Changes between Version 23 and Version 24 of venice/npu

Timestamp:

02/26/2026 10:39:47 PM (7 weeks ago)

Author:

Ryan Erb

Comment:

update examples

venice/npu

@@ -232 +232 @@
 
 == Upstream / Mainline NPU support (via Mesa)
+
 The IMX8MP has a Verisilicon NPU which is from Vivante. Vivante supports this via their vivante driver (/dev/galcore) but that is not an opensource driver so it would make sense to want to support the NPU with it's opensource equivalent (etnaviv driver). Support for this has been added to the Linux 6.10 kernel.
 
@@ -241 +242 @@
 
 
-On a Gateworks Venice board with an IMX8MP and an Ubuntu noble root filesystem:
-- update kernel to v6.10 with NPU support (if using an older kernel)
-{{{#!bash
-# update kernel
-cd /tmp && wget https://dev.gateworks.com/venice/kernel/linux-venice-6.10.6.tar.xz && tar -C / -xvf linux*.tar.xz --keep-directory-symlink && reboot
-}}}
-- create a non-root user (always a good idea but not required for mesa)
+Requirements:
+ * Gateworks Venice board with an IMX8MP and an Ubuntu noble root filesystem with a 6.10 or newer kernel
+
+- Create a non-root user (always a good idea but not required for mesa)
 {{{#!bash
 # create user
@@ -260 +258 @@
 su -l $USER
 }}}
-- to avoid a lot of python dependency issues with tensorflow-lite install an older version of python using the [https://launchpad.net/%7Edeadsnakes/+archive/ubuntu/ppa deadsnakes ppa] and create a virtualenv
+- To avoid a lot of python dependency issues with tensorflow-lite install an older version of python using the [https://launchpad.net/%7Edeadsnakes/+archive/ubuntu/ppa deadsnakes ppa] and create a virtualenv
 {{{#!bash
 sudo add-apt-repository ppa:deadsnakes/ppa
@@ -271 +269 @@
 }}}
  - Note Python 3.9, 3.10, 3.11 work, 3.12 does not
-- build mesa (22.2.0-devel fork with updated teflon support for imx8mp)
+- Build mesa (22.2.0-devel fork with updated teflon support for imx8mp)
 {{{#!bash
 # install build deps
@@ -287 +285 @@
 cd ..
 }}}
-- install tensorflow lite runtime (requires python <= 2.11)
+- Install tensorflow lite runtime (requires python <= 2.11)
 {{{#!bash
 pip3 install tflite_runtime
 }}}
-- clone tensorflow for some examples and assets used below
+- Clone tensorflow for some examples and assets used below
 {{{#!bash
 git clone https://github.com/tensorflow/tensorflow.git
 }}}
-- run teflon image classification test
-{{{#!bash
-# note this test requires python pillow, python numpy<2.0 and write access to /dev/dri/renderD128
+- Run teflon image classification test
+{{{#!bash
+# Note this test requires python pillow, python numpy<2.0 and write access to /dev/dri/renderD128
 pip3 install "numpy<2.0" pillow
 groups # make sure your in the render group (or have write access to /dev/dri/renderD128)
@@ -312 +310 @@
  -e ~/mesa/build/src/gallium/targets/teflon/libteflon.so
 }}}
-- run tensorflow label_image example:
- * first we need to patch the label_image example to use tflite_runtime
-{{{#!bash
-cd ~/tensorflow
-cat <<EOF |
+- Run tensorflow label_image example:
+ * First we need to patch the label_image example to use tflite_runtime. Use a text editor like vi to edit the file ~/tensorflow/tensorflow/lite/examples/python/label_image.py per the patch changes below: 
+{{{#!bash
 diff --git a/tensorflow/lite/examples/python/label_image.py b/tensorflow/lite/examples/python/label_image.py
 index d26454f921f..08c65962bf1 100644
@@ -340 +336 @@
        num_threads=args.num_threads)
 
-EOF
-patch -p1
-}}}
- * now we can run the label_image example:
+
+}}}
+ * Now we can run the label_image example:
 {{{#!bash
 # without acceleration (175.993ms on imx8mp)
@@ -350 +345 @@
   -l ~/mesa/src/gallium/frontends/teflon/tests/labels_mobilenet_quant_v1_224.txt \
   -i ~/tensorflow/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp
+0.874510: military uniform
+0.031373: Windsor tie
+0.015686: mortarboard
+0.011765: bulletproof vest
+0.007843: bow tie
+time: 176.267ms
+
 # with acceleration (14.138ms on imx8mp)
 python3 ~/tensorflow/tensorflow/lite/examples/python/label_image.py \
@@ -356 +358 @@
  -i ~/tensorflow/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp \
  -e ~/mesa/build/src/gallium/targets/teflon/libteflon.so
+Loading external delegate from /root/mesa/build/src/gallium/targets/teflon/libteflon.so with args: {}
+0.870588: military uniform
+0.031373: Windsor tie
+0.011765: mortarboard
+0.007843: bow tie
+0.007843: bulletproof vest
+time: 14.234ms
+
 }}}