Abstract:Negative Capacitance Field-Effect Transistor (NCFET) is an emerging technology that incorporates a ferroelectric layer within the transistor gate stack to overcome the fundamental limit of sub-threshold swing in transistors. Even though physics-based NCFET models have been recently proposed, system-level NCFET models do not exist and research is still in its infancy. In this work, we are the first to investigate the impact of NCFET on performance, energy and cooling costs in many-core processors. Our proposed … Show more
“…NCFET fundamentally changes the characteristics of transistors and therefore also changes the performance and power of circuits [19], single-core processors [1], and many-core processors [15]. This section demonstrates the impact of the thickness of the ferroelectric layer on the power and performance of a many-core processor.…”
Section: Performance Power and Cooling Trade-offs With Ncfet-based mentioning
confidence: 96%
“…Power and timing signoffs are performed for different NCFET configurations (TFE1 to TFE4) and different operating voltages. Further details of the experimental setup can be found in [15]. Figure 8.2a shows how NCFET increases the performance of a processor.…”
Section: Processor-level Investigationmentioning
confidence: 99%
“…We thereby scale the leakage and dynamic power that is estimated by McPAT to estimate the power consumption of NCFETbased many-cores. For brevity, details on this approach are omitted here and can be found in [15].…”
Section: Simulation Of Ncfet-based Many-corementioning
confidence: 99%
“…Figure 8.4 shows the thermally sustainable utilization of two benchmarks bodytrack and swaptions during the parallel section of the benchmarks (Region of Interest) for different NCFET technologies. Other benchmarks are available in [15]. Swaptions is a highly compute-intensive task, which results in high power consumption and therefore, the thermally sustainable utilization in the baseline is low (only 8 out of 25 cores).…”
Section: Impact Of Ncfet On Performancementioning
confidence: 99%
“…These investigations show that the optimal thickness of the ferroelectric layer depends on the application characteristics. Further investigations on how NCFET affects the performance in the case that cores are not operated at the peak V/f-levels can be read in [15]. These investigations additionally study forced-convection cooling (a heat sink with a fan) and reveal that the optimal thickness of the ferroelectric layer also depends on the cooling scenario.…”
“…NCFET fundamentally changes the characteristics of transistors and therefore also changes the performance and power of circuits [19], single-core processors [1], and many-core processors [15]. This section demonstrates the impact of the thickness of the ferroelectric layer on the power and performance of a many-core processor.…”
Section: Performance Power and Cooling Trade-offs With Ncfet-based mentioning
confidence: 96%
“…Power and timing signoffs are performed for different NCFET configurations (TFE1 to TFE4) and different operating voltages. Further details of the experimental setup can be found in [15]. Figure 8.2a shows how NCFET increases the performance of a processor.…”
Section: Processor-level Investigationmentioning
confidence: 99%
“…We thereby scale the leakage and dynamic power that is estimated by McPAT to estimate the power consumption of NCFETbased many-cores. For brevity, details on this approach are omitted here and can be found in [15].…”
Section: Simulation Of Ncfet-based Many-corementioning
confidence: 99%
“…Figure 8.4 shows the thermally sustainable utilization of two benchmarks bodytrack and swaptions during the parallel section of the benchmarks (Region of Interest) for different NCFET technologies. Other benchmarks are available in [15]. Swaptions is a highly compute-intensive task, which results in high power consumption and therefore, the thermally sustainable utilization in the baseline is low (only 8 out of 25 cores).…”
Section: Impact Of Ncfet On Performancementioning
confidence: 99%
“…These investigations show that the optimal thickness of the ferroelectric layer depends on the application characteristics. Further investigations on how NCFET affects the performance in the case that cores are not operated at the peak V/f-levels can be read in [15]. These investigations additionally study forced-convection cooling (a heat sink with a fan) and reveal that the optimal thickness of the ferroelectric layer also depends on the cooling scenario.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.