Skip to content
View johnnyw3's full-sized avatar
8 followers · 4 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pull Sharkx2Achievement: YOLO

Organizations

@TeamBipartite @examix @pic64-hpsc-hx

Block or report johnnyw3

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
johnnyw3/README.md

Hi!

I'm a 4th year honours computer science student at UVic. Most of my main "serious" work involves matrix multiplication, both dense and sparse. You'll also find some other random little side projects here too.

My main interests are:

  • High-performance computing, particularly GPU algorithms, SIMD, and parallelism
  • Firmware development (RISC-V 🥰)

Pinned Loading

  1. TeamBipartite/bipartite-gemm TeamBipartite/bipartite-gemm Public

    High throughput data-parallel GEMM implementations in Cuda using Cuda cores and Tensor cores

    C++

  2. gemm gemm Public

    High performance GEMM kernels written in C using AVX and AMX intrinsics. Achieves 75-105% performance of OpenBLAS

    C++ 1

  3. spmm spmm Public

    [WIP] High-performance CPU SpMM (N:M sparsity) algorithm accellerated using AVX. Achieves ~1.35-1.4x speedup compared to our gemm algorithm in 2:4 elementwise sparsity.

    C++ 1