Nicolas Vasilache

cc @vinodgro @jdemouth @jdemouth-nvidia

@ftynse > 1. what happens if the function you call has multiple outputs, some of which may be temporaries ?you can only assign one tensor in one expression. We should...

> Has this site gone dead already?? During conference submission crunch time, yes unfortunately :) but we're now back Reg. benchmarking, we have been making progress in #423 during this...

@perdavan for CPU-only tests there is ```test_mapper.cc```, ```test_mapper_llvm.cc``` and ```test_mapper_memory_promotion.cc``` which are unit tests that allow you to see what happens in the context of polyhedral mapping. ```test_core.cc``` shows what...

We had discussions about this with @Yangqing, @zdevito and others that it would be easy to: 1. split into ```inputs, outputs, temporaries``` 2. pass a ```alloc``` and a ```free``` lambda...

Hello @larspars My apologies for the long delay, I am sorry to say that the core TC team has moved on to other things. As far as I know the...

@ttheodor for more context I am thinking we could override the automatic HW key by some user specified string for load / store. The user is then responsible for ensuring...

Sorry I am late to the party as I missed this PR: > This brings me to my next question: how do we want to handle partial tiles? (i.e., assuming...

I have some tricking changes that I am trying to land in #10527, they will conflict with this, sorry .. Can you please rebase on top?

> It also renames workgroup to gridDim in order to have same naming convention with the mlir's gpu dialect. This is not a good change, IREE uses Vulkan terminology pervasively...