preloader

I’m Juechu “Joy” Dong

Confidential Computing GPU Programming Model Computer Architect & Systems PhD candidate @Umich

NEWS

  • [Mar 2025]

    Excited to be selected to recieve the MLCommons ML and Systems Rising Star Award!!

  • [Mar 2025]

    FlexAttention is accepted to MLsys ‘25. See you in the Santa Clara this summer~

  • [Oct 2024]

    Our work mm2-gb is accepted to ACM BCB ‘24, the flagship conference of the ACM SIGBio. Join us in Shenzhen, China to see how we accelerate minimap2 using GPU!

  • [Aug 2024]

    Our work FlexAttention is lauched. See our PyTorch Blog and 180k view X post. Stay tuned to FlexAttention Part II - decoding and paged attention.

  • [Jun 2024]

    Our work Toleo is accepted to ASPLOS ‘24. Its presentation is delayed to ASPLOS ‘25. See you in Rotterdam~

Archived news ...
  • [May 2024]

    I joined Meta Pytorch Compiler team this summer as a research scienctist intern. See you at Menlo Park~

  • [Mar 2024]

    Our work mm2-gb for long sequence DNA mapping is accepted by BioSys'24. Checkout our open sourced demo. Many thanks to AMD HPC team! see you in San Diego~

  • [Jan 2024]

    I passed PhD qualification test and becomes a PhD candidate.

  • [Dec 2023]

    I recieved Rackham International Student Fellowship for 2023-2024 acdemic year .

EXPERIENCE

PUBLICATIONS

SERVICES

SKILLS

  • Programming Language

    c/c++ cuda, (system)verilog HIP, bash, Makefile

  • Technologies/Frameworks

    GPU Tuning: nsight-compute/nsight-sys, omniperf/omnitrace/rocprof
    Formal Verification: Murphi
    SIMD: avx512, avx2 on Xeon Phi
    Simulation: SniperSim, DRAMSim, pinplay
    Confidential Computing: Open Enclave SDK, Intel SGX

  • Architectures

    AMD CDNA2 Instinct GPU, NVIDIA Hopper GPU, Intel Xeon Phi, Out-of-order CPU