Overview of candidate device technologies for storage-class memory

Abstract

Storage-class memory (SCM) combines the benefits of a solidstate memory, such as high performance and robustness, with the archival capabilities and low cost of conventional hard-disk magnetic storage. Such a device would require a solid-state nonvolatile memory technology that could be manufactured at an extremely high effective areal density using some combination of sublithographic patterning techniques, multiple bits per cell, and multiple layers of devices. We review the candidate solid-state nonvolatile memory technologies that potentially could be used to construct such an SCM. We discuss evolutionary extensions of conventional flash memory, such as SONOS (silicon-oxide-nitrideoxide-silicon) and nanotraps, as well as a number of revolutionary new memory technologies. We review the capabilities of ferroelectric, magnetic, phase-change, and resistive random-access memories, including perovskites and solid electrolytes, and finally organic and polymeric memory. The potential for practical scaling to ultrahigh effective areal density for each of these candidate technologies is then compared.

Role of activation energy in resistance drift of amorphous phase change materials

“…Memory technologies based on phase change materials have been anticipated to fill a technological gap between DRAM and Flash as a fast, non-volatile memory technology [1,2]. These memory technologies are based on the large resistivity contrast between the two phases of the active material-mostly chalcogenide alloys such as Ge 2 Sb 2 Te 5 .…”

Understanding the Impact of BPRAM on Incremental Checkpoint

“…First, PCM is byte-addressable as DRAM. Second, it is a persistent storage like disk and flash, and up to four orders of magnitude faster than flash [20]- [23]. According to recent research, the read latency of PCM can be as fast as 10 ns [24] and the write latency can be as fast as 100 ns [22].…”

Storage-class memory: The next storage system technology

“…The industry is currently studying three techniques that are expected to yield such memories: multilayers [12], multibit cells [13], and sublithographic addressing and patterning [14]. In their article in this journal issue, Burr et al [2] provide an overview of SCM candidate device technologies and then compare them in terms of their potential for scaling to ultrahigh areal density [2]. Of the many SCM technologies described in their paper, the one that seems to be in the best position to replace the current flash technology and serve as SCM in the next decade is phasechange memory (PCM) [15,16].…”

“…Research and development efforts are underway worldwide on several nonvolatile memory technologies that not only complement the existing memory and storage hierarchy but also reduce the distinctions between memory (fast, expensive, evanescent) and storage (slow, inexpensive, permanent). An overview of these technologies appears as a companion paper [2] in this issue of the IBM Journal of Research and Development. One or more of these technologies may eventually replace disks and perhaps even DRAM.…”