Modern computing devices employ High-Bandwidth Memory (HBM) to meet their memory bandwidth requirements. An HBM-enabled device consists of multiple DRAM layers stacked on top of one another next to a compute chip (e.g, CPU, GPU, and FPGA) in the same package. Although such HBM structures provide high bandwidth at a small form factor, the stacked memory layers consume a substantial portion of the package's power budget. Therefore, power-saving techniques that preserve the performance of HBM are desirable. Undervolting is one such technique: it reduces the supply voltage to decrease power consumption without reducing the device's operating frequency to avoid performance loss. Undervolting takes advantage of voltage guardbands put in place by ...
Abstract—Power density has become the limiting factor in technology scaling as power budget restrict...
Power density has become the limiting factor in technology scaling as power budget restricts the amo...
The memory subsystem is responsible for a large fraction of the energy consumed by compute nodes in ...
Modern computing devices employ High-Bandwidth Memory (HBM) to meet their memory bandwidth requireme...
High Bandwidth Memory (HBM) has been introduced as a solution to DRAMs’ bandwidth and power ineffici...
The power and energy efficiency of Field Programmable Gate Arrays (FPGAs) are estimated to be up to ...
In this work, we evaluate aggressive undervolting, i.e., voltage scaling below the nominal level to ...
The power consumption of digital circuits, e.g., Field Programmable Gate Arrays (FPGAs), is directly...
In this work, we evaluate aggressive undervolting, i.e., voltage scaling below the nominal level to...
As the semiconductor roadmap reaches smaller feature sizes and the end of Dennard Scaling, design go...
©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for al...
In this work, we evaluate aggressive undervolting, i.e., voltage underscaling below the nominal leve...
Abstract—Energy efficiency and resilience are two crucial challenges for HPC systems to reach exasca...
Due to quadratic dependence of switching power on supply power, supply scaling leads to significant ...
One of the most effective techniques to reduce a processor\u27s power consumption is to reduce suppl...
Abstract—Power density has become the limiting factor in technology scaling as power budget restrict...
Power density has become the limiting factor in technology scaling as power budget restricts the amo...
The memory subsystem is responsible for a large fraction of the energy consumed by compute nodes in ...
Modern computing devices employ High-Bandwidth Memory (HBM) to meet their memory bandwidth requireme...
High Bandwidth Memory (HBM) has been introduced as a solution to DRAMs’ bandwidth and power ineffici...
The power and energy efficiency of Field Programmable Gate Arrays (FPGAs) are estimated to be up to ...
In this work, we evaluate aggressive undervolting, i.e., voltage scaling below the nominal level to ...
The power consumption of digital circuits, e.g., Field Programmable Gate Arrays (FPGAs), is directly...
In this work, we evaluate aggressive undervolting, i.e., voltage scaling below the nominal level to...
As the semiconductor roadmap reaches smaller feature sizes and the end of Dennard Scaling, design go...
©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for al...
In this work, we evaluate aggressive undervolting, i.e., voltage underscaling below the nominal leve...
Abstract—Energy efficiency and resilience are two crucial challenges for HPC systems to reach exasca...
Due to quadratic dependence of switching power on supply power, supply scaling leads to significant ...
One of the most effective techniques to reduce a processor\u27s power consumption is to reduce suppl...
Abstract—Power density has become the limiting factor in technology scaling as power budget restrict...
Power density has become the limiting factor in technology scaling as power budget restricts the amo...
The memory subsystem is responsible for a large fraction of the energy consumed by compute nodes in ...