Cache-management scheme that they say improves the data rate of in-package DRAM
Source: Researchers from MIT, Intel, and ETH Zurich
Xiangyao Yu (MIT), Christopher J. Hughes (Intel), Nadathur Satish (Intel) Onur Mutlu (ETH Zurich), Srinivas Devadas (MIT)
As the transistor counts in processors have gone up, the relatively slow connection between the processor and main memory has become the chief impediment to improving computing performance but now, researchers from MIT, Intel, and ETH Zurich have created a cache-management scheme that they say improves the data rate of in-package DRAM caches by 33 to 50 percent.
New architectures, packaging approaches gain ground as costs increase, but shrinking features continues to play a role.
Four industry experts talk about what’s changing, how quickly, and where the limits are with AI.
Work begins on building a quantum computing ecosystem.
2019 will be a year of change for the semiconductor industry as new fields drive technological advancements.
Semiconductor devices face many hazards before and after manufacturing that can cause them to fail prematurely.
Interest in the open-source ISA marks a significant shift among chipmakers, but it will require continued industry support to be successful.
Chips will cost more to design and manufacture even without pushing to the latest node, but that’s not the whole story.
This will go down as a good year for the semiconductor industry, where new markets and innovation were both necessary and rewarded.
Slowdown due to impact on timing, and dependencies between power, thermal and timing that may not be caught by signoff tools.
Experts at the Table, Part 1: Impact on the supply chain, who’s using advanced packaging, and the cost of packaging versus device scaling.
Access to source code makes it attractive for custom applications, but gaps remain in the tool flow and in software.
Technology adds more granularity, but starting point for design shifts as architectures cope with greater volumes of data.
Sticking a bigger/better cache on a CPU doesn’t fix the fundamental problems with the architecture. Really you want to do processor-in-memory (PiM). Most of the NVMe cards for the storage have ARM (or similar) CPUs managing the storage, and it’s a lot quicker to ask them to do the work than shoveling the data back and forth to a central X86 CPU.
This gets worse as you start die-stacking memory for density, but don’t get any more I/O pins (as with pins on a PCIe card), so you need to move the memory controller and compute into the die stacks.
Surfaces and edges are a dimension down from volumes and areas.
I have checked Apple iPhone Support and read something about the way of making the high capacity data caches. It is very important and the efficient as well for the user. We must know about this in detail.