This project is mirrored from https://review.mlplatform.org/tosa/specification.
Pull mirroring updated .
- Sep 13, 2023
-
-
Eric Kunze authored
Prepare for release Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: Ib88eaf0c6028a1c035fd5e84ed572d6928b85a36
-
- Aug 18, 2023
-
-
Eric Kunze authored
CUSTOM operators are still implementation specific, but now have attributes added to identify and namespace the underyling operation. Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I8db2fffd0b34958bd8c718633a130941f32f962b
-
- Aug 17, 2023
-
-
Eric Kunze authored
Integer inputs and outputs to TOSA operators are now defined as signless values. In most instances the operator will used signed arithmetic as indicated in previous versions of the specification resulting in little functional change to the specification. New attributes have been added to the RESCALE operator to indicate whether the input and output values should be treated as signed or unsigned. Explicit use of static_cast, sign_extend, zero_extend and truncate are added to the pseudocode to avoid ambiguity. Change-Id: I71c67d3e5aeaabc418c768f821fce6ee3eebb65b
-
- Aug 16, 2023
-
-
Dominic Symes authored
Adds a local_bound flag to convolution operations. If the local_bound flag is true then the output accuracy for floating-point is measured relative to the input tensor data local to the particular convolution output. If the local_bound flag is false then the output accuracy for floating-point is measured relative to the whole input tensor. This accuracy measure is the default and more approapriate for implementations with non local optimizations (such as transform based fast convolutions). Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I64e3e4981a63e26e6391149e28d5d71e7ef5560a
-
Dominic Symes authored
Shape inference derives the shape of tensors in the graph from input shapes. Operations such as RESHAPE may need calculations to derive the new tensor shape. This patch: - Adds a DIM operator to get the size of a tensor in a given axis as a rank 0 tensor of type shape_t - Allows RESHAPE to take a 1D shape tensor as input for the new shape - Allows RESIZE, TILE, PAD to take input sizes based on shape tensors. - Allows ADD, SUB, MUL, INTDIV to operate on rank 0 shape_t tensors - Allows CONCAT to concatenate 0D shape_t tensors to a 1D shape_t tensor - Adds CONST support for shape_t tensors In this version of the specification shape tensors must be resolvable to constants at backend compile time. Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I484bd44452453b5e05d0d8a82689564587b224e4
-
- Aug 15, 2023
-
-
Eric Kunze authored
We've seen networks with >64 scale ratios that we would expect to run on systems implementing the 8K level. Raise the ratio to 256. Change-Id: I5a72a533b2125fe56ffedc8b8d5c31bb96f60f10 Signed-off-by:
Eric Kunze <eric.kunze@arm.com>
-
- Aug 11, 2023
-
-
Jerry-Ge authored
Signed-off-by:
Jerry Ge <jerry.ge@arm.com> Change-Id: I63a4c1202a1eddcdedb222e64cac34557647ff21
-
- Aug 07, 2023
-
-
Dominic Symes authored
Bias tensors often have the same value for each channel. To allow for this the number of bias channels, BC, is permitted to be 1 or the output channel size. If BC == 1 then the bias is broadcast. Change-Id: I3262a6c699bd045f44201e2a123f9b792b9f67c9 Signed-off-by:
Dominic Symes <dominic.symes@arm.com>
-
- Aug 03, 2023
-
-
Eric Kunze authored
No functional changes, cleanup only Add missing copyright notices Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I0ddc8738f16aeced28fe7aa2ccc4fb715a84bd18
-
- Jul 24, 2023
-
-
Dominic Symes authored
Nesting of if/while is bounded by MAX_NESTING, set accoring to the TOSA level. Change-Id: If9435a143ffa6bd7ba2e46a68542459b3d723b76 Signed-off-by:
Dominic Symes <dominic.symes@arm.com>
-
- Jul 11, 2023
-
-
Eric Kunze authored
This aligns them with most of the other operators, with the maximum rank handled defined by the level parameter MAX_RANK. Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: Iad9dd285121b4252b39e8e4c3d12a762299c9722
-
- Jul 06, 2023
-
-
Dominic Symes authored
Change-Id: I188694080b74ec81c6dea675430e29db11ee6079 Signed-off-by:
Dominic Symes <dominic.symes@arm.com>
-
- Jun 23, 2023
-
-
Signed-off-by:
Jerry Ge <jerry.ge@arm.com> Change-Id: I3b6193f90541087be2de91837fb0c399e49a45b4
-
Dominic Symes authored
To be consistent with CONV2D, the FULLY_CONNECTED weight and bias arguments should be inputs rather than attributes. Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I77bd0ca36f98bccd0c2224060476e3b4ac04b4bf
-
- Jun 21, 2023
-
-
Eric Kunze authored
int8/uint8 zero point within the given range uint16 zero point is either 0 or 32768 other data types zero point must be 0 Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I3aa240dd8fb88a5f77b7ab90d4dbf634fbf4aa0b
-
Jerry-Ge authored
Signed-off-by:
Jerry Ge <jerry.ge@arm.com> Change-Id: Iabe1095e58ddce446d4c1781660bcfe82a596e61
-
Eric Kunze authored
Defined for floating-point types only. For integer versions, a TABLE should be used. Change-Id: Ieaec6e6eb3227c5dcd9741cddd57426002a8db4d Signed-off-by:
Eric Kunze <eric.kunze@arm.com>
-
- Jun 08, 2023
-
-
Dominic Symes authored
Correct the kernel size for the DEPTHWISE_CONV2D test data generator in Appendix A. Change-Id: I4fea6192bcd8a70d82d12543730cdc684fb839e5 Signed-off-by:
Dominic Symes <dominic.symes@arm.com>
-
- Jun 02, 2023
-
-
Dominic Symes authored
Correct scaling factor for tosa_mi_data() for S=1 and S=4 data sets. Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I3f09f758d82ccd64da8bb26fd219ff4d7a55918c
-
- Jun 01, 2023
-
-
Eric Kunze authored
Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: Ifdcc2433cf632136f9d025ce2bdd4445e4cd2d09
-
- May 25, 2023
-
-
Eric Kunze authored
Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I82eb4b2005cb4124840de9c452705bfaa8cf9738
-
- May 24, 2023
-
-
Kevin Petit authored
- Standardise the terminology for operator arguments. Argument, Operand, and Parameter were used interchangeably. - Introduce a templatized tensor_t<> type for tensor arguments. Scalars are represented by rank-0 tensors. - Types can be checked with the XSD schema. Signed-off-by:
Kevin Petit <kevin.petit@arm.com> Change-Id: Ic57b9387950824e994c5e7f9ec1489c29159b974
-
- May 23, 2023
-
-
Eric Kunze authored
Provide the mathematical formulas for sigmoid and tanh. Define the operation function for sigmoid and tanh for floating-point numbers. Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: Ib949d2e8e06309e5c5292aa0192746ad0f9b1f11
-
- May 22, 2023
-
-
Kevin Petit authored
Signed-off-by:
Kevin Petit <kevin.petit@arm.com> Change-Id: I75753adecd50b68e1184ab8aa59fd4c8c3638a1a
-
- May 19, 2023
-
-
Eric Kunze authored
The lines using the flattened pad values were removed, but the flatten call remained. Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I2b33945fa40ba413a657c4daaaf1820dd5b1c3d4
-
- May 18, 2023
-
-
Kevin Petit authored
Add REQUIRE statements to constrain the range where needed. Also fix a typo. Change-Id: I281e6249d8951b4cb3ff19eaf199660bed3feac9 Signed-off-by:
Kevin Petit <kevin.petit@arm.com>
-
- May 17, 2023
-
-
Signed-off-by:
Kevin Petit <kevin.petit@arm.com> Change-Id: I3b57615531eebebd356528deeb95a4930ca0b04c
-
This make it easier for implementations to use variadic constructs to implement input_list. Signed-off-by:
Kevin Petit <kevin.petit@arm.com> Change-Id: I3fcc40be30551d883ead506f5eba2aa08cc5186e
-
- May 15, 2023
-
-
Eric Kunze authored
Adds new optional element to argument 'rank' - Must supply minimum and maximum rank - Integer values or the level based "MAX_RANK" - trailing modifiers allowed for "MAX_RANK" - Displays in a new column in the document - Document generation validates rank against specified shape Change-Id: I507dc51bfe012d3230af43103c6c423a6f1e92b5 Signed-off-by:
Eric Kunze <eric.kunze@arm.com>
-
- May 09, 2023
-
-
Dominic Symes authored
- Add additional main inference compliance test data sets for dot product testing in Appendix A. - Express dot product test criteria in terms of tensors rather than individual dot products. - Add per-operation details on test set generation in Appendix A. - Clarify compliance vs conformance wording. - Clarify that the comment in the table of section 1.8.2 on integer saturation applies to the CAST from floating point to integer operation. Change-Id: I1b4c4493b02ed7c8a6eb547656c91ca67d4b0e86 Signed-off-by:
Dominic Symes <dominic.symes@arm.com>
-
- May 02, 2023
-
-
Eric Kunze authored
Existing logic was impossible to resolve Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: I7f38ea57adb7fff9018a6f0fa8dd82453782d59b
-
- Apr 28, 2023
-
-
Kevin Petit authored
resize_t is already used in the type support table for RESIZE, rename the mode enum to resize_mode_t. Also add a python function to get an enum object by name to the spec object. Change-Id: Id12c10929beda469c6e3714518d6e26f18ddd440 Signed-off-by:
Kevin Petit <kevin.petit@arm.com>
-
- Apr 27, 2023
-
-
Dominic Symes authored
The tensor size in bytes must fit within the level defined size range. Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I131e3aa7e8666b4d0093ae8198367f243081da51
-
- Apr 26, 2023
-
-
Kevin Petit authored
Also make LEVEL_CHECKs unconditional in pseudocode. The various MAX_* maximums are always defined. Change-Id: Iee5d8ade5cba3b4f86cc09f8b867b59fe18f5cfe Signed-off-by:
Kevin Petit <kevin.petit@arm.com>
-
- Apr 18, 2023
-
-
Kevin Petit authored
Also replace all instances of "co-ordinate" with "coordinate" for consistency. Signed-off-by:
Kevin Petit <kevin.petit@arm.com> Change-Id: Idff73092711d3ff85bf4db33df92924c754cf451
-
- Apr 14, 2023
-
-
Eric Kunze authored
Currently used by RESIZE and AVG_POOL2D Change-Id: I4f401ac092fcf426e6d57b3729943135f634a31e Signed-off-by:
Eric Kunze <eric.kunze@arm.com>
-
- Apr 06, 2023
-
-
Jeremy Johnson authored
Signed-off-by:
Jeremy Johnson <jeremy.johnson@arm.com> Change-Id: Ie75b0ea9c820fcd26602b9e143e06245a39b5a8b
-
- Mar 21, 2023
-
-
Jerry-Ge authored
Signed-off-by:
Jerry Ge <jerry.ge@arm.com> Change-Id: Idc68dfee54f1855782e57a8855b4e4120e25e74d
-
Eric Kunze authored
multiplies -> multiples Signed-off-by:
Eric Kunze <eric.kunze@arm.com> Change-Id: Iab407332a4f34ad658f7c7618f5811d120f21b80
-
- Mar 20, 2023
-
-
Dominic Symes authored
For an operation that performs broadcast the output shape size must be the maximum of the input shape sizes in each dimension. Additionally, the input dimension size must be 1 whenever an input shape does not match the output shape size in a dimension. Signed-off-by:
Dominic Symes <dominic.symes@arm.com> Change-Id: I89492f4ef22da76f84f12e720c79634ea42545bc
-