aboutsummaryrefslogtreecommitdiff
path: root/chapters/introduction.adoc
AgeCommit message (Collapse)Author
14 daysClarifications and cleanupEric Kunze
Miscellaneous cleanup and clarifications across the specification. No functional changes intended in this commit. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Iaa89e2f7828ae55abe3fbb19afafb6161a8a43fc
2024-05-22Main conformance: clarify zero sign for max, minDominic Symes
For maximum and minimum operations either sign of zero is permitted. Change-Id: If5ed01259a8c550f44599b2414f324a4a802e662 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2024-05-08Fix link to broadcast helpers in introductionThomas Preud'homme
Signed-off-by: Thomas Preud'homme <thomas.preudhomme@arm.com> Change-Id: Ia26ffc9eae21bccdd1b48277ab494f1bc1b744c3
2024-04-19Status update and text cleanupEric Kunze
Update the status section of the specification as well as various textual simplifications/clarifications. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Ie77039e537bc66e6d05b14c7e0705b1c1cc4be58
2024-04-19Add limit on size of tensor listsEric Kunze
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
2024-04-19Define TOSA versioning and compatibilityEric Kunze
Defines the versioning policy for TOSA. Includes definition of what can change between minor versions to retain compatibility. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Iad6073c986acf1696c0880ef9f614ce6f5cf1f16
2024-04-18Clarify error bound for non-normal valuesEric Kunze
Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I9678952cc78cdf90272ccd5179b6220c293d62f7
2024-04-17Switch fp8 to use non-saturating mode when convertingEric Kunze
Implementations should use non-saturating mode and call CLAMP if saturation is needed. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I7a79931552dd6c3ab5fc247a963e3e7ba1e38ae2
2024-04-16Clarify wording on level definitionsEric Kunze
Level 1.0 was never defined. Update to note that the ranges are for the levels defined in the specification. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: If38a7d1d96efd41e6708537ea5a1577c4c48a4de
2024-04-12Remove Main Training profileEric Kunze
The Main Training profile does not have any unique operators in the specification. Remove it as unneeded. New training operators can be added as extensions to existing profiles. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Ida5f49a1c7f71276508da0484dff5fae2444b9fc
2024-04-05Main Conformance: Update SIN,COS error boundsDominic Symes
Large input values to SIN or COS can lead to proportionately large errors in the angle and so in the SIN or COS result. Change-Id: Ibc0d8f4f1db27b8c8855c48a238040442c14ef71 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2024-03-13Modify convolution operators to improve bias handlingEric Kunze
Accumulator size moves to an enumerated attribute, out_t for floating-point changes to be the size of the input. Bias for floating-point also becomes the bit width of the input type. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I7369417adbb1106ce34a1978e7f511a30272c318
2024-03-12Modify TOSA profilesEric Kunze
Create composable profiles and profile extensions. Define requirements for a TOSA implementation to fully implement at least one profile. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I02cfb0171b2d227727f530cb29108b479206b25b
2024-02-23Accuracy requirements for RESIZE operatorEric Kunze
Initial accuracy requirements for RESIZE calculations. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I44f997df857915ca77b04dd0b87dee9ccac6e7b0
2024-02-14Add SIN/COS to elementwise operator setEric Kunze
Only defined for floating-point types. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Ieae355076f9aac6882fab8530e6d7d9985a6e661
2024-02-14Initial FP8 supportEric Kunze
Adds support for Open Compute Project (OCP) 8-bit floating point operations to the TOSA specification. Both E4M3 and E5M2 types are supported for profiles as indicated in the Supported Data Types table for each operator. FP8 operator list ARGMAX AVGPOOL CONV2D CONV3D DEPTHWISE_CONV2D MATMUL MAX_POOL2D TRANSPOSE_CONV2D CONST CAST CONCAT PAD DIM RESHAPE REVERSE SLICE TILE TRANSPOSE GATHER SCATTER Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I3dd83f48afcc3c880c5c88039337ff4f1fd95b1b
2024-02-09Main Conformance: Update POW error boundDominic Symes
Update POW error bound to allow for the error of a LOG, MUL, EXP sequence. Change-Id: I250635130bce2ac72cc39a9c9052d8e868f7cf41 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2024-01-31Add section of shape operatorsv0.90.0Eric Kunze
Rework of the shape operations. Shape operations are now done in shape specific operators rather than being based on type. shape_t is reworked to a list of size_t values. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I2fca0728f9caa6a6fc34a8ce9e389bb581eea959
2024-01-25Handle CAST from fp-type to narrow integer typesEric Kunze
Be explicit that the value is converted to int32 and then clamped to the output type range. Also remove use of apply_clip, replacing with either apply_clip_s or apply_clip_u Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I0efc7f4d653c1bef13c9989cfe2647208dad9617
2024-01-23pseudocode: use true/false consistently for boolean valuesKevin Petit
- Some operators were using True and False. - Document the use of true and false in the definition of the boolean number format. Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: Ic4c16c8527d46ca01d22e3c70c5371821a726df8
2024-01-15Main Conformance: TANH change, SCATTER clarificationDominic Symes
TANH can have cancellation between exp(x) and exp(-x) for small abs(x). To allow for this, a lower bound of 0.5*exp(-normal_fraction<in_out_t>) is set for the error bound. The TANH formula also can contain 4 exp() values, so the error bound is increased to 4 multiplied by the exp() error bound. SCATTER output size K must be as least as great as the number of indices W, as each index is distinct. Change-Id: I8d1f1c866bd59d8140cf7db76404f5006a04a3f3 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2024-01-09Fix typo in i48_t descriptionEric Kunze
i48_t is 48-bit, not 32-bit. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: Icd602931ffb5d74842359fae2a8885e96b85bf59
2024-01-09Main Conformance: Clarify REDUCE_PRODUCT conformanceDominic Symes
Update the REDUCE_PRODUCT conformance description to be consistent with EXP, POW, TANH, SIGMOID. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: I083c41ce09e70b51d07cfea30a4bbc4dff4a8657
2024-01-08Add note to POW accuracyEric Kunze
Cannot raise a negative base to a non-integral power. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I851006abc30bccb612b2a41e27f5c259bb221e41
2023-12-04Main Conformance: Update SIGMOID, TANH precisionDominic Symes
Change SIGMOID, TANH precision to allow an implementation using EXP. The bound is based on the EXP bound. Change-Id: I19582b31753ac614a1064a1b81961dbc54acf823 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2023-11-22Main Conformance: Update RSQRT precisionDominic Symes
Change RSQRT precision to 2 ulp to allow unfused square root and reciprocal. Also fixes: - a typo in EXP and POW conformance - exp2() handling of large negative values - symmetry about 0 of test set S=4 data generation - err_bnd cannot be negative - ulp not taken for reference value of 0 Change-Id: Idaeeb7b615f1634e8e09dea5f82827039780b462 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2023-11-01Main Conformance: Update EXP, POW precisionDominic Symes
EXP and POW are complex to implement in a precise number of ulp and a more flexible precision is given. Additionally, the test generater S=5 has the bias values changed to zero. If the bias values are non-zero then a bias for all output tensor elements of the channel can affect the dot product bias test. The numeric accuracy helpers are updated for bf16. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: Ia46a2ef4d577244b6983a08ce850de3db9573a42
2023-10-09Main conformance: clarify floating point accuracyDominic Symes
Clarify how to compare with an error range of a given number of ulp in this specification. Denormals may be flushed to zero. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: I1158e777030c4770d74f1acff84ab98e4a3420ac
2023-09-26Define missing accuracy boundsEric Kunze
REDUCE_MIN, REDUCE_MAX, SELECT did not have an accuracy bound defined. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I0fea091752dfcdc2bb55eae7becc68b9c1860e9e
2023-09-12Main Conformance: Add local_bound to RFFT2DDominic Symes
Also express the fp32_t acc_min_normal calculation without a double negation. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: I34ba274264bc511e60f0e01601d5d0a3f983e594
2023-09-07Main Conformance: Update dot product error boundv0.90a0Dominic Symes
Update the error bound for dot product operations to allow floating point accumulators where denormal values are flushed to zero. Change-Id: I1d5805f0ad613ca9d78c6a6da12e31d7df5f6cc4 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2023-08-17Change TOSA specification to signless typesEric Kunze
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
2023-08-16Main conformance: Add local bound flag for convolutionsDominic Symes
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
2023-08-16Add DIM operator and operations on shape_t valuesDominic Symes
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
2023-07-24COND_IF/WHILE_LOOP: Add nesting level limitDominic Symes
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>
2023-06-21Add ERF activation functionEric Kunze
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>
2023-05-24Formalise the description of operator argument typesKevin Petit
- 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
2023-05-22Update descriptions for activation functions.Eric Kunze
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
2023-05-18Replace uint6_t with int8_tKevin Petit
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>
2023-05-09Main inference compliance testing updatesDominic Symes
- 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>
2023-04-27Move the tensor size limit into the level range definitionDominic Symes
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
2023-04-26Generate level maximums from the XMLKevin Petit
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>
2023-04-18Fix description of tensor size limitKevin Petit
Also replace all instances of "co-ordinate" with "coordinate" for consistency. Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: Idff73092711d3ff85bf4db33df92924c754cf451
2023-02-24Main inference conformance additionsDominic Symes
Add a check on the error bias for dot product calculations and slightly increase the error variance bound for dot products. Change-Id: I518704d1fb1b109695b0f90f7ca6733850e6a8c7 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2023-02-01Main inference conformance draftDominic Symes
This patch contains a draft of the Main Inference profile floating-point conformance requirements. Change-Id: Ib1201fff7f4015668b2de6dccf4cd85b419c3f76 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
2022-12-05Add Levels defintionDominic Symes
Add definition of Level 1.0. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: I1b34ae22396f273cc5ecdf99198fdbece6e2809c
2022-10-19Define the index type for tensor co-ordinatesDominic Symes
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
2022-06-30Relax limit on input value for RESCALEEric Kunze
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
2022-06-17Initial work on floating-point type definitionEric Kunze
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
2022-06-17Rework the introductionEric Kunze
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
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-06 19:31:29 +0000