Age | Commit message (Collapse) | Author |
|
Change-Id: I49b2e8b4200c9ed654736d9451e4ab9c073b4b10
|
|
-Fixes NEWinogradConvolution memory manager usage
-Moves allocations in prepare staged for GEMMDispatchWrapper.
Change-Id: Ic1c709ee473eb4968f5a081f2bc26960f882f8db
|
|
Change-Id: I29e35024e29781a6b943b568abec9c73649215e6
|
|
Change-Id: I6ee2c0b670727fc808fa636c53ddfaec3a0036c9
|
|
Change-Id: I49f1d865f5e7562f1d80db849353a89ef77e6a9e
|
|
Output of Priorbox should be independent of the input
data layout and should always be in NCHW format
Change-Id: Ie80cd4e51c78945b158c0db1af1923bdf8d7ea7b
|
|
Change-Id: I95fdf5bd85becfe081f6ae587284f3b294681308
|
|
Change-Id: I62d937533967b29505d3ac8a51b513f0c6de8cd0
|
|
Fixes for:
- ReduceMean, reduction on the X axis for FP16 with 8 elements was
performed only up to a certain point. The fix now takes into account the
number of elements of the vector and does as many reductions as
necessary.
- YOLOLayer, activation for FP16 has to be performed on 32 bits until
the FP16 approximations is fixed.
Change-Id: I75373f4edd37de476e6fe1a56de3ef386b65c619
|
|
-Simplifies import memory interface
-Changes the used of void** handles with appropriate interfaces.
Change-Id: I5918c855c11f46352058864623336b352162a4b7
|
|
-Adds NHWC support for FP16
Change-Id: I61addf8efecf511ac8cd5f8aa9afc3e09c476aaf
|
|
FP mixed precision support added to GEMM kernel used for fp16 winograd conv on Midgard GPUs
Change-Id: I1619beb025fc484a1ac9d3e528d785edabbc7ee6
|
|
Change-Id: I770b044b67d93510ef65e556905135b34be7ea0a
|
|
Change-Id: I6e7dee8bd615a5eff01c523f208a218574ee5eab
|
|
kernels
Change-Id: I98183f95814442b6f3dbb67a1bdae99df05b9b01
|
|
Change-Id: I5d2ed5dcc342abff8124762f7bdee587cdf20032
|
|
- Fixing a bug for which we did not scale the boxes before transforming them
- Adding the correct_transform_coords option to BoundingBoxTransformInfo
Change-Id: I40281254bcf87e7c8583c119e99562414fe59822
|
|
BoxWithNMSLimitKernel
COMPMID-1792: Accuracy issue in CLGenerateProposals
This patch does the following:
- Some fixes for GenerateProposals function and tests
- Adapting BoxWithNMSLimitKernel to only accept U32 tensors as keeps_size
- Update 3rdparty
- Adds a small tolerance for a GenerateProposals test
Change-Id: Ia8ec1cdfe941fe05003645e86deb9ea6a6044d74
|
|
Introduced F32 accumulation for F16 winograd gemm and output transform
WinogradConvolution will be available for F16 only if fast math flag is enabled
Change-Id: I215593c205236a0f9669218437bb40b184ec6a4f
|
|
With this patch we are able to dispatch a single GPU job also in case of
batched-flatten
Change-Id: I755e7af29d44b24f67fa04bad3c9b7646e8deefc
|
|
Change-Id: I2c2250669829e399fdc2363f729dc5e68d8aac17
|
|
Change-Id: I8a9b1e16d90b9d99a6ff2a442347748432723b14
|
|
Change-Id: I99e1c3939cfea4b9cb0ddfa313706f31b213ca89
|
|
Change-Id: Ibc8d903c8d3c97b51dc8a3344197b56ad9d6c00e
|
|
Change-Id: Ia8d4e46ce5d9bb366af15726bc208dc14583c6ae
|
|
Change-Id: Icf813a0a87d4a07e180eafdb5fa916b2ea4028d2
|
|
num_elems_processed was passed as a scale instead of a step
Change-Id: I8c6d58fe4432f9f6beb31c0a1e02204c96775d98
|
|
AccessWindowRectangle::update_window_if_needed()
Change-Id: I56426cc9c9688a0aa0acdd439d5887c7ef208cd2
Note: The code to shrink the window hasn't been fixed yet.
|
|
Change-Id: I69e995973597ba3927d29e4f6ed5438560e53d77
|
|
In case of CIFG optimisation scratch buffer should have a size of
[batch_size, num_units * 3] else [batch_size, num_units * 4].
Change-Id: I43e46f7b52e791472f1196f36e9142240ba76c5c
|
|
Change-Id: Ib0798cc17496b7817f5b5769b25d98913a33a69d
|
|
Change-Id: Id94fb9c88a498d7b938f4f707e2e7b9b6df94880
|
|
Change-Id: I5bf5d751ec7c02d96c26a769f49d03ea23a248b7
|
|
Change-Id: Ie13a9eb6d417388b5de533bffa895796d9d2cf62
|
|
Change-Id: Ibab049f09413258c99335b7da6b151530a1bd136
|
|
and 8 tensors (Part 1)
Creating special cases for concatening 2 and 4 tensors.
Change-Id: I6a739a494ae45011acb65369e353f9ef96970b90
|
|
NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint
Change-Id: I1d5bc4d24059917f9ddef0873dd3043b1f2320a8
|
|
-Use raw string literals in regexp in CPUUtils.cpp
-Avoid implicit cast bool->int
Change-Id: I45a403ab8d0be02bb8dec267fe59545ad1074292
|
|
Change-Id: I93b14106cda8a1f640cf5acf120d31e2ebdaf495
|
|
Some systems don't have enough memory to run the VGG networks, for example
on systems with only 2GB memory the VGG example fails throwing a bad_alloc exception.
This patch introduces the concept of global memory policy in ACL, the policy
is a mechanism which could be used by the library's functions to try to reduce
memory consumption on systems with limited memory.
In this specific case the VGG examples set the policy to MINIMIZE. The GEMM
function checks if the policy is MINIMIZE and in this case does not use the
pretransposed weights path as this requires considerable more memory.
Change-Id: I53abc3c9c64d045d8306793ffc9d24b28e228b7b
|
|
Adds 0.5f after scaling AVG pooling to be able to round to nearest as
vcvtq_u32_f32 rounds towards zero.
Change-Id: I22ce78f9e628cf4184a317edabce47211ab09456
|
|
Removed gemmlowp_mm_bifrost_transposed_dot8 kernel as not used
Change-Id: I43cf463a3a4c0cdb2808621c534ffd5c9fd47ca1
|
|
Increases the steps for calculating invsqrt used in L2 pool by 1 to increase accuracy.
Change-Id: Ib938a963809b07c30d47ec0675abae75bc086986
|
|
Change-Id: I57bbdbef85d1f6e8cf1d13324f9cc38a3e3f0cc3
|
|
Change-Id: If5be77602e37b14aea63d7ec6d8adab324628f04
|
|
Removes:
-sve_interleave_8way_block2_16bit
-sve_interleave_8way_block4_16bit
-sve_sgemm_3VLx8
Change-Id: I0aa35fe974d8e122937dfe8923ecf63ff5a52001
|
|
-Uses output quantization information for the activation layer.
-Updates checks for BoundedRelu at CL side.
Change-Id: I0447860e90f1c89b67b9ace3c8daad713f6c64e0
|
|
Change-Id: I953f3b63aa4910650a1a3f6faea31beb4f6f376a
|
|
Change-Id: I67cbbce59d61d907fc4dc4c3997e96b347dfe895
|
|
CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloat
Since we perform an element-wise operation, it is not necessary to pass the output_depth3d.
Change-Id: Ibfa07a0706e902acf59b444aa61e18a348162ea9
|