Macro Scale

Professor Bahl from the University of Illinois at Urbana-Champaign has developed a new RF transmitter capable of transmitting at frequencies below 3 kHz while exploiting the magnetic component of the electromagnetic field. Transmitting at these low frequencies while taking advantage of the magnetic component of the electromagnetic field will allow for transmission of RF signals through conductive material such as water or the ground. Prior technology for transmitting radio signals at such low frequencies required very large antenna structures along with a large power input. The current technology weighs less than 10 kg and fits in a backpack. This technology has applications in the military as well as oil exploration, mining, and anywhere else where data communication is desired underground or underwater.

The emergence of datacenters as single computer entities has made latency a critical consideration in designing datacenter networks. PCIe interconnect is known to be a latency bottleneck in communication networks as its overhead can contribute to up to 90% of the overall communication latency. PCIe is a standard motherboard interface, sending a packet over a conventional NIC requiring several PCIe and memory channel transactions. This data movement in the network software stacks consumes thousands of processor cycles, which ultimately prevent ultra-low latency networking.

Researchers eliminate NIC-PCIe transactions and instead use the local memory channels between the memory and NIC, resulting in reduced latency and improved data center computer performance (figure 1). This finding is the basis for NetDIMM, which is a method for integrating a network interface chip with the memory module of a computer.

Figure 1: State of the art network interface architectures vs. NetDIMM

On average, NetDIMM improves per packet latency by 49.9% compared with a baseline network deploying PCIe NICs (figure 2). The NetDIMM architecture is located in the memory module and does not require any change to the processor architecture or memory subsystem.

Figure 2: One-way network latency breakdown for packets of various sizes when using a PCIe NIC (left), an integrated NIC (middle), and NetDIMM (left). X-axis is not drawn to scale.

Most recently, NetDIMM was presented at the 52nd IEEE/ACM International Symposium on Microarchitecture in Columbus, Ohio. The conference publication can be accessed here.

Researchers at the University of Illinois Urbana-Champaign have developed a processor architecture that allows for greater efficiency in computing power and energy consumption. The architecture exploits parallelism through thread pipelining and an out-of-order loop system. This process is possible by utilizing more processing elements in the system. This method does create extra cost and is essentially a cost for efficiency trade-off. The system can be used in a variety of embedded systems such as CPUs and GPUs. The decrease in energy consumption can also be applied to servers and other large processing units that consumer a lot of energy and in the process and lot of heat.