Replies: 1 comment 2 replies
-
|
We're still moving the MLIR, but the plan has changed a little bit in terms of what the end-result should look like. We aim to update the end-to-end documentation by the end of next month. |
Beta Was this translation helpful? Give feedback.
2 replies
-
|
Cool. Thanks for the update. |
Beta Was this translation helpful? Give feedback.
-
|
https://www.tensorflow.org/mlir/xla_gpu_codegen This link is 404'ed. Is there a updated doc? |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
hi folks,
According to MLIR CodeGen for XLA, most of the current XLA's codegen will move to MLIR based implementation.
This page hasn't been updated for quite sometime.
According to my understanding the current status is at "Migrating Device LLVM IR (Task 3)". Am I right?
ElementalIrEmitter ops go for (4)which isRefactor old emitters to be LHLO -> Linalg, and write new Linalg emittersIs this still valid? Is this task on schedule?
Thanks
Beta Was this translation helpful? Give feedback.
All reactions