User Details
- User Since
- Jan 6 2015, 1:11 PM (316 w, 8 h)
Today
Yesterday
THanks Nicolas for the explanation. Code looks fine to me. Still think that this is effectively adding promotion during tiling and doing this on tensors only is strange. Just trying to see if there is a more commonality between buffers and tensors so as to reuse things instead of completely new paths. Lets land and experiment. I understand how this would subsume promotion though.
Sun, Jan 24
Sat, Jan 23
Promotion is guaranteed to alloc and copy but is not guaranteed to create static shapes.
This in contrast has no guarantees of alloc/copy and is guaranteed to create static shapes.
Fri, Jan 22
Closed by commit 6e8ef3b76ab65960edd6ee99f387e75564d8d9db
Rebase and adress comments
Rebase
This feels like it is promotion on tensors with the linalg.simple_pad (for now and linalg.pad later) being used instead of the alloc(...) ; copy(...) method. So the tensor "promotion" and buffer promotion are living in entirely different places. Ill go deeper into this code, but my read of the tests informs this comment.
Removing errant function.
Rebase on top of enhancements to LinalgDependenceGraph allowing
dependence tracking through results.
Rebase on top of change to LinalgDependenceGraph that accounts for
tracking dependence through result values.
Oh thanks for fixing this. I did see the Kernel capability requirement. Got confused about it not being valid for Shader
Thu, Jan 21
Rebase
Adding test for tiling of fill op on tensor
Wed, Jan 20
Fri, Jan 15
Add a test
Thu, Jan 14
Address comments.
Rebase
Rebase
Address comments
Address comments
Wed, Jan 13
Tue, Jan 12
Rebase
Mon, Jan 11
Catching up on the discussion after break here. I agree the design is flawed. The strides are wrong of the result memref. As defined right now that would mean that lowering the memref will need to look at where the memref is coming from which is really wrong. You could return a memref with the strides embedded into the memref type so that it works fine, but I dont think that fully works either. I think Hanhan had a fix to this shortly. Thanks for the feedback!
Rebase and add extra test
Rebase
Fri, Jan 8
Fix build errors
Address comments
Addressed remaining minor comments
Minor comment addressed
Rebase
Rebase
Rebase
Rebase
Rebase
Sat, Jan 2
Dec 26 2020
Rebase
Rebase
Rebase
Rebase
Rebase
Dont need this anymore. Abondoning.
Rebase on chnages to linalg on tensors
Rebase
Rebase