diff options
author | Ayaan Masood <Ayaan.Masood@arm.com> | 2022-06-29 11:30:57 +0100 |
---|---|---|
committer | Ayaan Masood <Ayaan.Masood@arm.com> | 2022-06-29 11:30:57 +0100 |
commit | 4965faee41300393cd8d74da4b399fa4c4ee9030 (patch) | |
tree | 1054d6f89be70ec471007132dec97d325ecc0067 /SUPPORTED_OPS.md | |
parent | 68b8f2f9457d56df3211be5318e3682332bcefbf (diff) | |
download | ethos-u-vela-4965faee41300393cd8d74da4b399fa4c4ee9030.tar.gz |
MLBEDSW-6313 Static optimisation for Shape OP
*Shape OP value is available at compile time hence
it can be optimised
*Disconnected shape OP at compile time from parent
tensor
*Transformed shape OP tensor into constant
Change-Id: I0a024269e2b592c6146dd72e62d7a41951fb727a
Signed-off-by: Ayaan Masood <Ayaan.Masood@arm.com>
Diffstat (limited to 'SUPPORTED_OPS.md')
-rw-r--r-- | SUPPORTED_OPS.md | 25 |
1 files changed, 13 insertions, 12 deletions
diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md index 3e76670f..c258dfbd 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: `3.4.0` +Vela version: `3.4.0rc3.dev1+g5e0ae55` This file complies with [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md) @@ -55,17 +55,18 @@ Please check the supported operator list for your chosen runtime for further inf ### TFLite Generic Constraints -This is a list of constraints that all NPU operators must satisfy in order to be scheduled on the NPU. - -- Input(s) and Output tensors must not be dynamic -- Input(s) and Output tensors must have a defined shape -- Output tensors cannot be scalar -- Scalar Input tensors are only valid for op type: ADD, EXPAND_DIMS, MAXIMUM, MEAN, MINIMUM, MUL, SPLIT, SPLIT_V, SUB -- Input(s) and Output tensors must not be greater than 4D -- Input(s), Output and Weight tensors must have quantization parameters -- Input(s), Output and Weight tensors with quantization scales must be finite -- Input and Output tensors must have quantization scales that fit within float32 precision -- Constant tensors should not have NoneType-values +This is a list of constraints most NPU operators must satisfy in order to be scheduled on the NPU. +(Operators excluded from certain constraints are shown in brackets [ ] ) + +- Input(s) and Output tensors must not be dynamic +- Input(s) and Output tensors must have a defined shape +- Output tensors cannot be scalar +- Scalar Input tensors are only valid for op type: ADD, EXPAND_DIMS, MAXIMUM, MEAN, MINIMUM, MUL, SPLIT, SPLIT_V, SUB +- Input(s) and Output tensors must not be greater than 4D +- Input(s), Output and Weight tensors must have quantization parameters - [Shape] +- Input(s), Output and Weight tensors with quantization scales must be finite - [Shape] +- Input and Output tensors must have quantization scales that fit within float32 precision - [Shape] +- Constant tensors should not have NoneType-values - Tensors must be of type: int16, int32, int8, uint8 - Tensors which are int32 are only valid when op type is: ADD, MUL, SUB - Tensor dimensions must be in the range [1, 65535] |