Riyadh Baghdadi

Hi, We are interested in this, but for now we do not have this feature in our immediate milestones. If you are interested in helping on this you are very...

Hi, Yes Tiramisu can generate code that has array access bounds parametrized by function arguments. The loop bounds in Tiramisu can be any expression (as long as the loop bound...

Yes, there is an example in the GEMM benchmark. The sizes are passed in SIZES and then used to initialize N, M and K: https://github.com/Tiramisu-Compiler/tiramisu/blob/master/benchmarks/linear_algebra/blas/level3/sgemm/cpu/sgemm_generator.cpp For the autoscheduler, I think...

When you set the size of a loop to 1 that loop will disappear, this will mean that you need to change the other optimizations to take this in consideration....

Hi, Pytorch intergration will be made open source in the near future. @IHIaadj is working on this and we should an open source version soon.

They are complementary and they attack different problems. Tiramisu is designed for optimizing dense loops using the polyhedral model. Its strength is in optimizing dense loops. TACO is designed for...

Hi @elfring , thanks. Good catch. Yes I agree. If you want to send a pull request this, we will be happy to accept it. There are few header files...

Hi @kazimuth , yes indeed. If we use the new Halide (and not our fork of Halide which is a bit old), that would solve the problem. On one of...

Oh Ok I see. That one is independent though. You should be able to compile and use Tiramisu without a problem. The problem that we have with CI is only...

Ok, here is the solution then: - Compile a fresh Halide as described in the Halide github page: https://github.com/halide/Halide (you do not need to compiler LLVM from sources) - Then...