gromero commented on code in PR #12182:
URL: https://github.com/apache/tvm/pull/12182#discussion_r930304436


##########
gallery/how_to/work_with_microtvm/micro_aot.py:
##########
@@ -24,8 +24,10 @@
 `Alan MacDonald <https://github.com/alanmacd>`_
 
 This tutorial is showcasing microTVM host-driven AoT compilation with
-a TFLite model. This tutorial can be executed on a X86 CPU using C runtime 
(CRT)
-or on Zephyr plarform on a microcontroller that supports Zephyr platform.
+a TFLite model. AoTExecutor reduces the overhead of parsing graph at runtime 
+compared to GraphExecutor. Also, we can have better memory management using 
Ahead 

Review Comment:
   I think using lower case here for "ahead" is better, otherwise looks good!



##########
gallery/how_to/work_with_microtvm/micro_aot.py:
##########
@@ -110,11 +121,11 @@
 
 ######################################################################
 # Create a microTVM project
-# -----------------------
+# -------------------------
 #
-# Now that we have the comipled model as an IRModule, we need to create a 
project
-# with the compiled model in microTVM. To do this, we use Project API. We have 
defined
-# CRT and Zephyr microTVM template projects which are used for X86 CPU and 
Zephyr platforms
+# Now that we have the compiled model as an IRModule, we need to create a 
firmware project
+# to use the compiled model with microTVM. To do this, we use Project API. We 
have defined
+# CRT and Zephyr microTVM template projects which are used for x86 CPU and 
Zephyr platforms

Review Comment:
   would "Zephyr platform (singular)" be better here? I know the boards in 
Zephyr by themselves can be considered also "platforms" but since we are using 
the Project API and in the TVMC we consider Zephyr and Arduino platforms. Or 
even s/platforms/boards/ ? 



##########
gallery/how_to/work_with_microtvm/micro_aot.py:
##########
@@ -24,8 +24,10 @@
 `Alan MacDonald <https://github.com/alanmacd>`_
 
 This tutorial is showcasing microTVM host-driven AoT compilation with
-a TFLite model. This tutorial can be executed on a X86 CPU using C runtime 
(CRT)
-or on Zephyr plarform on a microcontroller that supports Zephyr platform.
+a TFLite model. AoTExecutor reduces the overhead of parsing graph at runtime 
+compared to GraphExecutor. Also, we can have better memory management using 
Ahead 
+of time compilation. This tutorial can be executed on a x86 CPU using C 
runtime (CRT)
+or on Zephyr platform on a microcontroller that supports Zephyr platform.

Review Comment:
   @mehrdadh I would say rather: "or on Zephyr platform on a microcontroller 
that is supported by Zephyr" or, shorter: "... or on a microcontroller/board 
supported by Zephyr".



##########
gallery/how_to/work_with_microtvm/micro_aot.py:
##########
@@ -81,20 +85,27 @@
 #
 # Now we need to define the target, runtime and executor. In this tutorial, we 
focused on
 # using AOT host driven executor. We use the host micro target which is for 
running a model
-# on X86 CPU using CRT runtime or running a model with Zephyr platform on 
qemu_x86 simulator
-# board. In the case of a physical microcontoller, we get the target model for 
the physical
-# board (E.g. nucleo_f746zg) and pass it to `tvm.target.target.micro` to 
create a full
+# on x86 CPU using CRT runtime or running a model with Zephyr platform on 
qemu_x86 simulator
+# board. In the case of a physical microcontroller, we get the target model 
for the physical
+# board (E.g. nucleo_l4r5zi) and pass it to `tvm.target.target.micro` to 
create a full
 # micro target.
 #
+
+# Use the C runtime (crt) and enable static linking by setting system-lib to 
True

Review Comment:
   +1 for adding explanation for `system-lib` : ) 



-- 
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]

Reply via email to