Mengchi Zhang's starred repositories
free-programming-books-zh_CN
:books: 免费的计算机编程类中文书籍,欢迎投稿
paper-reading
深度学习经典、新论文逐段精读
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
cuda-samples
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
x86-assembly-cheat
MOVED TO: https://************.com/linux-kernel-module-cheat/userland-assembly with code at https://github.com/************/linux-kernel-module-cheat/tree/master/userland/arch/x86_64 SEE README. x86 IA-32 and x86-64 userland minimal examples tutorial. Hundreds of runnable asserts. Nice GDB setup. IO done with libc, so OS portable in theory. NASM and GAS covered. Tested in Ubuntu 18.04. Containers (ELF), linking, calling conventions. System land cheat at: https://github.com/************/x86-bare-metal-examples, ARM cheat at: https://github.com/************/arm-assembly-cheat 移至:https://github.com/************/linux-kernel-module-cheat#userland-assembly请参阅自述文件。 x86 IA-32和x86-64 userland最少示例教程。 数百个可运行的断言。 好的GDB设置。 IO是用libc完成的,因此OS在理论上是可移植的。 涵盖了NASM和GAS。 在Ubuntu 18.04中测试。 容器(ELF),链接,调用约定。 系统土地作弊网址:https://github.com/************/x86-bare-metal-examples,ARM作弊网址:https://github.com/************/arm-assembly-cheat
DeathStarBench
Open-source benchmark suite for cloud microservices
llvm-pass-skeleton
example LLVM pass
accel-sim-framework
This is the top-level repository for the Accel-Sim framework.
ai_and_memory_wall
AI and Memory Wall
machine_learning
a collection of packages for ML projects, written in Tensorflow's Python API
MicroSuite
µSuite: A Benchmark Suite for Microservices
source-glibc
notes about glibc, ld-so and more.
heterosync
HeteroSync is a benchmark suite for performing fine-grained synchronization on tightly coupled GPUs
hotcrp-docker-compose
An easy docker-compose deployement of hotcrp
amd-llvm-project
DO NOT USE : Deprecated : Mirror of AMD llvm-project : The source repo is https://github.com/RadeonOpenCompute/llvm-project. Several times a day the default branch "amd-stg-open" is updated from the source repo and then locked. The purpose of this repo is to share and test fixes that have not yet gone into a review process.
ISCA-2021-Script
A collection of redistributable Python scripts to help organize ISCA 2021 (The 48th International Symposium on Computer Architecture).
gpu_unified_cache
GPU-UniCache: Automatic Code Generation of Spatial Blocking for Stencils on GPUs