Solar Bommai - A school to have Acquaintance in Engineering

At The Next FPGA Platform event in January there were several conversations about what roles reconfigurable hardware will play in the future of deep learning. While inference was definitely the target of most of what was discussed, there is ample opportunity across the spectrum for acceleration but that changes with the type of neural network. Martin Ferianc a machine learning researcher at University College London says that FPGAs have advantages in power consumption, which makes them suitable for applications with energy constraints. Secondly, the reconfigurability of FPGA makes it an ideal hardware platform when the algorithm changes frequently, especially for deep learning.  Thirdly, compared with SIMD hardware such as GPU, FPGA usually has higher latency performance because it allows custom architecture design. These advantages shift depending on the type of neural network but to Ferianc and his team, CNNs are a perfect fit for FPGA. His team are exploring performance es...

RF GaN is growing, but will it ever make it in phones? NOVEMBER 21ST, 2019 - BY:  MARK LAPEDUS Wide-bandgap semiconductors are hot topics these days. One wide-bandgap semi type–silicon carbide (SiC)–is the talk of the town and is gaining steam in electric vehicles and other systems. But let’s not forget about gallium nitride (GaN). GaN, a binary III-V material, has 10 times the breakdown field strength with double the electron mobility than silicon. GaN is used for LEDs, power electronics and RF. While GaN-based power semiconductors are heating up, the RF version of GaN is taking off. In 2018, sales of RF GaN-enabled devices grew by nearly 22%, according to Strategy Analytics. By 2023, the RF GaN device market will surpass $1.7 billion, according to the firm. Cree, Qorvo and Sumitomo are among the big suppliers of RF GaN. For years, RF GaN was a niche-oriented technology used in the military/aerospace community, namely for radar. Then, the technology q...