UP | HOME

About Me

20230727-104449_screenshot.png

TL; DR

  • Seasoned Engineer and Technical Leader with a strong background and track record of success at Google, ByteDance, Alibaba and Intel.
  • Extensive technical expertise in AI/ML solutions, software/hardware co-design, AI/ML & cloud infrastructure, accelerators, embedded systems, memory/storage technologies and computer architecture.
  • Strong experience in XFN collaboration, communication and working with partners & system integrators.
  • Ph.D. in Computer Engineering, Certified Google Cloud Architect & TensorFlow Developer.

See my LinkedIn profile for more details.

Things I’ve Worked On

ByteDance (Present)

Applied Research/Infrastructure Lab

  • Lead the SW/HW co-design projects for accelerating storage and data analytics workloads. Drive XFN effort E2E, including prototyping, ROI estimation, project proposal, architectural design, planning and execution.
  • Lead the research and exploration of emerging memory/storage technologies, including CXL, disaggregated memory architecture, Persistent Memory/NVRAM, in-memory computing, Neuromorphic computing.
  • Next-gen infrastructure for AI/ML: As one of the few core members of the task force, I drive the XFN effort for the exploration and planning of the next-gen infra for AI/ML. Provide important recommendations to the C-level management, and help incubate new projects in optimizing data pipelines for AI/ML workloads.

Google

Hardware Partner Service

  • Led the XFN project for enabling next-gen streaming platform for ecosystem partners.
  • Worked with Google Product Areas and BD teams with focus on SoC integration, hardware ecosystem scaling, program development and management.
  • Onboarded partner devices with Google technologies and help partners scale.
  • Managed internal and external stakeholders and product lifecycle from end to end.
  • Tool development and automation, solution design, prototyping and technical troubleshooting.
  • Successfully launched Google Assistant/Chromecast on embedded devices from top partners.
  • Successfully onboarded top SoC partners with Project Matter and Google Ecosystem.

Edge TPU (Collaboration with Google Brain)

  • “Moonshot” project of using Machine Learning to improve TPU design and model architecture.
  • Developed Learned Performance Model, a key component for model architecture exploration.
  • Developed the end-to-end pipeline for automated performance modeling on TPU.
  • Work was featured by Google AI and published in CVPR-22 (ECV22) with patents pending.

Alibaba

Storage Innovation with Hardware/Software Co-optimization

  • Created and led the AliFlash team for storage innovation.
  • Designed new storage architecture with software/hardware co-design and optimization.
  • Launched the first production Open Channel SSD in industry (AliFlash V3).
  • Project management with internal/external collaborations.

Storage Innovation with Intel 3D XPoint Technology

  • Led the XFN effort of deploying 3D XPoint technology in Alibaba’s infrastructure, making Alibaba one of the earliest adopters of this disruptive technology.

Research and Pathfinding of Innovative Technologies and Solutions

  • Evaluation of emerging technologies, strategic analysis & recommendations for executives.

Intel

3D XPoint Storage Technology (Optane)

  • As core developer of this disruptive product, I was responsible for media management, NVMe, Error Recovery/Injection, test automation, media characterization and performance analysis.

NVMe SSD Products

  • Core developer of P3700 (Intel’s first NVMe SSD) and P4500 (Intel’s first 3D NAND SSD).

Streaming Media

  • Core developer of streaming driver, firmware and platform software for Intel media SoC.
  • Bootloader & kernel enablement, performance optimization of the embedded device.

Academic

University of Pittsburgh (PhD, Computer Engineering)

  • New memory/storage technologies (Phase Change Memory, STT-RAM, Memrister)
  • Computer architecture
  • Memory hierarchy, modeling, performance, power

My Publications

My Inventions/Patents

  • Dynamic storage for adaptive mapping for data compression on a storage device (US20230273727A1)
  • Space manager for transparent block device compression (US20230229324A1)
  • Multi-dimensional solid state drive block access (US20230195345A1)
  • Adaptive mapping for transparent block device level compression (US20230176734A1)
  • System and method for allocating memory space (US20230122533A1)
  • NEURAL NETWORK ARCHITECTURE FOR IMPLEMENTING GROUP CONVOLUTIONS (WO2023059336A1)
  • HARDWARE ACCELERATOR OPTIMIZED NEURAL NETWORK MODELS USING GROUP CONVOLUTIONS (WO2023059335A1)
  • Universal and automatic end-to-end testing of smart TVs (defensive publication)
  • SYSTEM AND METHOD FOR FLASH STORAGE MANAGEMENT USING MULTIPLE OPEN PAGE STRIPES (US 20210034301 A1)
  • SYSTEM AND METHOD FOR OPTIMIZATION OF GLOBAL DATA PLACEMENT TO MITIGATE WEAR-OUT OF WRITE CACHE AND NAND FLASH (US 20200159419 A1)
  • COLLABORATIVE COMPRESSION IN A DISTRIBUTED STORAGE SYSTEM, (US 20200042500 A1)
  • METHOD AND SYSTEM FOR FACILITATING ATOMICITY ASSURANCE ON METADATA AND DATA BUNDLED STORAGE (US 20200034079 A1)
  • RAPID SIDE-CHANNEL ACCESS TO STORAGE DEVICES (US 20190347204 A1)
  • METHOD AND SYSTEM FOR DATA DESTRUCTION IN A PHASE CHANGE MEMORY-BASED STORAGE DEVICE (US 20190087587 A1)
  • METHOD AND SYSTEM FOR ACTIVE PERSISTENT STORAGE VIA A MEMORY BUS (US 20190073132 A1)
  • METHOD AND SYSTEM FOR MITIGATING WRITE AMPLIFICATION IN A PHASE CHANGE MEMORY-BASED STORAGE DEVICE (US 20190012111 A1)
  • SYSTEM AND METHOD FOR FINE-GRAINED POWER CONTROL MANAGEMENT IN A HIGH CAPACITY COMPUTER CLUSTER (US 20180364795 A1)
  • METHOD AND SYSTEM FOR IMPLEMENTING BYTE-ALTERABLE WRITE CACHE (US 20180349041 A1)
  • HIGH-VOLUME, LOW-LATENCY DATA PROCESSING IN FLEXIBLY CONFIGURED LOCAL HETEROGENEOUS COMPUTING ENVIRONMENTS (US 20180329632 A1)
  • PERSISTENT MEMORY FOR KEY-VALUE STORAGE (US 20180307620 A1)

Things I’m Interested In

  • AI/ML stuff
  • Quantum computing
  • Cloud computing & infrastructure
  • Linux, Emacs, Lisp, Python, C/C++, Go & other programming stuff
  • Astronomy, physics, math
  • Embedded systems, smart devices, IoT
  • Emerging memory & storage technologies (PCM, STT-RAM, ReRAM, ….)
  • In-memory computing & Neuromorphic computing
  • (and many more…)