The pros and cons of four alternative memory architectures that could be coupled to SFQ-based processors.
Cryogenic, superconducting digital processors offer the promise of greatly reduced operating power for server-class computing systems. This is due to the exceptionally low energy per operation
of Single Flux Quantum circuits built from Josephson junction devices operating at the temperature of 4 Kelvin. Unfortunately, no suitable same-temperature memory technology yet exists to complement these SFQ logic technologies. Possible memory technologies are in the early stages of development but will take years to reach the cost per bit and capacity capabilities of current semiconductor memory. We discuss the pros and cons of four alternative memory architectures that could be coupled to SFQ-based processors. Our feasibility studies indicate that cold memories built from CMOS DRAM and operating at 77K can support superconducting processors at low cost-per-bit, and that they can do so today.
Click here to continue reading.
New architectures, different markets and more variables make it increasingly difficult to design and verify low-power chips.
How good are standard FPGAs for AI purposes, and how different will dedicated FPGA-based devices be from them?
Seventeen startups took in mega-rounds of $100 million or more during October, with a cumulative total of just over $3.2 billion.
More nodes and alternative memories are in the works, but schedules remain murky.
Sixteen startups attracted funding rounds of nine figures in November.
New architectures, different markets and more variables make it increasingly difficult to design and verify low-power chips.
New materials, new architectures and higher density have limited what can be done with DRAM, but it’s still king (Experts At The Table Part 3)
Can the processor/memory bottleneck be closed, or do applications need to be re-architected to avoid it?
As chips grow in size, optimizing performance and power requires a bunch of new options and methodology changes.
The design of the power delivery network just got a lot more complicated, and designers can no longer rely on margining when things become vertical.
Through QED-C, the U.S. government helps build industry support behind quantum computing.
Arm’s CEO examines the impact of an explosion of data at the edge, 5G and heterogeneous architectures.
What are the worst-case conditions for a chip, and should you worry about them? Of course, it is a little more complicated than that.
Leave a Reply