Estimating the Energy Consumption of Emerging Random Access Memory Technologies
In this work, a model for estimating the energy consumption of different types of
random access memory(RAM) technologies, likely to be commercially available by
2017, has been developed. The goal for this model has been to evaluate which
of the memory technologies that will be the most energy efficient in 2017. This
was done by building the model on the required energies to read or write a bit for
the different technologies. The memory technologies that have been modelled are:
Dynamic RAM (DRAM), Static RAM (SRAM), Ferroelectric RAM (FeRAM),
Magnetic RAM (MRAM), Spin-Torque Transfer Magnetic RAM (STT-MRAM)
and Phase Change RAM (PCRAM).
The volatile memory technologies, DRAM and SRAM, have been estimated to
have the lowest energy consumption if the memories are operated at a high duty
cycle. However, if the duty cycle is reduced, the emerging non-volatile memory
technologies become more energy efficient. The FeRAM was estimated to have the
lowest power consumption when manufactured with the technology available today.
And it has been estimated that with a duty cycle lower than 8.5 × E−4, FeRAM
technology consumes less power than the SRAM, and with a duty cycle lower than
1.6 × E−4, the FeRAM consumes less power than DRAM. When looking forward
towards 2017, STT-MRAM was estimated to have the lowest power consumption
of the emerging memory technologies. It was estimated that the STT-MRAM consumes
less power than SRAM for duty cycles lower than 2.3 × E−2 and consumes
less power than the DRAM for duty cycles lower than 4.6 × E−4.
An experimental set-up has been developed to validate the model, and a case
study of some selected memories has been performed. With this case study some
limitations on the theoretical model have been pointed out. These limitations are
believed to be reduced if the memories are embedded on chip.
Place, publisher, year, edition, pages
Institutt for elektronikk og telekommunikasjon , 2013. , 257 p.
IdentifiersURN: urn:nbn:no:ntnu:diva-22566Local ID: ntnudaim:9897OAI: oai:DiVA.org:ntnu-22566DiVA: diva2:649811
Tybell, Thomas, ProfessorSyvertsen, Alf Petter