+886 2 8797 8337
12F-2, No.408, Ruiguang Rd., Neihu Dist., Taipei City 11492, Taiwan
Center of Innovative Incubator R819, No. 101, Section 2, Kuang-Fu Road, Hsinchu, Taiwan
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 retargetable. Together, we accelerate AI innovation.
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 ASICtronix 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.
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.
William received his Master’s degree from the Department of Electrical and
Computer Engineering, University of Massachusetts, Amherst in 1993 and
obtained his EMBA degree from University of North Carolina, Chapel Hill in
2004. He spent 20+ years in the U.S. building system level products from the
early days at NeXT Computer to later days at Apple, contributing to the core
technology of iOS and MacOS.
William was recognized as the Global Top 100 Leaders in Technology in 2021
when he served as CTO at Foxconn (HonHai) Technology Group. William
spearheaded technology strategies in Electric Vehicles, Robotics, and AI. His
crowning achievement was the design and launch of the MIH Open EV Platform,
dubbed the "Android of EV”, showcasing William's foresight in shaping the
future of automotive technology.
At Skymizer, William's strategic vision was instrumental in pivoting the
company's focus towards AI infrastructure.
Dr. Kuang-Chih Liu (KC Liu) is a technology leader specializing in system
architecture, AI acceleration, and semiconductor design. He holds a Ph.D. in
Computer Engineering from National Tsing Hua University, Taiwan, with expertise in
parallel computing, vectorization algorithms, and AI hardware/software co-design.
Currently, he is Senior VP of Sales at Skymizer, driving business development
across applications, algorithms, architectures, and ASIC design. He has led
compiler integration for PyTorch, TensorFlow, and ONNX while advancing ML
benchmarking and compute-in-memory solutions for LLMs.
He also serves as an Executive Committee Advisor for the RISC-V Taiwan
Alliance, fostering industry-academic collaboration. Previously, he held
leadership roles at Foxconn, MediaTek, ITRI, and Infineon, contributing to AI-driven manufacturing, on-device AI, cloud virtualization, and networking.
Dr. Liu holds multiple U.S. patents in networking, encryption, and signal
processing. He has published research on AI acceleration and system
architecture and co-authored books on x86 assembly and UNIX programming.
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.