Interference Risks In Processing-Using-DRAM (U. of Tokyo, ETH Zurich, CISPA, Riken)


Researchers from The University of Tokyo, ETH Zurich, CISPA, and RIKEN published a technical paper titled “PuDGhost: Experimental Analysis of Computation Result Corruption in Processing-using-DRAM Operations on Real DRAM Chips and Implications for Future Systems.” Abstract excerpt: “We reveal PuDGhost, an interference phenomenon where a PuD operation in a given column produces erron... » read more

Will Your Chip’s Memory Work As Expected?


Increased density at advanced nodes, multi-die assemblies, and the rollout of AI everywhere are making it much more challenging to ensure that memory will function properly over its expected lifetime. Test is no longer about a single memory or one approach for testing memory. It can vary by application, by workload, and by architecture. Some testing is close to memory, some is built into memory... » read more

DDR5 MRDIMM: A Transformational Evolution For DDR5 DIMM


DDR5 is the latest generation of DDR server memory capable of supporting data rates of up to 9,200 Mbps, which is a huge leap over the previous generation of DDR memories. It is used in a wide variety of applications, with the huge server and data center market being the key driver behind the adoption of DDR5-based memory systems. As systems move towards more CPU cores, bandwidth, and capacity,... » read more

SOCAMM2: Bringing LPDDR5X Benefits To AI Servers


The rapid scaling of artificial intelligence is reshaping nearly every dimension of data center design. While much of the focus has been on GPUs, accelerators and advanced packaging, another constraint is emerging as equally critical: power. As AI models grow larger and more complex, power consumption, not raw compute, is increasingly the limiting factor in system scalability. Modern AI work... » read more

HBM Shifts Testing Left To Preserve AI Chip Yield


Key Takeaways: A high-yield, known-good stack requires multiple test insertions. Known good stack testing poses challenges for power delivery and thermal management. The shift to HBM4 and HBM5 will increase the pressure for shift-left test flows. Taller high-bandwidth memory (HBM) stacks and tighter TSV pitch are impacting AI module yields. The solution is to push test furth... » read more

Unraveling DRAM SAQP Process Complexity With Monte Carlo Virtual Fabrication


By Swapnil Kailash More and Roopa Hegde As DRAM technologies scale to increasingly tighter pitches, the patterning requirements exceed the limits of conventional single-exposure DUV lithography. In advanced nodes such as D1b (1-beta), active-area (AA) pitches fall in the range of 22 to 26 nm, well below the capability of single patterning. To achieve these sub-lithographic dimensions, advan... » read more

GPU Rowhammer Attacks Beyond Data Corruption (U. of Toronto)


A new technical paper, "GPUBreach: Privilege Escalation Attacks via GPU Rowhammer," was published by researchers at University of Toronto. Summary "GPUBreach shows that GPU Rowhammer attacks can move beyond data corruption to real privilege escalation. By corrupting GPU page tables, an unprivileged CUDA kernel can gain arbitrary GPU memory read/write, and then chain that capability into CPU... » read more

PDN Challenges In DRAM-Based Compute-In-Memory Systems (UT Austin)


A new technical paper, "A comparative study on power delivery aspects of compute-in/near-memory approaches using DRAM," was published by researchers at UT Austin. Abstract "Compute-in-memory (PIM) mitigates the memory wall by performing computation within memory, reducing data movement and improving energy efficiency. DRAM-based PIM is particularly attractive due to its high density, matu... » read more

DRAM’s Whac‑A‑Mole Security Crisis


Key takeaways: Rowhammer remains a DRAM security threat, while Rowpress has increasingly become a related threat. New commands issued by the memory controller can help manage refreshes, but they’re not a perfect solution. A smaller, vertical DRAM cell may eliminate the problem, but it’s years away. Rowhammer has been a persistent DRAM issue across several memory generati... » read more

Memory For AI At The Edge


Inferencing at the edge has very different needs than training large language models or large-scale inferencing in AI data centers. Many edge devices run on a battery. They're price-sensitive, and they are constrained by the physical area of the device. As a result, the amount of memory that can be packed into these devices is also limited. Steve Woo, Rambus fellow and distinguished inventor, t... » read more

← Older posts