Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ethos-u
/
ethos-u-vela
/
refs/tags/3.7.0
tag
24779d825c327bec8d9ecdab64c8c80bba8792a3
tagger
Rickard Bolin <rickard.bolin@arm.com>
Tue Feb 28 11:38:05 2023 +0100
object
c60b7e3a4cda84a196801baa407a0dcc5d39832b
23.02 Release.
« Previous
a9fba26
MLBEDSW-6710: Revert Tensorflow 2.9
by Johan Alfvén
· 2 years ago
1156317
MLBEDSW-6703 Add SHAPE operator to supported operators
by Fredrik Svedberg
· 2 years ago
93f492b
MLBEDSW-6635: Update to TensorFlow 2.9
by erik.andersson@arm.com
· 2 years ago
d03dc50
MLBEDSW-6496 mlperf_deeplabv3_mnv2_ade20k_int8 fails at verify_output for u65
by Fredrik Svedberg
· 2 years ago
a04f2f7
MLBEDSW-6687 Vela crashes in npu_serialisation.py and tflite_graph_optimiser.py
by Fredrik Svedberg
· 2 years ago
c4d35eb
MLBEDSW-4856: Removed dead code
by oliper01
· 2 years ago
6b2a0b4
MLBEDSW-6261: Elementwise cascading
by erik.andersson@arm.com
· 2 years, 3 months ago
25f48dd
MLBEDSW-6314 Static optimisation for quantise OP
by Ayaan Masood
· 2 years ago
4965fae
MLBEDSW-6313 Static optimisation for Shape OP
by Ayaan Masood
· 2 years ago
68b8f2f
MLBEDSW-6639: Bug fix for evicted FMS in the fast storage allocator
by Johan Alfvén
· 2 years ago
5c30971
MLBEDSW-6347: Improved fast storage allocator
by Johan Alfvén
· 2 years, 1 month ago
5cc4c76
MLBEDSW-6614 Improve elementwise block size selection
by Fredrik Svedberg
· 2 years, 1 month ago
7ce6b32
MLBEDSW-4783: Make config handling more user friendly
by Rickard Bolin
· 2 years, 1 month ago
3ea7025
MLBEDSW-6422: Update release notes
by Tim Hall
· 2 years, 1 month ago
3.4.0
3.4.0.rc3
6d7a4f0
MLBEDSW-4783: Fix issue with relative paths to config files
by Rickard Bolin
· 2 years, 1 month ago
9b8b448
MLBEDSW-6593: Issue with finding some config files
by Rickard Bolin
· 2 years, 1 month ago
c3597d1
MLBEDSW-6406: Restrict numpy version limit
by Tim Hall
· 2 years, 1 month ago
cda4fcb
MLBEDSW-6563: networks failing with memory area exceeded in vela
by Tim Hall
· 2 years, 1 month ago
3.4.0.rc2
8bc7a65
MLBEDSW-6296: improvement_dram can become NaN
by Tim Hall
· 2 years, 1 month ago
eb5a4a8
MLBEDSW-6271: Key error when using --verbose-performance option
by Rickard Bolin
· 2 years, 1 month ago
0f98de6
MLBEDSW-6384: Updated weight buffering cycle calculation
by Johan Alfvén
· 2 years, 2 months ago
1e363b1
MLBEDSW-6430: MLCE: Update to graph has sequential ethos-u ops
by Johan Alfvén
· 2 years, 1 month ago
0b20781
MLBEDSW-6430: MLCE: Vela splitting network into two ethos operators
by Johan Alfvén
· 2 years, 2 months ago
1538dce
MLBEDSW-4783: Add config file directory structure
by Rickard Bolin
· 2 years, 2 months ago
c1be087
MLBEDSW-6271: MLCE: Layer wise Utilization info from Vela
by Tim Hall
· 2 years, 4 months ago
3dae1b6
MLBEDSW-6296: Updated condition for the opt size weight buffering schedule
by Johan Alfvén
· 2 years, 2 months ago
fd8b500
MLBEDSW-6263: Use separate tensors for double buffering
by Rickard Bolin
· 2 years, 2 months ago
6f4cb03
MLBEDSW-6296: Regression caused by bigger weight buffering size
by Johan Alfvén
· 2 years, 2 months ago
3.4.0.rc1
e51a05c
MLBEDSW-6454: Enable ReLu with negative alpha value
by Johan Alfvén
· 2 years, 2 months ago
f018a68
MLBEDSW-6518: Change to Python 3.7
by Dwight Lidman
· 2 years, 2 months ago
114baba
MLBEDSW-6452: Add byte offset in command stream
by Tim Hall
· 2 years, 2 months ago
e80038a
Revert "MLBEDSW-6312: Find block config improvement"
by Tim Hall
· 2 years, 2 months ago
ab677b3
MLBEDSW-6500: Address offset out of range
by Johan Alfvén
· 2 years, 2 months ago
b5df773
Revert "MLBEDSW-6263: Use separate tensors for double buffering"
by Tim Hall
· 2 years, 2 months ago
95b07c1
MLBEDSW-6425: Update to TensorFlow 2.8 (bugfix)
by Rickard Bolin
· 2 years, 2 months ago
d66f801
MLBEDSW-6425: Update to TensorFlow 2.8
by Rickard Bolin
· 2 years, 2 months ago
a2ec5aa
MLBEDSW-5384 FC layers run on NPU if underlying shape is 2D
by Ayaan Masood
· 2 years, 2 months ago
f9267da
MLBEDSW-6407: Vela fails with TypeError in npu_performance
by Tim Hall
· 2 years, 2 months ago
814d01f
MLBEDSW-6371: Output diff caused by operator clone bug
by Rickard Bolin
· 2 years, 2 months ago
cce7f2d
MLBEDSW-6339 Performance drop on wav2letter
by Johan Alfvén
· 2 years, 3 months ago
1e9ee1d
MLBEDSW-6406 Vela: Remove numpy version limit
by Fredrik Svedberg
· 2 years, 3 months ago
a3fe665
vela: Minor refactor
by Tim Hall
· 2 years, 4 months ago
dev/mlbedsw-6271
68df8a1
vela: Added debug info to external API
by Tim Hall
· 2 years, 4 months ago
d857507
Update version of Black to 22.3.0
by Jonas Ohlsson
· 2 years, 3 months ago
cc5f4de
MLBEDSW-6263: Use separate tensors for double buffering
by Louis Verhaard
· 2 years, 4 months ago
a19b467
MLBEDSW-6249: HillClimb improved stuck avoidance
by Louis Verhaard
· 2 years, 4 months ago
37ba98c
MLBEDSW-6098: Order check in cascade builder
by Louis Verhaard
· 2 years, 4 months ago
3c5cfe9
MLBEDSW-6298: MLCE: Unable to find a valid block config
by Tim Hall
· 2 years, 4 months ago
845e232
MLBEDSW-3367 Add mypy to pre-commit
by Jonas Ohlsson
· 2 years, 4 months ago
d2b5510
MLBEDSW-6312: Find block config improvement
by Louis Verhaard
· 2 years, 4 months ago
43d2758
MLBEDSW-5332: Bug fix optimise_strided_conv
by Louis Verhaard
· 2 years, 4 months ago
5c8f1e5
MLBEDSW-6245: Bug fix fast storage allocator
by Louis Verhaard
· 2 years, 4 months ago
77b448f
Fix bug storing encoded NPU weight UUIDs
by Jonas Ohlsson
· 2 years, 4 months ago
1ddb2ed
Vela: Fix diff in mean op
by Diqing Zhong
· 2 years, 4 months ago
f8e353b
Updated elementwise cycle calculation
by Johan Alfvén
· 2 years, 5 months ago
25e700c
MLBEDSW-3367 Update pre-commit flake8 version
by Jonas Ohlsson
· 2 years, 4 months ago
51bb337
MLBEDSW-6184: Release notes for version 3.3.0
by James Peet
· 2 years, 5 months ago
3.3.0
3.3.0.rc3
5a39218
MLBEDSW-5996: Clarify Sram_Only AXI port mapping
by Tim Hall
· 2 years, 4 months ago
0ab2edc
MLBEDSW-6247: MLCE: Issue when running a model with Padding
by Tim Hall
· 2 years, 4 months ago
d5cbef3
MLBEDSW-5873 Fixed divide by zero warning in memory transfer efficiency
by Ayaan Masood
· 2 years, 4 months ago
b801dda
MLBEDSW-5880 Fixed Vela verbose weight flag
by Ayaan Masood
· 2 years, 4 months ago
5e0ae55
MLBEDSW-6148: Reduce SRAM usage for elementwise op
by Johan Alfvén
· 2 years, 5 months ago
f3760e1
MLBEDSW-5995: Clarify installation instructions in README
by James Peet
· 2 years, 5 months ago
3.3.0.rc2
8682331
MLBEDSW-6036: Regenerate SUPPORTED_OPS.md
by James Peet
· 2 years, 5 months ago
0bb7ad1
MLBEDSW-5554: Constraints for single-axis mean operations on NPU
by James Peet
· 2 years, 5 months ago
1b9218e
MLBEDSW-6180: Protect overwrite of subgraph output
by Johan Alfvén
· 2 years, 5 months ago
3.3.0.rc1
a881055
MLBEDSW-5912 - Update to Python 3.8
by Rickard Bolin
· 2 years, 6 months ago
211165a
MLBEDSW-5582: MLCE: memory corruption with zero concat
by Johan Alfvén
· 2 years, 5 months ago
de6cb64
MLBEDSW-5839: Port of improved spilling behaviour
by erik.andersson@arm.com
· 2 years, 5 months ago
8d57aaa
MLBEDSW-6148: Allow overwrite of subgraph input
by Johan Alfvén
· 2 years, 5 months ago
e546def
MLBEDSW-3623: Diff on semantic_segmentation
by Rickard Bolin
· 2 years, 5 months ago
628928d
MLBEDSW-6060: Revert patch for MLBEDSW-5582
by Johan Alfvén
· 2 years, 5 months ago
1793e2f
Revert "MLBEDSW-5752: Fix version string when installing from shallow clone"
by Tim Hall
· 2 years, 5 months ago
e91b531
MLBEDSW-6018: Fix double buffering on dual core
by Louis Verhaard
· 2 years, 5 months ago
849ff81
MLBEDSW-5582: MLCE: memory corruption with zero concat
by Tim Hall
· 2 years, 6 months ago
2de898a
MLBEDSW-4870: Update to TensorFlow 2.7
by Rickard Bolin
· 2 years, 6 months ago
3c25ff6
MLBEDSW-5752: Fix version string when installing from shallow clone
by Rickard Bolin
· 2 years, 7 months ago
36da8d3
Optimize tensor allocation verification
by Johan Alfvén
· 2 years, 5 months ago
1c08afa
MLBEDSW-5534: Enet_640_640_int8 output diff
by Rickard Bolin
· 2 years, 6 months ago
bdb1d6e
Set product in driver action config struct
by Jonny Svärd
· 2 years, 6 months ago
3bbbed6
MLBEDSW-4704: Crash when loading empty constant tensors
by erik.andersson@arm.com
· 2 years, 6 months ago
91c5a14
MLBEDSW-5740: Fix assert when setting address on identical LUT tensors
by Johan Alfvén
· 2 years, 7 months ago
51a8dce
MLBEDSW-5844: Inconsistent calculation of read shapes
by Tim Hall
· 2 years, 6 months ago
3df5b96
MLBEDSW-5834: split shape is None when split offset is not
by Tim Hall
· 2 years, 7 months ago
86dcee2
MLBEDSW-4261: External contributions to MLPlatform
by erik.andersson@arm.com
· 2 years, 7 months ago
3751aa4
MLBEDSW-5629: MLCE: Model falling when creating explicit_padding
by Tim Hall
· 2 years, 7 months ago
7d7cb67
MLBEDSW-5554: Place MEAN op exceeding max height with axis==1 on CPU
by Rickard Bolin
· 2 years, 7 months ago
e3dd2f3
MLBEDSW-5717 Fix for sigmoid int16
by Patrik Gustavsson
· 2 years, 7 months ago
eed30ea
MLBEDSW-5417: Update release notes & supported ops
by Dwight Lidman
· 2 years, 7 months ago
3.2.0
3.2.0.rc3
3a1cfda
MLBEDSW-5514: Update PERFORMANCE.md
by Dwight Lidman
· 2 years, 8 months ago
480e31b
MLBEDSW-4996: Community bug reporting on ML Platform
by erik.andersson@arm.com
· 2 years, 10 months ago
837c31c
MLBEDSW-5507: Fix vela summary for passes
by Tim Hall
· 2 years, 7 months ago
3584a9c
MLBEDSW-3602: Output mismatch on some mobilenet_v1 int8 and int16
by Tim Hall
· 2 years, 8 months ago
f88771b
MLBEDSW-5148: Add author_email to setup.py
by Dwight Lidman
· 2 years, 7 months ago
e3d18b0
TOSA: Add ifm ofm elem size into raw output
by Diqing Zhong
· 2 years, 8 months ago
3.2.0.rc2
399c4a2
MLBEDSW-5383 npu_find_block_configs() differs between v2.1.1 and v3.1.0
by James Ward
· 2 years, 8 months ago
3.2.0.rc1
e6607c5
MLBEDSW-5496: Revert patch for MLBEDSW-4704
by Dwight Lidman
· 2 years, 8 months ago
9338978
MLBEDSW-5410 Clarify "Subgraph IO Summary" output
by James Ward
· 2 years, 9 months ago
cc8569f
MLBEDSW-5209 Vela: output diff depthwise with non-zero zero points
by Fredrik Svedberg
· 2 years, 8 months ago
b1a9a92
MLBEDSW-5437: MLCE: Vela ignores back2back Activations in model
by Tim Hall
· 2 years, 8 months ago
Next »