Many architects believe that major improvements in cost-energy-performance must now
come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor …

The first-generation tensor processing unit (TPU) runs deep neural network (DNN) inference
15-30 times faster with 30-80 times better energy efficiency than contemporary CPUs and …

A domain-specific architecture for deep neural networks Page 1 50 COMMUNICATIONS OF
THE ACM | SEPTEMBER 2018 | VOL. 61 | NO. 9 contributed articles ILL US TRA TION B Y MA …

With rising network rates, cloud vendors increasingly deploy FPGA-based SmartNICs (F-
NICs), leveraging their inline processing capabilities to offload hypervisor networking …

The computing demand for massive applications has led to the ubiquitous deployment of
computing power. This trend results in the urgent need for higher-level computing resource …

The decline of computers as a general purpose technology Page 1 64 COMMUNICATIONS OF
THE ACM | MARCH 2021 | VOL. 64 | NO. 3 contributed articles ILL US TRA TION B Y THE IMA …

This paper discusses the role of Field Programmable Gate Array (FPGA) in Internet of Things
(IoT) applications. Benefits of FPGAs over ASICs and microcontrollers are emphasized to …

It is a triumph of technology and of economics that our computer chips are so universal.
Countless applications are only possible because of the staggering variety of calculations …

We propose a new system design for connecting hardware and FPGA accelerators to the
network, allowing the accelerator to directly control commodity Network Interface Cards …

As specialized hardware accelerators like FPGAs become a prominent part of the current
computing landscape, software applications are increasingly constructed to leverage …