Blog Review: Nov. 6


Cadence's Satish Kumar C explores how the Deferrable Memory Write transaction type in PCIe and CXL can improve latency, efficiency, and performance by delaying certain memory write operations during system bus congestion or until other priority tasks are complete and highlights implementation and verification challenges. Synopsys' Daryl Seitzer and Rahul Thukral point to magnetoresistive RAM... » read more

Chip Industry Week In Review


Siemens announced plans to acquire Altair Engineering, a provider of industrial simulation and analysis, data science, and high-performance computing (HPC) software, for about $10 billion. Altair's software will become part of Siemens' Xcelerator portfolio and provide a boost to physics-based digital twins. Onto Innovation bought Lumina Instruments, a San Jose, California-based maker of lase... » read more

Chiplets Make Progress Using Interconnects As Glue


Breaking up SoCs into their component parts and putting those and other pieces together in some type of heterogeneous assembly is beginning to take shape, fueled by advances in interconnects, complex partitioning, and industry learnings about what works and what doesn't. While the vision of plug-and-play remains intact, getting there is a lot more complicated than initially imagined. It can ... » read more

Locking When Emulating Xtensa LX Multi-Core On A Xilinx FPGA


Today's high-performance computing systems often require the designer to instantiate multiple CPU or DSP cores in their subsystem. However, the performance gained by using multiple CPUs comes with additional programming complexity, especially when accessing shared memory data structures and hardware peripherals. CPU cores need to access shared data in an atomic fashion in a multi-core environme... » read more

Blog Review: Oct. 30


Synopsys' Frank Schirrmeister argues that hardware-assisted verification techniques like emulation and prototyping are essential to help engineers improve design behavior to manage complexity and ensure systems function seamlessly in real-world applications. Siemens’ Stephen V. Chavez finds that ultra high-density interconnect (UHDI) has changed the design and production of PCBs to enable ... » read more

Blog Review: Oct. 23


Cadence’s Sanjeet Kumar introduces the message bus interface in the PHY Interface for the PCIe, SATA, USB, DisplayPort, and USB4 Architectures (PIPE) specification, which provides a way to initiate and participate in non-latency-sensitive PIPE operations using a small number of wires. Siemens’ Dennis Brophy argues that the recently published Portable Test and Stimulus Standard (PSS) 3.0 ... » read more

Chip Industry Week In Review


Arm joined forces with Korea's Samsung Foundry, ADTechnology, and Rebellions to create a CPU chiplet platform for AI training and inference. The new chiplet will be based on Samsung's 2nm gate-all-around technology. Intel and AMD, arch competitors for decades, formed an x86 ecosystem advisory group to collaborate on architectural interoperability and simplify software development. Samsung... » read more

How Big A Deal Is Aging?


Nothing lasts forever, but in the semiconductor world things used to last long enough to become obsolete long before their end of life. That's no longer the case with newer nodes, and it is raising concerns in safety-critical markets such as automotive. Being able to fully understand what happens inside of chips is still a work in progress, and analysis approaches are trying to keep up. Unti... » read more

Is Liquid Cooling Right For Your Data Center?


We live in an exciting time—liquid cooling, which once seemed more trouble than it’s worth, is fast becoming an accepted and sought-after technology in the data center industry. That said, it’s still a complex technology to implement, especially in legacy facilities. Is your data center ready to operationalize liquid cooling? Liquid cooling in the data center Liquid cooling in the d... » read more

Mass Customization For AI Inference


Rising complexity in AI models and an explosion in the number and variety of networks is leaving chipmakers torn between fixed-function acceleration and more programmable accelerators, and creating some novel approaches that include some of both. By all accounts, a general-purpose approach to AI processing is not meeting the grade. General-purpose processors are exactly that. They're not des... » read more

← Older posts Newer posts →