Skymizer is a leading-edge system software company established in November 2013 in Taipei and Hsinchu Science Park. We help integrated circuit (IC) design houses, particularly vendors of AI SoCs, enhance their products by improving functionality, performance, and reliability. This is accomplished with unique compiler software technology. At Skymizer, we believe that it is a new golden age of computer architecture. Revolutionary opportunities reside in both hardware architecture and system software architecture. With an unmatched group of hardware architects and system software architects, we create, adapt, and re-invent the software programming environment to achieve complex heterogeneous multicore SoCs during the More-than-Moore era.
We specialize in compiler and runtime technology for any IC chips with heterogeneous multicores on a system. Our compiler technology transforms abstract programming languages into control instructions of the hardware engine of your choice. The runtime technology manages the hardware and software resources in the chips and ensures high memory and bus system utilization. Currently, we are focused on system software for AI accelerators, which includes connecting AI frameworks, such as TensorFlow, TensorFlow Lite, PyTorch, Keras, ONNX, and Android NNAPI, to deep-learning accelerator ASICs.
Our system software enables AI chip design houses to automate AI application development, improve system performance, and optimize inference accuracy. Heterogeneous multicore systems have variant programmable engines and complex memory and bus systems. Building automation tools for such complex chips is a significant challenge. In fact, many senior AI chip design houses provide only libraries or limited tools to their customers. We have examined solutions to all potential challenges regarding mass production, including compiler, calibrator, runtime, virtual platform, and benchmark model zoo. With these solutions, our customers are able to improve their system performance and optimize inference accuracy to sky-high levels.
We have been helping many chip customers quickly bring their products to market. As a result of our solution, there have been more than 20 AI chips, including cloud inference, edge, and sensors, going to new tape-out or mass production with our solution since 2019. Best of all, although chips are diverse, our software stack is modular and re-targetable. Together, we accelerate AI innovation.
Luba Tang received his M.S. in computer science in only one year from National Tsing-Hua University,
Taiwan. He has been a Ph.D. student in the National Tsing-Hua University computer science department
since 2007. At the same time, he has been working in the compiler groups of Marvell, Inc. and MediaTek,
Inc. since 2010.
His research interests include electronic system level (ESL) design and compilers. During his career, he has focused on iterative compilers, ahead-of-time compilers, link-time optimization, electronic system-level simulation, and electronic system-level design. His most recent professional focus is on dynamic linking and link-time optimization. He was the chief programmer of the Starfish DSP simulator, the original writer of the Marvell iterative compiler, and the software architect of MCLinker and ONNC. He is also the founder and CEO of Skymizer Inc.
Jim graduated from the Department of Electrical Engineering of National Taiwan University in 1981 and
obtained a master's degree in electrical engineering from the University of California, Santa Barbara.
He has numerous years of experience in the ASIC/CAD field. During his time in the United States, he
worked for LSI Logic and Toshiba and founded ASICtronics Solutions.
From 1992 to 2003, he was responsible for design services and emerging customer groups in TSMC North America. He returned to Taiwan in 2003 and served as the president of Global Unichip Corporation for more than 13 years. During this period, he transformed the company from a local small company to the largest design service company in the world. He successfully led the company to go public in 2006, and was awarded National Outstanding Manager Award in 2009.
Wen-Han graduated from the Department of Electrical Engineering of National Taiwan University in 1981
and subsequently obtained a master's degree in electrical engineering from the Netherlands in 1985.
Thereafter, he earned a doctorate in computer science from the University of Washington in the United
States in 1989. Regarding his classic academic papers, he won the Best Paper Award of ACM SIGMETRICS,
the Best Paper Award of ACM/IEEE ISCA, the Most Influential Paper Award, and IEEE Fellow.
In 1991, Wen-Han joined Intel Corporation, engaged in designing and analyzing the Intel Pentium Pro platform architecture, and contributed critically to developing the company's Intel Xeon processor product line, making the world's most advanced technology popularized. With his excellent technical research, development, management, and communication skills, he was promoted to the vice president of Intel Corporation and the executive director of Intel Labs in 2013.
Wen-Han entered the top leadership team of Intel Corporation, becoming a model for Chinese tech industry leaders and personnel. In recognition of his outstanding technical strength and contributions, Intel awarded Wen-Han an honorary senior academician in 2015. This is Intel's highest-level technical title, and the first since its establishment, which is of great significance.
After graduating from the Massachusetts Institute of Technology, Yu-Ting joined McKinsey as a strategic
consultant in 1995 and subsequently participated in various industrial strategic planning work in the
Greater China and Southeast Asian markets. Thereafter, he joined Microsoft as a product technical
marketing, planning, and R&D work for over 20 years.
In 2015, Yu-Ting spawned the first batch of Microsoft cloud artificial intelligence services: Azure Cognitive Services. Notably, during the following year, he single-handedly facilitated Microsoft's acquisition of SwiftKey, an artificial intelligence mobile keyboard app worth hundreds of millions of dollars. In the following years, he led the team to make SwiftKey the most user-friendly mobile app in Microsoft's history.
From 2018 to 2020, Yu-Ting served as the global senior vice president of Microsoft Cloud and led the computer vision R&D team in Europe, Asia, North America, and Latin America. He is currently the global senior vice president of Microsoft Technology and Research, responsible for Microsoft's artificial intelligence and machine learning technology strategy and planning.