DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

The Modular Platform (includes MAX & Mojo)

Xiao's CUDA Optimization Guide [NO LONGER ADDING NEW CONTENT]

Google Drive CLI Client

MathBox-based conference talks

TLB Benchmarks

Fastest kernels written from scratch

Solve puzzles. Learn CUDA.

A 120-day CUDA learning plan covering daily concepts, exercises, pitfalls, and references (including “Programming Massively Parallel Processors”). Features six capstone projects to solidify GPU par…

Algorithms implemented in CUDA + resources about GPGPU

CUDA Templates and Python DSLs for High-Performance Linear Algebra

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, s…

how to optimize some algorithm in cuda.

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Step by step implementation of a fast softmax kernel in CUDA

Fast CUDA matrix multiplication from scratch

LeetGPU Challenges

Fast and memory-efficient exact attention

A collection of free miscellaneous Windows tools

View ETW Provider manifest

Event Tracing For Windows (ETW) Resources

Frame profiler

KrabsETW provides a modern C++ wrapper and a .NET wrapper around the low-level ETW trace consumption functions.

A library containing utilities for mapping higher-level graphics work to D3D12

The OpenCL-on-D3D12 mapping layer

AMD Research Instruction Based Sampling Toolkit

Read and modify memory timings on the fly

Read and modify memory timings on the fly