Building AI SoCs


Ron Lowman, strategic marketing manager at Synopsys, looks at where AI is being used and how to develop chips when the algorithms are in a state of almost constant change. That includes what moves to the edge versus the data center, how algorithms are being compressed, and what techniques are being used to speed up these chips and reduce power. https://youtu.be/d32jtdFwpcE    ... » read more

Machine Learning Shifts More Work to FPGAs, SoCs


A wave of machine-learning-optimized chips is expected to begin shipping in the next few months, but it will take time before data centers decide whether these new accelerators are worth adopting and whether they actually live up to claims of big gains in performance. There are numerous reports that silicon custom-designed for machine learning will deliver 100X the performance of current opt... » read more

Variation In Low-Power FinFET Designs


One of the biggest advantages of moving to the a leading edge process node is ultra-low voltage operation, where devices can achieve better performance using less power. But the latest generation process nodes also introduce a number of new challenges due to increased variation that can affect everything from signal integrity to manufacturing yield. While variation is generally well understo... » read more

The Week In Review: Design


M&A MIPS has reportedly been acquired again, this time by AI startup Wave Computing. Wave focuses on data center-based neural network training using its parallel dataflow processing architecture. In March, the company signed on to use 64-bit multi-threaded processor cores from MIPS in future projects. Previously, MIPS was owned by Tallwood Venture Capital, which acquired MIPS from Imaginat... » read more

eFPGAs Accelerate Data-Centric Processing


With the ever-increasing requirements to manage and process enterprise data, system architects are looking closer than ever at programmable logic, a technology to make computing much more efficient and secure. While traditional processors force data into their pipelines through a complex hierarchy of caches, programmable logic makes it possible to construct data pipelines. Data can flow seam... » read more

The Week in Review: IoT


Finance BroadLink has raised $54.4 million in Series D funding from Citic Private Equity Funds Management. Baidu and Libai Group participated in the new round. BroadLink will use the money to expand its artificial intelligence and Internet of Things units, while also acquiring or investing in companies involved in smart home devices. Aperio Systems of Haifa, Israel, has received $4.5 millio... » read more

The Data Center In 2018 And Beyond


As computing continues to evolve, a number of trends are continuing to challenge the design of conventional von Neumann architectures, and in turn are driving the development of new architectural approaches and technologies. These include the growing adoption of artificial intelligence (AI), machine learning, AR/VR, IoT, high-speed financial transactions, self-driving vehicles, and blockchain/c... » read more

Using FPGAs To Accelerate Data Centers


With the technology industry at a crossroads — the effective repeal of Mooreʹs Law and the stagnation and decline of PC, tablet, consumer electronics and smartphone markets — data centers have become the sweet spot of the technology sector, showing healthy revenue growth and attracting new system solutions in both hardware and software. Unlike the ethereal promise of upcoming wonders from ... » read more

24 x 7 Productivity


Emulators are now managed as a corporate-wide shared resource in a datacenter, but standard job management software does not allow companies to take full advantage of emulator resources and capabilities. The Veloce Enterprise Server App (Veloce ES) delivers a fully-integrated solution for complete, transparent access to emulation resources for concurrent projects worldwide. It significantly enh... » read more

New Ways To Scale Performance


Immense amounts of data are being collected today in areas such as meteorology, geology, astronomy, quantum physics, fluid dynamics, and pharmaceutical research. Exascale computing (the execution of a billion billion floating point operations, or exaFLOPs, per second) is the target that many HPC systems aspire to over the next 5 to 10 years. In addition, advances in data analytics and areas su... » read more

← Older posts