion, deal with these attacks and overloads. We discuss how these schemes can be efficiently implemented on an active network adapter based gateway that controls access to a pool of backend data servers. Performance tests conducted on a system based on a dual-ported active NIC demonstrate that efficient optimization schemes can be implemented on such a gateway to minimize the grid service response time and to improve server throughputs under heavy loads and DoS attacks. Our results, using the gridFTP server available with Globus Toolkit 4.0.1, demonstrate that even in adverse load conditions, the response times can be maintained at a level similar to normal, low-load conditions.
- 1 January 1996
- Published by Springer Nature
- p. 291-294
Bottom-Up Scheduling with Wormhole and Circuit Switched Routing
- 1 January 1996
- Published by Springer Nature
- p. 291-294
Bottom-Up Scheduling with Wormhole and Circuit Switched Routing
- 1 August 1994
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 151-154
A Bottom-Up Approach to Task Scheduling on Distributed Memory Multiprocessors
This paper presents a new approach to statically schedule parallel programs modeled as Directed Acyclic Graphs (DAGs) on various distributed memory multi-processor topologies represented as processor graphs to reduce the overall execution time of the program. The scheduler factors in the processor topology, communication delays and delays due to channel conflicts for scheduling. Our scheme differs dramatically from existing schedulers in that tasks of the DAG are scheduled bottom up. Experimental results presentedfor message switched systems using the hypercube and torus topologies show the effectiveness of our scheme. Our scheme can also be adapted for other topologies and routing schemes such as wormhole routing and circuit switching.
- 1 August 1994
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 151-154
A Bottom-Up Approach to Task Scheduling on Distributed Memory Multiprocessors
This paper presents a new approach to statically schedule parallel programs modeled as Directed Acyclic Graphs (DAGs) on various distributed memory multi-processor topologies represented as processor graphs to reduce the overall execution time of the program. The scheduler factors in the processor topology, communication delays and delays due to channel conflicts for scheduling. Our scheme differs dramatically from existing schedulers in that tasks of the DAG are scheduled bottom up. Experimental results presentedfor message switched systems using the hypercube and torus topologies show the effectiveness of our scheme. Our scheme can also be adapted for other topologies and routing schemes such as wormhole routing and circuit switching.
- 30 July 1994
- Published by Elsevier in Microprocessing and Microprogramming
- Vol. 40 (6) , 387-410
The architecture of response-pipelined content addressable memories
- 30 July 1994
- Published by Elsevier in Microprocessing and Microprogramming
- Vol. 40 (6) , 387-410
The architecture of response-pipelined content addressable memories