In preparation for the 0.50.0 release

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ib7cda8120da40daef4c99e4614e62734512988c3

Dominic Symes authored Nov 30, 2022 and Eric Kunze committed Dec 05, 2022

Condition tensors used by the control
flow operations must contain a single
element.

Change-Id: Ie3cb8f0b4a4149cee1b3aacbfa720dd4cad02fbc
Signed-off-by: Dominic Symes <dominic.symes@arm.com>

Dominic Symes authored Nov 04, 2022 and Eric Kunze committed Dec 05, 2022

Add definition of Level 1.0.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I1b34ae22396f273cc5ecdf99198fdbece6e2809c

No such attribute.

Signed-off-by: Kevin Petit <kevin.petit@arm.com>
Change-Id: If1b1ece15589e9bf07971542783f51294a05aab9

Zero-point addition after rescale is not
permitted to overflow an int32_t.

Change-Id: I7bc99a9296dce9d48abe271e68f9069425c9c270
Signed-off-by: Dominic Symes <dominic.symes@arm.com>

Dominic Symes authored Oct 07, 2022 and Eric Kunze committed Oct 19, 2022

Tensor co-ordinate indices are signed 32-bit values
in this version of the specification.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I6b8dde500ef9c4c4c5688c1a43f8d658863e4a49

The restriction on border limits in the ERROR_IF is
-16 * scale_y_n <= border_y < scale_y_n
and
scale_y_n <= (1 << 11)

Together, these imply

-(1 << 15) < border_y < (1 << 11)

which fits in 16 bits

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I843f29a5efd8ea3fe559d83d33a3280b39bc7068

BF16 <-> FP32
FP16 <-> FP32

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I8b8d31dc5debb29b609e927a26fabe9ce71f81cd

Change resize_t to use the same type as in_t and out_t
for floating point data.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I3214d92477688b95ba572f22d34aab3fef7d0f82

Change-Id: I5206e59c6dd2212796a8d888d4ef8986ad1dfd2d
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Iee620079018191e3e58627c6d779b94d81d84727

Also be consistent to use the term 'rank'
rather than 'dims'.

Change-Id: Ica827fcfd44e9735da2d1a4ddb8cb1fa04c6479b
Signed-off-by: Dominic Symes <dominic.symes@arm.com>

Dominic Symes authored Jul 04, 2022 and Eric Kunze committed Aug 25, 2022

Increasing output pad values reduces the size of the output
region in the old definition. This is counter-intuitive.
This patch inverts the sign of the output pad values such
that increasing values leads to increasing pad. It also
specifies a pad limit range of output pad values that
give an output dependent on the whole input.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I47ff4ee67942aec9e728f0b42d87d20117f0b97a

tosa.xml had the wrong mode for 16-bit MATMUL.

Change-Id: I1feeac9b9a5f61c53d64ae826aa5727da21e5dce
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

This changes the arguments for the convolution operators to
be inputs rather than attributes for all profiles.

Change-Id: I9d5fd1ae721271b881179765dc44e966208150da
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

This converts portions of the asciidoc specification into an xml
document and schema. For the html and pdf outputs, the xml is
converted to asciidoc files that are included into the existing
specification.

The xml allows future automated uses of the tosa specification
while maintaining rough compatibility with the existing document.
No significant functional changes are included in this change.

Change-Id: I7f1f95c527638e270c157d58fcdec6a3510daea5
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

Check output shape matches the padded
input shape.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I8e335ce9b086a36d9e38aa332ecc88782e040cc6

Define scaling factor as a ratio of integers so
that output dimensions can be derived from input
dimensions without rounding.

Change-Id: Iddfd9ff549edf2963bf22047e8641a348cadb35f
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

The current value is too strict, and can lead to some cases to fail.
By making the new value limit between (-1 << shift-1) and (1 << shift-1),
we still restrict the input value a range that works for optimized implementations
that left shift their values before multiplying.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ib4f49732e361418884888d398087560da3ccd6e8

Use branch v0.30 and tag 0.30.0 for previous version.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I1469a9f631e44488142a1c0536e1d4be10153958

Also update copyright date for specification.

Change-Id: I72d2423247f62fa304d0c0535ef33defb903b74e
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

The current version does not match the reference model or
serialization library. Revert to the old behavior until the
model is updated and tested that it works correctly.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I237dc3e94e6c31337073524527da75084ba7b578

Define operations in terms of common floating-point data
types. Definitions for the data types are in the introduction.

Added a section to describe status of the different profiles.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Iac57026806acfb7913f40af61176322fb02b7cc1

The information on quantization and numerics was out of date.
The tensor access helpers were also consolidated and moved into
their own section in the pseudocode chapter.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I472e674ed88f4a3ef379010cf50b13cf8afa5f17

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ib953cc4b635469034300662b9ae997d0a1bd58a7

The captions for the images used 'direction', instead of 'inverse'
which is the attribute name.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I4d8ab9642288efb984d03b7862068e09334ce8f6

Adds FFT2D for complex->complex FFT
Adds RFFT2D for real->complex FFT

Change-Id: Id50f96b8f66f17c3020767c002f0c1f41a76d62e
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: Ibb60c192ea60b665cec8d91f7de7cc6e3f553fa6

Remove the calculation of a -1 dimension from the operator.
Calculates the new coordinates, and adds the proper
tensor_read/tensor_write for the data.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Iad1d83c170732bdfb3652dead9044809168b23d2

Replicates multiples times, not multiplies.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I78c19013d08295171a20fead17661a8f9ea68ac8

An unsigned 16-bit integer data type for use with image networks.
Limited to only operating with the RESCALE operator for conversion
to signed int16.

Zero point can be 0 or 32768 in the RESCALE to allow for no loss of
precision (by subtracting 32768), or keeping all values as positive,
(zero point=0) with scaling/clipping as defined in the other RESCALE
arguments.

Change-Id: Id1aebab68fa207f8f8cc235fc3fa5d050307198e
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

They are arrays of multipliers and shifts to handle per channel
scaling.

Change-Id: I4451a87ef4d710fcb93745c8df73ec41752415c0
Signed-off-by: Eric Kunze <eric.kunze@arm.com>

Kevin Petit authored May 03, 2022 and Eric Kunze committed May 04, 2022

Signed-off-by: Kevin Petit <kevin.petit@arm.com>
Change-Id: I15ba640629433f87648ece24ffe723a60c8aaf11

Define scaling factor as a ratio of integers so
that output dimensions can be derived from input
dimensions without rounding.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: Ie4c1a323dec80379fb0d6db1767777e6c9760a11

Jeremy Johnson authored Apr 26, 2022 and Eric Kunze committed May 03, 2022

Output dimensions should have been worked out correctly by the end
of the compilation to TOSA

Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: I0193958d7d51bf1c6915a0953daa514f86516710

Clarify for types previously definded as int
the width assumed by the specification.

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: Ied62d4803a4323a600d33cff09752a76ca48f18d

It should be an attribute.

Signed-off-by: Kevin Petit <kevin.petit@arm.com>
Change-Id: I2c9c73605486a44297dad105dbdb94abfb5903fb

- The input/output types for CAST should be in_t* and out_t*
- The shape for the multiplier and shift arguments to RESCALE was in the wrong column

Change-Id: I0a3c4ffed15e36f0c4bf8fc9b4a84df5a17a5523
Signed-off-by: Kevin Petit <kevin.petit@arm.com>

For each tensor op clarify how the output dimensions
of output height (OH) and output width (OW) relate
to the input height (IH) and input width (IW).

Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: Iad36041f54e439c944cacf08afac5567dd2bad3f

Will also fail if aspell is not installed

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I4cab802b64a938797d84604af80cb37caa04f401