This PR adds several optimization capabilities in the compiler backend:
- Now using inline PTX for `tl.store`, making it possible to use things like evict_last
- For A100, mma layout can be directly converted to shared memory
- For A100, an additional "transpose" argument in `dot` allows tensors to be loaded once and used both row- and col- major.
- Fixed liveness analysis; this was broken.
- Now can load/store directly mma layout without converting. Useful for when tl.dot accumulator is initialized with DRAM data inside of an inner loop.
- `tl.dot` can now take LHS inputs in registers when it comes from a previous `tl.dot` instruction. Useful for e.g. fused attention.
Significantly improves the performance of `triton.ops.matmul` in memory-bound settings via the use of many more block configs coupled with a performance model to drive the auto-tuning process.
- A100 support via mma.16816
- Thread swizzling for conflict-free shared memory accesses without
padding
- Complete overhaul of the LLVM code generation in
codegen/selection/generator.cc to remove overengineering
- Added debugging capabilities in the Python binding
- Compilation error for kernels that spill
torch-blocksparse package:
* Now using warp shuffle in reductions when possible
* Various bugfixes in layout inference
* Added INFINITY, exponential and select
* Better error messages for unimplemented constructs
