This project attempts to improve the native code generator of GHC by adding support for Intel AVX and SSE SIMD instructions. This support would enable GHC to expose a bunch of vector primitive operations, which can be utilized to by various high performance and scientific computing libraries of the Haskell ecosystem to parallelize their code for free.

Organization

Student

Abhiroop Sarkar

Mentors

  • carter schonwald
  • Ben Gamari
close

2018