aboutsummaryrefslogtreecommitdiff
path: root/chapters
AgeCommit message (Collapse)Author
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>
2023-11-28REDUCE_SUM: Specify the accumulator typeDominic Symes
For bf16_t data type, REDUCE_SUM is changed to use fp32_t as the accumulator type to be consistent with CONV2D. For other data types the accumulator type is the same as in_out_t (and so no change). Also correct the rank limit text. Update reduction pseudo-code to be consistent with REDUCE_SUM. Change-Id: I9923066be7d1b7edb0efd9bcf3365b4af9501beb 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>
2023-11-02Fix CustomOp description textJerry Ge
- CustomOp's domain attribute name has been updated to domain_name - Forget to update that for the description text part. Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: Ifa731125dc2f224ecc1cd661e238c7b27945db68
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
2023-09-21TRANSPOSE_CONV2D: Remove redundant out_shape argumentDominic Symes
The output shape can be calculated from the input shape and attributes so the out_shape argument is redundant. Change-Id: I7e6b0b7f03dc75ccdf967261fad4185c513ed187 Signed-off-by: Dominic Symes <dominic.symes@arm.com>
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
2023-09-11Add integer divide with floor for coordinate calculationEric Kunze
Define idiv_floor to give equivalent behavior to the floating-point floor function for image coordinate calculation. Change-Id: Id6268794b1e3ce5cc1114bda74dd06b892457a8e Signed-off-by: Eric Kunze <eric.kunze@arm.com>
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>
2023-08-18Update Custom operator argumentsEric Kunze
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
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
2023-08-11Add StatefulOps to TOSA specificationJerry Ge
Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: I63a4c1202a1eddcdedb222e64cac34557647ff21
2023-08-07Allow bias tensors to be broadcastDominic Symes
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>
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>
2023-07-06AVG_POOL2D conformance: fix kernel size namesDominic Symes
Change-Id: I188694080b74ec81c6dea675430e29db11ee6079 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>
2023-06-08Fix main inference conformance test dataDominic Symes
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>
2023-06-02Fix main inference conformance data generator scalingDominic Symes
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
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
2023-05-22Start introducing concepts to better describe the execution modelKevin Petit
Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: I75753adecd50b68e1184ab8aa59fd4c8c3638a1a
2023-05-18Remove orphaned pseudocode linesEric Kunze
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
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>
2023-05-02Fix logic error for RESCALE of uint16Eric Kunze
Existing logic was impossible to resolve Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I7f38ea57adb7fff9018a6f0fa8dd82453782d59b
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
2023-04-14Add enumerations to TOSA specificationEric Kunze
Currently used by RESIZE and AVG_POOL2D Change-Id: I4f401ac092fcf426e6d57b3729943135f634a31e Signed-off-by: Eric Kunze <eric.kunze@arm.com>
2023-03-21Update Argmax's rank maximum to MAX_RANKJerry Ge
Signed-off-by: Jerry Ge <jerry.ge@arm.com> Change-Id: Idc68dfee54f1855782e57a8855b4e4120e25e74d
2023-03-20Check the output shape of broadcast operationsDominic Symes
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
2023-03-17SCATTER/GATHER: Replace value_t with in_out_tKevin Petit
Most operators use in_out_t. This removes a special case. Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: Icfc86f1101d250700677959949bda466519152de
2023-03-07Update version to 0.60.0 for releasev0.60.0v0.60Eric Kunze
Also update copyright year on license. Signed-off-by: Eric Kunze <eric.kunze@arm.com> Change-Id: I6acf8b11990e436c4e2ceffa9c044a34a577a5ae
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>
2023-02-24Fix rank limits for various data layout operationsLuke Hutton
This commit removes the maximum rank 4 restriction from REVERSE, SLICE and TILE operations so that the new maximum is now MAX_RANK. In doing so some rank inconsistencies were also cleaned up, including: * Adding a minimum rank to the PAD op description * Adding level limit checks to SLICE and TILE ops * Adding checks for rank(shape1) == rank(shape) for TILE and TRANSPOSE ops * Add tensor_size(shape1) == tensor_size(shape) check for TRANSPOSE * Replace tensor name with shape name in pesudo code where necessary Change-Id: I94bb8ee0b6b720b2ba5a884ce9300dca6281245a Signed-off-by: Luke Hutton <luke.hutton@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>
2023-01-23Clarify description for LOGICAL_LEFT_SHIFTEric Kunze
Align with the definition for LOGICAL_RIGHT_SHIFT which was clearer. Change-Id: I9d8f33b54fb982a09597078eb14a7730c488bcef Signed-off-by: Eric Kunze <eric.kunze@arm.com>
2023-01-17RFFT2D: Adjust output height to be same as the inputLuke Hutton
The expected output shape of RFFT2d should be (N, H, W/2+1) as opposed to (N, H/2+1, W/2+1). Change-Id: I66d830f1ffa86417b57572b3cd904db0290cac42
2022-12-09SELECT: Replace use of cmp_t with bool_tKevin Petit
cmp_t is only used in the definition of SELECT and always defined to bool_t. This removes a special case in generators. Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: I9e7992bbfdf5c7fafdd55df90feb4dcbcdee2972
2022-12-05Clarify the type of condition tensorsDominic Symes
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>
2022-12-05Add Levels defintionDominic Symes
Add definition of Level 1.0. Signed-off-by: Dominic Symes <dominic.symes@arm.com> Change-Id: I1b34ae22396f273cc5ecdf99198fdbece6e2809c
2022-11-30SLICE: remove the mention of an axis in the descriptionKevin Petit
No such attribute. Signed-off-by: Kevin Petit <kevin.petit@arm.com> Change-Id: If1b1ece15589e9bf07971542783f51294a05aab9
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-01 04:09:43 +0000