mlir
mlir copied to clipboard
tensorflow
"Multi-Level Intermediate Representation" Compiler Infrastructure
In a previous version of the toy example the lowering of the PrintOp to LLVM dialect was done differently. In that version the inner loop nest was generated as: >...
Can we maintain an .md or a doc table about MLIR adoption in projects with i.e. a status (planned, in-progress, complete) or target dates if known/declared. The same could be...
Subview op's with mixed shape (static and dynamic dimensions) currently parse and verify correctly. This is inconsistent given the number of size values that are taken as input. (In the...
It would be great to have a shared implementation for live variable analysis in core that could be used by various resource allocation schemes in tensorflow and others.
We don't have much canonicalization patterns for SPIR-V ops thus far. It would be nice to gradually build them up. Interesting ones include but not limited to: * Combine chained...
I notice that for this simple loop nest, -affine-vectorize does nothing, and emits nothing with its -debug-only= option either. I didn't dig any deeper, but at least the second part...
There are a few tests which are referenced in the tutorial documents but which don't seem to exist in the Test directory (or any of its subdirectories): - Ch3: transpose_transpose.toy...
LLVM provides the ```llvm-config``` which is very useful for both humans and automated configuration systems to query the properties of an LLVM installation. The command helps to find compilation options,...
Hi. I have found a couple of problems when trying to lower from Vector to LLVM using --vector-lower-to-llvm. Linalg and Affine dialects are also used. I attach two example input...
Metadata
Owner
Metadata
"Multi-Level Intermediate Representation" Compiler Infrastructure