中文 English

More Data Drives Focus On IC Energy Efficiency


Computing workloads are becoming increasingly interdependent, raising the complexity level for chip architects as they work out exactly where that computing should be done and how to optimize it for shrinking energy margins. At a fundamental level, there is now more data to compute and more urgency in getting results. This situation has forced a rethinking of how much data should be moved, w... » read more

Understanding Write Combining On Arm


Write Combining (WC) is a specialized memory type defined by the x86-64 architecture that is used for gathering multiple stores into burst transactions over the system bus. WC is commonly used on x86-64 platforms for interaction with I/O and other peripheral devices. In this whitepaper we provide an overview of the Arm architecture memory types that provide WC-like capabilities. In addition, t... » read more

Computing Where Data Resides


Computational storage is starting to gain traction as system architects come to grips with the rising performance, energy and latency impacts of moving large amounts of data between processors and hierarchical memory and storage. According to IDC, the global datasphere will grow from 45 zettabytes in 2019 to 175 by 2025. But that data is essentially useless unless it is analyzed or some amou... » read more

Overcoming Challenges In Next-Generation SRAM Cell Architectures


Static Random-Access Memory (SRAM) has been a key element for logic circuitry since the early age of the semiconductor industry. The SRAM cell usually consists of six transistors connected to each other in order to perform logic storage and other functions. The size of the 6T (6 Transistors) SRAM cell has shrunk steadily over the past decades, thanks to Moore’s Law and the size reduction of t... » read more

HBM2E Raises The Bar For AI/ML Training


The largest AI/ML neural network training models now exceed an enormous 100 billion parameters. With the rate of growth over the last decade on a 10X annual pace, we’re headed to trillion parameter models in the not-too-distant future. Given the tremendous value that can be derived from AI/ML (it is mission critical to five of six of the top market cap companies in the world), there has been ... » read more

MRAM Evolves In Multiple Directions


Magnetoresistive RAM (MRAM) is one of several new non-volatile memory technologies targeting broad commercial availability, but designing MRAM into chips and systems isn't as simple as adding other types of memory. MRAM isn’t an all-things-for-all-applications technology. It needs to be tuned for its intended purpose. MRAMs targeting flash will not do as well targeting SRAMs, and vice vers... » read more

Usage Models Driving Data Center Architecture Changes


Data center architectures are undergoing a significant change, fueled by more data and much greater usage from remote locations. Part of this shift involves the need to move some processing closer to the various memory hierarchies, from SRAM to DRAM to storage. There is more data to process, and it takes less energy and time to process that data in place. But workloads also are being distrib... » read more

Fearless Chip Forecasts For 2021


It’s been a roller coaster ride in the semiconductor industry. In early 2020, the semiconductor business looked bright, but then the Covid-19 pandemic struck, causing a sudden downturn. By mid-2020, though, the market bounced back, as the stay-at-home economy drove demand for computers, tablets and TVs. The chip market ended on a high note in 2020, but the question is, what’s in store fo... » read more

Hidden Costs In Faster, Low-Power AI Systems


Chipmakers are building orders of magnitude better performance and energy efficiency into smart devices, but to achieve those goals they also are making tradeoffs that will have far-reaching, long-lasting, and in some cases unknown impacts. Much of this activity is a direct result of pushing intelligence out to the edge, where it is needed to process, sort, and manage massive increases in da... » read more

More Data, More Memory-Scaling Problems


Memories of all types are facing pressures as demands grow for greater capacity, lower cost, faster speeds, and lower power to handle the onslaught of new data being generated daily. Whether it's well-established memory types or novel approaches, continued work is required to keep scaling moving forward as our need for memory grows at an accelerating pace. “Data is the new economy of this ... » read more

← Older posts