Age | Commit message (Collapse) | Author |
|
Update test set generator scaling factors so that
different set values occur on calls to set_data()
for each test S value.
Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: I5651944b31476e264360c0fce17fc7a074ae425e
|
|
Signed-off-by: Thomas Preud'homme <thomas.preudhomme@arm.com>
Change-Id: Ia26ffc9eae21bccdd1b48277ab494f1bc1b744c3
|
|
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
|
|
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
|
|
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
|
|
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I9678952cc78cdf90272ccd5179b6220c293d62f7
|
|
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
|
|
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
|
|
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
|
|
Is more appropriate than the Data Layout section
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I5427d867b13a69dc0d66e268db4c64e047c65c7f
|
|
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>
|
|
This appendix attempts to record the rationale for decisions made
when modifying the TOSA specification.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ia2332d39c075a53f611665c446566bd89385b9fb
|
|
Define behavior if multiple values are tied for the maximum.
Define behavior if NaN values are encountered.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Id05a680cd11a331ba84a8e38f9a7c77a71bcbb78
|
|
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
|
|
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
|
|
Previous version accidentally included the copyright in the rendered
document. Also made the operator organization match other operators.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Iabca81fb84d032f17b6915a3c5135cb469edd797
|
|
Initial accuracy requirements for RESIZE calculations.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I44f997df857915ca77b04dd0b87dee9ccac6e7b0
|
|
Only defined for floating-point types.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Ieae355076f9aac6882fab8530e6d7d9985a6e661
|
|
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
|
|
Add types for the angle caclulations.
Add conformance appendix section for RFFT2D.
Signed-off-by: Dominic Symes <dominic.symes@arm.com>
Change-Id: Ic0ab79c0784c6359d2d66290e124dfb670a879cc
|
|
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>
|
|
Change-Id: I75ea94d42c63e862af8e492da7f47ecd6caa1055
Signed-off-by: Kevin Petit <kevin.petit@arm.com>
|
|
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
|
|
Signed-off-by: Kevin Petit <kevin.petit@arm.com>
Change-Id: Icb824233e5be84ac0eb693459b65441e9ae6c545
|
|
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
|
|
- 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
|
|
This makes it easier to process the pseudocode automatically.
Change-Id: I84394192598e589de07d43a7af60b96788e14f86
Signed-off-by: Kevin Petit <kevin.petit@arm.com>
|
|
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>
|
|
i48_t is 48-bit, not 32-bit.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: Icd602931ffb5d74842359fae2a8885e96b85bf59
|
|
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
|
|
Cannot raise a negative base to a non-integral power.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I851006abc30bccb612b2a41e27f5c259bb221e41
|
|
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>
|
|
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>
|
|
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>
|
|
- 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
|
|
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
|
|
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
|
|
REDUCE_MIN, REDUCE_MAX, SELECT did not have an accuracy bound defined.
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I0fea091752dfcdc2bb55eae7becc68b9c1860e9e
|
|
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>
|
|
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
|
|
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>
|
|
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>
|
|
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
|
|
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
|
|
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
|
|
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
|
|
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I63a4c1202a1eddcdedb222e64cac34557647ff21
|
|
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>
|
|
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>
|
|
Change-Id: I188694080b74ec81c6dea675430e29db11ee6079
Signed-off-by: Dominic Symes <dominic.symes@arm.com>
|