Compute
Shedding Light on Dark Bandwidth
We have heard much about the concept of dark silicon but there is a separate, related companion to this idea. …
HBM
Compute
Squeezing The Joules Out Of DRAM, Possibly Without Stacking
Increasing parallelism is the only way to get more work out of a system. …
HPC
3D Memory Sparks New Thinking in HPC System Design
Whether being built for capacity or capability, the conventional wisdom about memory provisioning on the world’s fastest systems is changing quickly. …
Compute
Memory is the Next Platform
A new crop of applications is driving the market along some unexpected routes, in some cases bypassing the processor as the landmark for performance and efficiency. …
Compute
Baking Specialization into Hardware Cools CPU Concerns
As Moore’s Law spirals downward, ultra-high bandwidth memory matched with custom accelerators for specialized workloads might be the only saving grace for the pace of innovation we are accustomed to. …
AI
Deep Learning Architectures Hinge on Hybrid Memory Cube
We have heard about a great number of new architectures and approaches to scalable and efficient deep learning processing that sit outside of the standard CPU, GPU, and FPGA box and while each is different, many are leveraging a common element at all-important memory layer. …
Compute
Compute
Future Systems: What Will Tomorrow’s Server Look Like?
We can talk about storage and networking as much as we want, and about how the gravity of data bends infrastructure to its needs, but the server – or a collection of them loosely or tightly coupled – is still the real center of the datacenter. …
Compute
There Is No Such Thing As Memory Performance
Petar Radokjovic, who leads the memory systems division at the Barcelona Supercomputer Center, described his desk, messy with the latest research on next-generation memory systems for high performance computing, and says that for a time, the sight of them was enough to give him an ulcer. …
Control
A Wake Up Call for Hybrid Memory Cube Efficiency
There has been quite a bit of talk over the last couple of years about what role high bandwidth memory technologies like the Intel and Micron-backed Hybrid Memory Cube (HMC) might play in the future of both high performance computing nodes as well as in other devices, but the momentum is still somewhat slow, at least in terms of actual systems that are implementing HMC or its rival high bandwidth memory counterpart, High Bandwidth Memory (backed by a different consortium of vendors, including Nvidia and AMD). …