[1910.00935] DiffTaichi: Differentiable Programming for Physical Simulation

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

View PDF HTML (experimental) Abstract:We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Based on an imperative programming language, DiffTaichi generates gradients of simulation steps using source code transformations that preserve arithmetic intensity and parallelism. A light-weight tape is used to record the whole simulation program structure and replay the gradient kernels in a reversed order, for end-to-end backpropagation. We demonstrate the performance and productivity of our language in…

saved by

• Umangi Jain

related reading

• Physics-Informed Diffusion Modelsarxiv.org
• Universal Guidance for Diffusion Modelsarxiv.org
• Differentiable Programming from Scratchthenumb.at
• [2512.19428] Attention Is Not What You Needarxiv.org
• Scalable Diffusion Models with Transformersarxiv.org
• [2010.04017] DiffTune: Optimizing CPU Simulator Parameters with Learned Differentiable Surrogatesarxiv.org
• [2403.14606] The Elements of Differentiable Programmingarxiv.org
• Hyper-Connectionsarxiv.org
• [2209.10797] DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generationarxiv.org
• [2312.15159] Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencearxiv.org
• [1903.08894] Towards Characterizing Divergence in Deep Q-Learningarxiv.org
• [1803.08823] A high-bias, low-variance introduction to Machine Learning for physicistsarxiv.org