accelerators index page
------------
learned
- [x]cuda
- [x]ga104 architecture
- [x]neuron/inferentia/trainium architecture
- [x]gemm
- [x]metal (apple silicon)
- [x]optimizations
- [x]memory coalescing
- [x]block tiling
- [x]thread tiling
- [x]warp tiling
- [x]vectorized memory access
- []transpose stuff
------------
notes
resources / references
------------
directory
------------