Supercomputing researchers document evolution of AI hardware

MIT AI News
Read the full article
Since 2018, Lincoln Laboratory Supercomputing Center researchers have conducted the Lincoln AI Computing Survey (LAICS) to track and compare commercial AI accelerators' performance and power. These accelerators, including CPUs, GPUs, ASICs, FPGAs, and dataflow accelerators, support AI and other computationally intensive tasks. The survey helps identify the best hardware for specific workloads, informing government and industry stakeholders.

More in Chips & Compute

Musk Claims $40 Billion Chips Debt Closed, Yet Talks Ongoing

Bloomberg

Blackstone Bet on Chips Drove a Debt Boom That’s Upending Credit

Covered by 2 sources
Chips & Compute4 min read

On the ground at Nvidia's AI showpiece: Jensen-mania, robot ducks and neocloud distress

CNBC