diff options
| author | Eric Kunze <eric.kunze@arm.com> | 2024-04-16 17:07:43 -0700 |
|---|---|---|
| committer | Eric Kunze <eric.kunze@arm.com> | 2024-04-19 16:55:40 +0000 |
| commit | d44dd79b926470b2588f56f514527d7ad45f4632 (patch) | |
| tree | 054e1b31b61e072dba9ece4168430e6f5a08eb8f /chapters | |
| parent | 618f66adbbd4db87cd1f51026e7f6b588031fb06 (diff) | |
| download | specification-d44dd79b926470b2588f56f514527d7ad45f4632.tar.gz | |
Add limit on size of tensor lists
List maximum varies by Level.
Also cleans up some stray references to tosa_list_t.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I66ba807361948f0b679d0865f967fa2684f8b279
Diffstat (limited to 'chapters')
| -rw-r--r-- | chapters/introduction.adoc | 2 | ||||
| -rw-r--r-- | chapters/operators.adoc | 7 |
2 files changed, 5 insertions, 4 deletions
diff --git a/chapters/introduction.adoc b/chapters/introduction.adoc index 95e405c..d931967 100644 --- a/chapters/introduction.adoc +++ b/chapters/introduction.adoc @@ -208,7 +208,7 @@ In terms of psuedo-code, if *graph* is a TOSA graph consisting of Baseline Infer [source,c++] ---- -bool tosa_test_compliance(tosa_graph_t graph, tosa_list_t input_list, tosa_level_t level) { +bool tosa_test_compliance(tosa_graph_t graph, tensor_list_t input_list, tosa_level_t level) { shape_list_t output_list_spec = tosa_allocate_list(tosa_output_shape(graph)); shape_list_t output_list_test = tosa_allocate_list(tosa_output_shape(graph)); tosa_graph_result = tosa_valid; // result starts as valid diff --git a/chapters/operators.adoc b/chapters/operators.adoc index b63ca1e..2f444e0 100644 --- a/chapters/operators.adoc +++ b/chapters/operators.adoc @@ -16,7 +16,8 @@ Their behavior can be configured using attribute arguments. Arguments may have one of the following types: * `tensor_t<element_type>`, abbreviated `T<element_type>`, represents a tensor whose elements are of type `element_type` where `element_type` can be any of the data types supported in TOSA. -* `tensor_list_t` represents a list of tensors. When lists are homogeneous, containing tensors of the same type, their type is further qualified as follows: `tensor_list_t<T<element_type>>`. +* `tensor_list_t` represents a list of tensors. When lists are homogeneous, containing tensors of the same type, their type is further qualified as follows: `tensor_list_t<T<element_type>>`. + +The maximum number of elements in a tensor list is set by the MAX_TENSOR_LIST_SIZE level parameter. * `tosa_graph_t` represents a TOSA graph (see <<operator-graphs>>). Arguments belong to one of three categories: Input, Output, or Attribute. The category to which an argument belongs further constrains its type: @@ -47,7 +48,7 @@ shape_list_t tosa_output_shape(tosa_graph_t graph); Similarly the type tensor_list_t will be used for a list of tensors and the following function returns the shape of a tensor list: [source,c++] ---- -shape_list_t tensor_list_shape(tosa_list_t tensor_list); +shape_list_t tensor_list_shape(tensor_list_t tensor_list); ---- The following function denotes the execution of a TOSA graph within a TOSA context, @@ -59,7 +60,7 @@ implementation-defined order that must be a topological ordering of the TOSA gra [source,c++] ---- -tosa_execute_graph(tosa_context_t context, tosa_graph_t graph, tosa_list_t input_list, tosa_list_t output_list, tosa_level_t level) { +tosa_execute_graph(tosa_context_t context, tosa_graph_t graph, tensor_list_t input_list, tensor_list_t output_list, tosa_level_t level) { ERROR_IF(tensor_list_shape(input_list) != tosa_input_shape(graph)); ERROR_IF(tensor_list_shape(output_list) != tosa_output_shape(graph)); |