"严肃"的学术/技术内容，请移步：
博文 (Blog Posts)
所有内容纯属虚构，请勿与真实世界中的人物/事件对号入座——如有雷同，纯属巧合。 远古时期文章亦不代表当前认知状态和观点。
- 2022 Use git-lfs to Manage Large Files in My Blog
- 2022 夏日记事
- 2022 殊途同归
- 2021 一类猜数问题的解法
- 2021 Data movement in CUDA
- 2021 Seize the day
- 2021 Writing a lock in CUDA
- 2021 Que Sera Sera–2020记事
- 2020 我和我的家乡
- 2020 吾生也有涯
- 2020 少年气
- 2017 康奈尔印象
- 2017 自适应多项式渲染
- 2017 拜占庭将军问题
- 2016 k-SAT问题的随机算法
- 2016 在丘奇数中构造前驱函数
- 2016 里约奥运圣火模拟
TODO 未完待续 (Working in Progress)
- 2022 Deciphering Notations in Programming Languages
- 2022 Survey on Sparse Architecture and Compilers
- 2022 量子计算初步
- 2022 dslab
- 2022 xv6
- 2022 Data Center Paper Reading
- 2022 A Survey of NPU architectures
- 2022 A taste of Rosette and Program Synthesis
- 2021 E-Graph for Good Explained
- 2021 Some novel DL workloads in 2021
- 2021 Some recent work on MoE(Mixture of Experts)
- 2021 Multi-Staged Programming Explained
- 2021 Actor model Explained
- 2021 Computer Architecture Arithmetics
- 2021 Hacking Operating Systems
- 2021 Hacking Network Systems
- 2021 比特币技术相关
- 2020 回合制游戏的并行化初探
- 2020 半途而废系列之——CargoCraft
- 2020 分布式系统相关
会议记录 (Conference Experience)
- 2022 MLSys 2022 记录
- 2022 David Patterson's visit at UW
书评 (Book Review)
相册 (Album)
相关链接
- 雨荷 （催更中）
Useful links
- Mark Oskin's Lecture Notes on Quantum Computing
- Quantization Algorithms
- Polyhedral Compilation as a Design Pattern for Compilers
- FPGA are (not) Good at Deep Learning by Mohamed from Cornell
- Everything Wrong With FPGAs
- Booting an Operating System
- Formal Verification of a MESI-based Cache Implementation
- How the JIT compiler boosts Java performance in OpenJDK
- The Future of Interactive Theorem Proving
- All About Monads
- A Simple GPU Hash Table
- 0.A.D findfinder design
- A short introduction to call-with-current-continuation (call/cc)
- [[A Short History of Markov Chain Monte
https://arxiv.org/pdf/0808.2902.pdf][A Short History of Markov Chain Monte Carlo]]
Podcast I'm subscribing
- Lex Fridman : interview of computer scientists, entrepreneurs, etc.
- Acquired : stories of companies.
- The Thesis Review Podcast : PhD thesis talk.
Coding Tips
Ph.D. Progress
Milestone
DONE Qualification Examination
- Date
- 2022.07.28
- Slide
- link
- Feedback
- SparseTIR feedbacks
- Talk
- Qualifying Project Presentation
TODO General Examination
Topic: reconfigurable sparse architectures, end-to-end sparse model acceleration
- Date
- TBD
- Proposal
- TBD
TODO Final Examination
- Date
- TBD
- Dissertation
- TBD
Paper Reading Tips
TODO Papers to read
- SparseCore @ ASPLOS 2022
- täkō @ ISCA 2022
- Exocompilation @ PLDI 2022
- Whitepaper on Sky Computing
- GS-DRAM @ MICRO 2015
- Multi-Stage Programming
- DISTAL @ PLDI 2022
- SpDISTAL @ SC 2022
- POET @ ICML 2022
- SANGER @ MICRO 2021
- The Case of Reduced Instruction Set Computer
- FPGA Architecture at 5nm and Beyond @ FPGA 2022
- Dark Silicon @ ISCA 2011
- Mozart @ SOSP 2019
- Offload Annotations @ ATC 2020
- LLM-int8 @ Neurips 2022
- Copy-and-Patch Compilation @ OOPSLA 2021
- Stratified Synthesis @ PLDI 2016
- Sparse Abstract Machine
- ANT @ ISCA 2022
- Magicube @ SC 2022
- FABNet @ MICRO 2022
- Movement Prunning
- Cambricon-X @ MICRO 2016
- Tensaurus @ HPCA 2020
- Is Dark Silicon Useful?
- TraceCache @ MICRO 1996
- SparseP @ Sigmetrics 2022
- Speculation or Dynamism? @ ASPLOS 2013
- The Cray-1 Computer System
- Using Modern Graphics Architecture for General Purpose Computing @ MICRO 2002
- Real-time Neural Radiance Caching for Path Tracing
- Instant-NGP @ ACM Trans Graphics
- Region-Based Memory Management
- Singularity @ OSR 2007
- Corey @ OSDI 2008
- Klee @ OSDI 2008
- Type-Directed Scheduling of Streaming Accelerators @ PLDI 2020
- Grappa @ ATC 2015
- Auto Vectorization with egraph @ ASPLOS 2021
- A Variable Warp Size Architecture @ ISCA 2015
- Knowledge and Common Knowledge in a Distributed Environment
- Uniprocessor Garbage Collection Techniques
- DMon @ OSDI 2021
- FingerTrees @ JFP
- Lock Free Queue @ PODC 1996
DONE Paper reading notes
- Reflections on Trusting Trust @ CACM 1984
- The Design Philosophy of DAPRA Internet Protocols
- Spanner: Google's Globally-Distributed Database
- BGP: Interdomain Internet Routing
- Two Phase Commit
- Dorylus @ OSDI 2021
- SpArch @ HPCA 2020
- Gamma @ ASPLOS 2021
- OneFlow
- Spatial Sparse Matrix Multiplier @ HPCA 2021
- K-ADD @ FPGA 2022
- SparseLNR @ ICS 2022
- FlashAttention @ ICML 2022
- TC-GNN
- RISC
- Tomasulo
- Very Long Instruction Word Architecture
- Cyclone @ ISCA 2003
- Address Resolution Buffer @ TC 1996
- PipeZKP @ ISCA 2021
- Pentium IV Architecture
- Is DarkSilion Useful @ DAC 2012
- A Preliminary Architecture for a Basic Data-Flow Processor @ ISCA 1975
- Pathway @ MLSys 2022
- Deterministic shared memory multiprocessing (DMP) @ ASPLOS 2009
- Rubik @ NSDI 2021
- Meet the Walkers @ Micro 2013
- Boqueria @ HotChips 2022
- SPGrid @ SIGGRAPH 2014
- RAKE @ ASPLOS 2022
- UGC @ ISCA 2021
- ExTensor @ MICRO 2019
- Tensarus @ HPCA 2020
- SparseTPU @ ICS 2020
- OuterSPACE @ HPCA 2018
- X-Cache @ ISCA 2022
- SortCache @ TACO 2022
- CUDA Persistent Kernel Survey @ InPar 2012
- Approximate Computing in Solid-State-Memories @ Trans on Computer System
- Tofu @ Eurosys 2019