junrushao1994 commented on a change in pull request #5:
URL: https://github.com/apache/tvm-rfcs/pull/5#discussion_r676997469
##########
File path: rfcs/0001-meta-schedule-autotensorir.md
##########
@@ -22,36 +22,48 @@
## 1. Summary
-This proposal introduces Meta Schedule: a probabilistic scheduling DSL on TIR
that unifies the
+This proposal introduces Meta Schedule: a scheduling DSL on TIR that unifies
the
approaches of AutoTVM and Auto Scheduler (Ansor). Meta schedule provides a
pragmatic way to define
the space of automatic tuning, extensibility in terms of all possible TIR
schedule primitives like
tensorization and loop partitioning, and customizability on every layer of the
automation system.
-Meta Schedule is our 3rd generation automatic scheduling system.
+Meta Schedule is the 3rd generation automatic scheduling system.
## 2. Motivation
**Scheduling and design space.** In TVM TensorIR, optimization of a TensorIR
program is done via a
-sequence of transformations. For example, we reorder loops for better locality
and we tensorize for
+sequence of transformations. For example, reordering loops for better locality
and tensorizing for
specific hardware intrinsics. The process of invoking such a set of
pre-defined transformations is
called "**scheduling**", and each transformation is called a "**schedule
primitive**". These
Review comment:
That makes sense. I will introduce scheduling as a general concept that
both TE and TensorIR uses to transform the IR into potentially more optimized
form. There are subtle difference here, because TE relies on a schedule tree
which doesn't generate TIR until being lowered (i.e. `tvm.lower` is called),
while TensorIR scheduling directly transforms the IR without the indirect
schedule tree.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
