Reading time ( words)
Tachyum™ Inc. announced the promotion of Krishna Thatipelli, a seasoned professional with strong technical and management skills in CPUs and ASIC development, to Senior Director of Hardware Design Engineering after successfully delivering August milestones related to the company’s Prodigy Universal Processor.
Thatipelli has more than 20 years of experience successfully delivering many high-performance microprocessors/ASICs across a spectrum of processors, such as Intel and AMD x86 multicore CPUs, including Opteron; next-generation ARM cores; and out-of-order high-end SPARC CPUs. His innovation has resulted in being awarded several patents for technologies such as CPU architecture and high-performance CPU pipeline designs. He holds a Master of Science/Technology degree from the National Institute of Technology (Regional Engineering College) in Warangal, India.
“I feel very fortunate to have a strong and talented team backing my work as we take on the challenge of bringing the world’s first universal processor to life,” said Thatipelli. “It is indeed a unique opportunity as I have never seen anything like Prodigy in my 20 years working in the industry, even when working at some of the biggest names in processors like Intel, AMD, ARM and SPARC. I’m appreciative of the fact that my value has been seen here at Tachyum and am pleased to have been recognized in this way with a promotion. I have high confidence that we will complete our remaining tasks on schedule to ensure Prodigy comes to market on time.”
Thatipelli has delivered on milestones helping move Prodigy, the company’s flagship Universal Processor, closer to volume production in 2021. In April, the Prodigy chip successfully proved its viability with a complete chip layout exceeding speed targets. In August, the processor is able to correctly execute short programs, with results automatically verified against the software model, while exceeding the target clock speed. The next step is to get a manufactured wholly functional FPGA prototype of the chip later this year, which is the last milestone before tape-out.
Prodigy outperforms the fastest Xeon processors at 10x lower power on data center workloads, as well as outperforming NVIDIA’s fastest GPU on HPC, AI training and inference. The 125 HPC Prodigy racks can deliver a 32 tensor EXAFLOPS. Prodigy’s 3X lower cost per MIPS and 10X lower power translates to a 4X lower data center Total Cost of Ownership (TCO), enables billions of dollars of savings for hyperscalers such as Google, Facebook, Amazon, Alibaba, and others. Since Prodigy is the world’s only processor that can switch between data center, AI and HPC workloads, unused servers can be used as CAPEX-free AI or HPC cloud, because the servers have already been amortized.
“I’m a big believer of setting lofty goals and rewarding those in our organization for achieving them through hard work and results,” said Dr. Radoslav Danilak, Tachyum founder and CEO. “Krishna has more than earned this promotion by delivering on all of the projects and tasks that we have asked of him. Few people have the breadth of experience across all the various processors platforms as Krishna. His enthusiasm on our ability to deliver the world’s fastest processor for servers, AI and HPC applications speaks volumes on our ability to provide something that we don’t see being achieved by any others in the near future.”