Was co-founder of Intel and the person behind Moore’s Law.
Intel revealed some of the details of their newest CPUs, a few tidbits of their Ponte Vecchio HPC GPU. They also mentioned their someday recently renamed consumer GPUs that are going to put AMD and Nvidia out of business. First off, and totally seriously, the Intel presentation was one of the best-looking and well-organized I have ever seen. Intel has … Read more
Moore Threads, a GPU-based AI accelerator supplier, was founded in October 2020. Moore Threads recently closed two rounds of funding amounting to RMB 1 billion (USD 155 million), according to Winsoul Capital, who managed the placement. Liu Shanshan is the founder and executive director of Moore Threads. She was formally a senior manager at Xilinx. She founded AI chip start-up … Read more
Streaming gaming is getting a lot of attention, especially with Google’s recent announcement as a provider. All the major gaming companies such as Microsoft, EA, Nvidia, and others are either offering such a service capability or soon will—they’ll have no choice if they want to stay competitive. Media delivery for gaming has evolved from cartridges to tape, to CDs, to … Read more
As a sign of its renewed focus on constructing and articulating a coherent strategy for the future, Intel recently held an industry analyst summit, the first in four years. The confluence of the slowing of Moore’s Law transistor scaling, a rapidly transitioning computing paradigm from distributed, local clients to data-rich clouds, and energized competition from competing providers of high-performance silicon … Read more
Everyone wants to be the law, the Maxwell, the Ohm, the Shannon. Perhaps the most famous non-law law is the oft touted Moore’s law. Moore made an observation about semiconductor manufacturing densities and projected that observation. It was Caltech professor Carver Mead who in 1975 popularized the term “Moore's law,” and Intel’s marketing folks knowing a good thing when they … Read more
The evolution of future processors Is it a revolution — or just evolution? The GPU with its hyper-dense compute capacity and relatively low cost, is an amazingly powerful workload accelerator for certain classes of problems — those that lend themselves to massive parallel processing and multi-threaded workloads. When programmable vertex shaders were first introduced in 2002 (by 3Dlabs), and the … Read more