Author Archives: Nicole Hemsoth
Author Archives: Nicole Hemsoth
Over the last few years we have detailed the explosion in new machine learning systems with the influx of novel architectures from deep learning chip startups to efforts from vendors and hyperscalers alike. …
One Deep Learning Benchmark to Rule Them All was written by Nicole Hemsoth at .
The Texas Advanced Computing Center (TACC) will soon be home to a top-tier supercomputer with the 2019 arrival of the “Frontera” system. …
Cascade Lake at Heart of 2019 TACC Supercomputer was written by Nicole Hemsoth at .
The last decade, and few years in particular, have brought a bevy of new architectures to bear for a market keen to understand what comes after Moore’s Law. …
A Rogues Gallery of Post-Moore’s Law Options was written by Nicole Hemsoth at .
FPGAs might not have carved out a niche in the deep learning training space the way some might have expected but the low power, high frequency needs of AI inference fit the curve of reprogrammable hardware quite well. …
Xilinx Unveils xDNN FPGA Architecture for AI Inference was written by Nicole Hemsoth at .
Another Hot Chips conference has ended with yet another deep learning architecture to consider. …
A Mythic Approach to Deep Learning Inference was written by Nicole Hemsoth at .
The relationship between quantum computers and supercomputing will be more complementary than competitive in the coming years with quantum processors being the offload engines for some key workloads in materials science and other areas. …
Quantum Simulation Work Blazes Trail for Hybrid Systems was written by Nicole Hemsoth at .
There have been several chip startups over the last few years that have sought to new ways to train and execute neural networks efficiently, but why reinvent the wheel when each idea has yielded at least one small piece of a much bigger performance picture? …
Arm Stands on Shoulders of Giants with First Generation AI Processor was written by Nicole Hemsoth at .
There is much value in separating storage from compute, particular for cloud database deployments. …
Alibaba Rolls Own Distributed File System for Cloud Database Performance was written by Nicole Hemsoth at .
The use of FPGAs in HPC is limited less by the capabilities of current hardware and more by the challenges in programming them without sacrificing performance. …
OpenCL Optimizations Make Case for FPGAs in HPC was written by Nicole Hemsoth at .
A research team from Nvidia has provided interesting insight about using mixed precision on deep learning training across very large training sets and how performance and scalability are affected by working with a batch size of 32,000 using recurrent neural networks. …
Nvidia DGX1-V Appliance Crushes NLP Training Baselines was written by Nicole Hemsoth at .
This year at the International Supercomputing Conference we detailed some of the major quantum computing development efforts, including updates from the Microsoft team on the Q# language, and the academic Project Q environment. …
QISKit Developments Key to IBM Quantum Engagement was written by Nicole Hemsoth at .
A working group formed on behalf of the Exascale Computing Project (ECP) in the U.S. …
The State of MPI for Future Exascale Systems was written by Nicole Hemsoth at .
At the height of the Hadoop era there were countless storage and analytics startups based on the Hadoop Distributed File System (HDFS), several of which were backed by venture capital firm Andreessen Horowitz, which was committed to the Hadoop and open source-driven big data startup cause when that was all the rage in 2010 until around 2014 or so. …
Pulling Storage Together at Extreme Scale was written by Nicole Hemsoth at .
Big things can often fit into small packages, especially if those packages are tightly bound. …
Bringing Back the Mighty Chiplet was written by Nicole Hemsoth at .
There has been much written about the potential for FPGAs to take a leadership role in accelerating deep learning but in practice, the hurdles of getting from concept to high performance hardware design are still taller than many AI shops are willing to scale, particularly when GPUs dominate in training and in a pinch, standard CPUs will do just fine for datacenter inference since they involve little developer overhead. …
Intel FPGA Architecture Focuses on Deep Learning Inference was written by Nicole Hemsoth at .
This morning at Google Next computer architecture pioneers, John Hennessey and David Patterson, remarked that even though it could be revolutionary, quantum computing is still at least a decade away. …
Fault Tolerance at Heart of Google’s Quantum Strategy was written by Nicole Hemsoth at .
As the rubber begins to meet the road for quantum computing, the conversation is shifting from one about the practicality of hardware to how future users will interface with quantum systems. …
Toward Open, Extensible Quantum Programming was written by Nicole Hemsoth at .
Despite some of the inherent complexities of using FPGAs for implementing deep neural networks, there is a strong efficiency case for using reprogrammable devices for both training and inference. …
Clearing the TensorFlow to FPGA Path was written by Nicole Hemsoth at .
When it comes to building extreme scale computing platforms, there are plenty of system design options but in supercomputing, the only practical choice for an OS is Linux. …
Replacing Linux with a Database System was written by Nicole Hemsoth at .
Quantum systems will not replace traditional supercomputers anytime soon but for certain types of simulations, they will be far more efficient and scalable than classical machines, at least according to CEO of quantum computer maker D-Wave, Vern Brownell. …
D-Wave CEO on Future of Quantum Simulations was written by Nicole Hemsoth at .