中文 English

Moving Intelligence To The Edge


The buildout of the edge is driving a slew of new challenges and opportunities across the chip industry. Sailesh Chittipeddi, executive vice president at Renesas Electronics America, talks about the shift toward more AI-centric workloads rather than CPU-centric, why embedded computing is becoming the foundation of all intelligences, and the importance of software, security, and user experience ... » read more

Seven Hardware Advances We Need to Enable The AI Revolution


The potential, positive impact AI will have on society at large is impossible to overestimate. Pervasive AI, however, remains a challenge. Training algorithms can take inordinate amounts of power, time, and computing capacity. Inference will also become more taxing with applications such as medical imaging and robotics. Applied Materials estimates that AI could consume up to 25% of global elect... » read more

1.6 Tb/s Ethernet Challenges


Moving data at blazing fast speeds sounds good in theory, but it raises a number of design challenges. John Swanson, senior product marketing manager for high-performance computing digital IP at Synopsys, talks about the impact of next-generation Ethernet on switches, the types of data that need to be considered, the causes of data growth, and the size and structure of data centers, both in the... » read more

Optimization Driving Changes In Microarchitectures


The semiconductor ecosystem is at a turning point for how to best architect the CPU based on the explosion of data, the increased usage of AI, and the need for differentiation and customization in leading-edge applications. In the past, much of this would have been accomplished by moving to the next process node. But with the benefits from scaling diminishing at each new node, the focus is s... » read more

SpZip: Architectural Support for Effective Data Compression In Irregular Applications


Technical paper link is here. Published in: 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA) Yifan Yang (MIT); Joel Emer (MIT / NVIDIA); Daniel Sanchez (MIT) Abstract: "Irregular applications, such as graph analytics and sparse linear algebra, exhibit frequent indirect, data-dependent accesses to single or short sequences of elements that cause high ma... » read more

Efficient Multi-GPU Shared Memory via Automatic Optimization of Fine-Grained Transfers


Harini Muthukrishnan (U of Michigan); David Nellans, Daniel Lustig (NVIDIA); Jeffrey A. Fessler, Thomas Wenisch (U of Michigan). Abstract—"Despite continuing research into inter-GPU communication mechanisms, extracting performance from multiGPU systems remains a significant challenge. Inter-GPU communication via bulk DMA-based transfers exposes data transfer latency on the GPU’s critical... » read more

Thermal Challenges And Moore’s Law


Steven Woo, fellow and distinguished inventor at Rambus, looks at the evolution of graphics cards over a couple of decades and how designs changed to deal with more graphics and more heat, and why smaller, faster and cheaper doesn’t apply in this market. » read more

Machine Learning Inferencing At The Edge


Ian Bratt, fellow in Arm's machine learning group, talks about why machine learning inferencing at the edge is so difficult, what are the tradeoffs, how to optimize data movement, how to accelerate that movement, and how it differs from developing other types of processors. » read more