新聞稿
SAN JOSE, Calif., July 16, 2019 – Tachyum Inc. announced today it has appointed Kiran Malwankar to the position of Vice President of System Engineering. Malwankar, a 30-year veteran of both pre-IPO companies and industry leaders, holds 21 U.S. patents in technologies such as I/O virtualization, PCIe, storage virtualization, and flash/solid-state media.
Malwankar joins the company after founding and/or joining a series of successful startups that delivered innovations in memory, AI, IoT, cloud, and flash devices; five of these companies were acquired and one went public. In addition, he has held executive and senior-level engineering positions at dominant vendors such as Cisco, Violin Memory, Nishan Systems/McDATA, and Aprius/FusionIO. He holds a master’s degree in electrical engineering from the prestigious Indian Institute of Technology in Mumbai.
“I am honored to oversee Tachyum’s breakthrough processor architecture and bring it to today’s most interesting applications and environments – supercomputing, hyperscalers, AI, deep machine learning, edge computing and IoT,” said Malwankar.
Among Malwankar’s professional achievements and patents are new high-speed bus protocols, circuit board design, FPGA design, processor-agnostic storage, and non-volatile memory. His engineering and design work is cross-functional, incorporating product management, marketing, and manufacturing, to deliver significant advancements in computing, not for their own sakes, but to meet market needs.
“Kiran has a rare combination of experience in complex compute, storage, and networking systems, plus the vision and strategy required to bring pioneering products to perfection,” said Dr. Radoslav “Rado” Danilak, Tachyum CEO. “With Kiran leading our system engineering team, Tachyum, a fabless semiconductor company, is now building a world-class organization to deliver solutions, including reference designs, to our partners and customers next year, to accelerate widespread adoption of our chip products across multiple markets.”
Tachyum’s Prodigy Universal Processor Chip is the smallest and fastest general purpose, 64-core processor developed to date, requiring 10x less processor power and reducing processor cost by 3x. Prodigy will directly enable a 32-Exaflop AI supercomputer and empower users to simulate, in real-time, human brain-sized neural nets beginning in 2020, years ahead of industry expectations. Prodigy reduces data center TCO (annual total cost of ownership) by 4x, through a disruptive processor architecture and a smart compiler that has made many parts of the hardware found in typical processors redundant. Fewer wires and shorter wires, due to a smaller, simpler core, translates into much greater speed and power efficiency for the Prodigy processor.
