diff options
author | Raul Farkas <raul.farkas@arm.com> | 2023-01-24 16:29:06 +0000 |
---|---|---|
committer | Raul Farkas <raul.farkas@arm.com> | 2023-02-07 15:55:53 +0000 |
commit | 090f18a55fcd4f7ae8ca1ae633418d05c62cbb6e (patch) | |
tree | 0d88ac2cf3253af50f63c507d8b397831bd32b7a /SUPPORTED_OPS.md | |
parent | 12e481147de461e3ea63a8b1dcbc1b66b0fe8e6f (diff) | |
download | ethos-u-vela-090f18a55fcd4f7ae8ca1ae633418d05c62cbb6e.tar.gz |
MLBEDSW-7237: CONV_2D stride 4 optimisation
* Extend stride range from (1,3) to (1,4)
* Add stride 4 support when optimising CONV_2D
* Add some tests for various strides
Change-Id: Iddaeb42c4a6e02695ecdd3740bc8b9dd59a7eb3c
Signed-off-by: Raul Farkas <raul.farkas@arm.com>
Diffstat (limited to 'SUPPORTED_OPS.md')
-rw-r--r-- | SUPPORTED_OPS.md | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index 43db4c5b..3d045923 100644 --- a/SUPPORTED_OPS.md +++ b/SUPPORTED_OPS.md @@ -1,7 +1,7 @@ # Supported Ops This file was automatically generated by Vela using the `--supported-ops-report` parameter. -Vela version: `3.6.1.dev17+g859efbe.d20230203` +Vela version: `3.6.1.dev18+g34cbb970` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -123,7 +123,7 @@ This is a list of constraints that the CONV_2D operator must satisfy in order to - Stride values for both width and height must be integer types - Dilation factor values for both width and height must be integer types -- Stride values for both width and height must be in the range [1, 3] +- Stride values for both width and height must be between 1 and 4 - Dilated kernel height must be in the range [1, 64] - Product of dilated kernel width and height must be in the range [1, 4096] - Weight tensor must be 8-bit @@ -139,7 +139,6 @@ This is a list of constraints that the DEPTHWISE_CONV_2D operator must satisfy i - Stride values for both width and height must be integer types - Dilation factor values for both width and height must be integer types -- Stride values for both width and height must be in the range [1, 3] - Dilated kernel height must be in the range [1, 64] - Product of dilated kernel width and height must be in the range [1, 4096] - Weight tensor must be 8-bit @@ -148,6 +147,7 @@ This is a list of constraints that the DEPTHWISE_CONV_2D operator must satisfy i - Optional Bias tensor must be of shape: 1D - Optional Bias tensor must be of type: int32, int64 - Optional Bias tensor values must fit within 40-bits +- Stride values for both width and height must be between 1 and 3 - For depth multipliers > 1, IFM channels must be 1 and OFM channels must be equal to the depth multiplier ### TFLite EXPAND_DIMS Constraints |