References

Some of the works or projects referenced in this wiki

1. Implementing a Code Generator for Fast Matrix Multiplication in OpenCL on the GPU { Matsumoto et al., (2012) }

2. A Portable and High-Performance General Matrix-Multiply (GEMM) Library for GPUs and Single-Chip CPU/GPU Systems { Garg and Hendren, (2014) }

3. CLTune: A Generic Auto-Tuner for OpenCL Kernels { Nugteren and Codreanu, (2015) }

4. CLBlast: A Tuned OpenCL BLAS Library { git and arXiv }

5. Accelerating GPU kernels for dense linear algebra { Nath et al. (2011) }

6. Accelerating cuBLAS/cuDNN using Input-Aware Auto-Tuning: The ISAAC library { code and slides }

7. A three-dimensional approach to parallel matrix multiplication { Agarwal et al. (1995) }

8. Matrix multiplication beyond auto-tuning: Rewrite-based gpu code generation. { Steuwer et al.(2016) }

More coming soon.