Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
armnn
/
refs/tags/v22.08
/
src
/
backends
tag
9bcf4954d4a481e8f2e165c76255b8ba5dc01129
tagger
Nikhil Raj <nikhil.raj@arm.com>
Thu Aug 25 15:50:42 2022 +0100
object
0ba0b2bf80f1d7aff1eff8de2b67eb04081b2af0
v22.08
« Previous
e011d20
IVGCVSW-4209 Create a public API for the ArmNN Utils
by Matteo Martincigh
· 4 years, 7 months ago
2445744
IVGCVSW-3864 Add support for per-channel QSymm8 DepthwiseConvolution2d to Neon backend
by Aron Virginas-Tar
· 4 years, 7 months ago
9820d30
MLCE-115 Remove redundant error checking in CL backend
by Matthew Bentham
· 4 years, 7 months ago
710f664
IVGCVSW-4148 Extend reporting of quant multiplier > 1 as unsupported on ACL to per-axis case
by Aron Virginas-Tar
· 4 years, 7 months ago
899f64f
IVGCVSW-3859 Per-channel QSymm8 support of Convolution2d in Cl
by Keith Davis
· 4 years, 7 months ago
e9323ec
Add IsQuantizeType(DataType) for use in validation functions
by Aron Virginas-Tar
· 4 years, 7 months ago
94c4fef
IVGCVSW-3728 Add CL workload for Slice
by Aron Virginas-Tar
· 4 years, 7 months ago
21fc28b
IVGCVSW-3866 Add support for per-channel QSymm8 Convolution2d to Neon backend
by Aron Virginas-Tar
· 4 years, 7 months ago
e131a0b
IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20
by Sadik Armagan
· 4 years, 8 months ago
b86a382
IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACL
by James Conroy
· 4 years, 8 months ago
cf7c1c6
IVGCVSW-4151 HAL 1_2 Dequantize FP32 Per Channel Tests on CpuAcc Failing
by Sadik Armagan
· 4 years, 8 months ago
434de54
Revert "Only enable mixed precision FP16 pooling for Android Q"
by Kevin May
· 4 years, 8 months ago
52ec346
IVGCVSW-3697 Add check for ArgMinMax QAsymm8 to ClLayerSupport
by Francis Murtagh
· 4 years, 8 months ago
85ad78c
IVGCVSW-4068 Add Guid to Workload
by Narumol Prangnawarat
· 4 years, 8 months ago
036f02d
IVGCVSW-3729 Added neon slice workload and supporting neon layer tests
by josh minor
· 4 years, 8 months ago
49d0f12
MLCE-144 Cts NNAPI test cases failed
by Mike Kelly
· 4 years, 8 months ago
17d8d85
IVGCVSW-3486 Add clipping parameter validation in LstmQueueDescriptor
by janeil01
· 4 years, 8 months ago
87972be
IVGCVSW-4119 Fix FP16 to FP32 fallback mechanism in optimizer to work with Dequantize
by Aron Virginas-Tar
· 4 years, 8 months ago
5716de2
IVGCVSW-4140 Report per-axis quantization as unsupported for DepthwiseConvolution on ACL backends
by Aron Virginas-Tar
· 4 years, 8 months ago
30db8ad
NNXSW-1853 Change SubgraphViewSelector algorithm
by Rob Hughes
· 4 years, 8 months ago
721b82f
Print CMake messages on stdout rather than stderr
by Rob Hughes
· 4 years, 8 months ago
db1a283
Add FP16 support to DebugWorkload
by Aron Virginas-Tar
· 4 years, 8 months ago
60538ad
Only enable mixed precision FP16 pooling for Android Q
by Derek Lamberti
· 4 years, 8 months ago
f4c502f
Fix redundancy in call to configure() in ACL DepthwiseConvolution workloads
by Aron Virginas-Tar
· 4 years, 8 months ago
e3803ea
CL & Neon workload factories inherit from WorkloadFactoryBase
by Derek Lamberti
· 4 years, 8 months ago
68a4dbc
IVGCVSW-4053 Enable ArgMinMax EndToEndTest for NEON/CL
by James Conroy
· 4 years, 8 months ago
1939df5
IVGCVSW-4128 Add Signed32 to supported input types for Ref ArgMinMax
by Francis Murtagh
· 4 years, 8 months ago
2dc0572
IVGCVSW-3695 Add CL ArgMinMax workload
by James Conroy
· 4 years, 10 months ago
663c184
IVGCVSW-4051 Update ACL pin to 94e0cf960ea6116eb57fa88d9b951f859b52c602
by James Conroy
· 4 years, 8 months ago
d8df026
IVGCVSW-4079 Add support of per-axis quantization to DepthwiseConvolution2d
by Teresa Charlin
· 4 years, 8 months ago
94d3b93
IVGCVSW-3839 Add support of per-axis quantization to reference TransposeConvolution2d
by Aron Virginas-Tar
· 4 years, 8 months ago
62cdb08
IVGCVSW-4064 ArmNN Master fails due to an error in RefArgMaxAxis2Uint8Test
by Francis Murtagh
· 4 years, 8 months ago
07f25e0
IVGCVSW-4104 Report Conv2d per-axis quantization unsupported on ACL backends
by Aron Virginas-Tar
· 4 years, 8 months ago
3fec1ea
IVGCVSW-4067 Change LayerGuid to use ProfilingGuid
by janeil01
· 4 years, 8 months ago
ffab16f
IVGCVSW-4077 Disable NEON memory import
by James Conroy
· 4 years, 8 months ago
130ec60
IVGCVSW-4108 Fixed invalid data type exception
by Mike Kelly
· 4 years, 8 months ago
70f609b
MLCE-144 Fix cts MAX_POOL_2D_V1_0 tests
by Finn Williams
· 4 years, 8 months ago
5edc881
IVGCVSW-3837 Add support for per-axis quantization to reference Convolution2d workload
by Aron Virginas-Tar
· 4 years, 8 months ago
ec33a91
IVGCVSW-4038 Convert Strided_Slice Shrink_Axis_Mask Parameter to ACL format
by Francis Murtagh
· 4 years, 8 months ago
b67f957
IVGCVSW-3836 Add support for Int32 per-axis scales
by Aron Virginas-Tar
· 4 years, 8 months ago
13b653f
IVGCVSW-3843 Add support of per-axis quantization to BuildArmComputeTensorInfo
by Aron Virginas-Tar
· 4 years, 8 months ago
5236e1d
IVGCVSW-3835 Create Encoder and Decoder for QSymm8PerAxis
by Keith Davis
· 4 years, 8 months ago
f710793
Add fp16 support for dequantize
by Jan Eilers
· 4 years, 8 months ago
d1f5773
IVGCVSW-3698 Add EndToEnd Layer test for ArgMinMax
by Narumol Prangnawarat
· 4 years, 8 months ago
3f4d710
Increase tolerance for bias scale quantization calculation for ResNet50v2
by ricbur01
· 4 years, 8 months ago
c601aa6
GitHub #292 Move BackendRegistry.hpp to the public API
by Matteo Martincigh
· 4 years, 8 months ago
d905307
IVGCVSW-3842 Add per-axis quantization support to ValidateBiasTensorQuantization()
by Aron Virginas-Tar
· 4 years, 8 months ago
9be4916
IVGCVSW-4039 AndroidQ (HAL 1.2) driver support for Fp16
by Sadik Armagan
· 4 years, 8 months ago
b3670b1
Refactor Resize layer tests
by Aron Virginas-Tar
· 4 years, 8 months ago
48623a0
IVGCVSW-4018 Move QuantizeHelper.hpp to armnnUtils
by Aron Virginas-Tar
· 4 years, 9 months ago
57d10b7
IVGCVSW-3962 Return 0 for Neon GetExportFlags()
by James Conroy
· 4 years, 9 months ago
d80cc0c
Fix build failures on RPi 4B
by Jammy Zhou
· 4 years, 9 months ago
e606b7c
IVGCVSW-4009 Enable IsLayerSupported tests again
by Derek Lamberti
· 4 years, 9 months ago
3bc00ec
IVGCVSW-3999 Add unit tests for new comparison operations
by Aron Virginas-Tar
· 4 years, 9 months ago
b99ef39
IVGCVSW-4009 Get string name for StandInLayer type
by Derek Lamberti
· 4 years, 9 months ago
013c390
IVGCVSW-4009 StandInLayer frontend API
by Derek Lamberti
· 4 years, 9 months ago
77bfb5e
IVGCVSW-3993 Add frontend and reference workload for ComparisonLayer
by Aron Virginas-Tar
· 4 years, 9 months ago
20bea00
IVGCVSW-3895 Add EndToEndLayerTest for the Reference Implementation of LOG_SOFTMAX
by Sadik Armagan
· 4 years, 9 months ago
062e0e9
IVGCVSW-3892 Add EndToEnd Layer test for INSTANCE_NORMALIZATION
by Sadik Armagan
· 4 years, 9 months ago
e662a94
IVGCVSW-3975 Add reference workload for LOG_SOFTMAX
by Aron Virginas-Tar
· 4 years, 9 months ago
f982dea
IVGCVSW-3973 Add frontend for LOG_SOFTMAX
by Aron Virginas-Tar
· 4 years, 9 months ago
a3600ba
IVGCVSW-3967 Avg_Pooling2d Fails on CL NHWC FP16
by Sadik Armagan
· 4 years, 9 months ago
c8724c7
IVGCVSW-3944 Add ArgMinMax output shape validation
by James Conroy
· 4 years, 9 months ago
09ca49c
IVGCVSW-3888 Add INSTANCE_NORMALIZATION Reference implementation
by Kevin May
· 4 years, 9 months ago
0d4863d
IVGCVSW-3890 Add NEON INSTANCE_NORMALIZATION Workload
by Sadik Armagan
· 4 years, 9 months ago
8168f40
IVGCVSW-3889 Add CL workload for INSTANCE_NORMALIZATION
by Aron Virginas-Tar
· 4 years, 9 months ago
c6e5a6e
IVGCVSW-3925 Add Backward compatibility for ITensorHandle CreateTensorHandle functions
by David Monahan
· 4 years, 9 months ago
ce5045a
IVGCVSW-3932 Add frontend for INSTANCE_NORMALIZATION
by Kevin May
· 4 years, 9 months ago
d47a064
IVGCVSW-3696 Add NEON ArgMinMax workload and tests
by James Conroy
· 4 years, 10 months ago
f97f6da
IVGCVSW-3738 Add end-to-end layer test for DepthToSpace
by Aron Virginas-Tar
· 4 years, 9 months ago
680f991
IVGCVSW-3882 Update ACL pin
by Narumol Prangnawarat
· 4 years, 9 months ago
99836d3
IVGCVSW-3734 Enable FLoat16 unit tests for DepthToSpace on NEON
by Aron Virginas-Tar
· 4 years, 9 months ago
b280196
IVGCVSW-3732 Add CL workload for DepthToSpace
by Aron Virginas-Tar
· 4 years, 9 months ago
2f00b74
IVGCVSW-3734 Add NEON workload for DepthToSpace
by Aron Virginas-Tar
· 4 years, 9 months ago
83239f9
IVGCVSW-3689 Support Import of Output Tensors for the Neon Backend
by Ferran Balaguer
· 4 years, 10 months ago
9926e58
IVGCVSW-3908 Fix DepthToSpace reference unit test failures on Android Q
by Aron Virginas-Tar
· 4 years, 10 months ago
73f6642
IVGCVSW-3885 Add reference workload for DepthToSpace
by Aron Virginas-Tar
· 4 years, 10 months ago
3fb7e10
IVGCVSW-3623 Implement NeonTensorHandle::Import
by David Monahan
· 4 years, 11 months ago
93667b1
Replace uses of non-standard C++:
by Rob Hughes
· 4 years, 10 months ago
8a1b218
Fix some minor issues around SpaceToDepth
by Aron Virginas-Tar
· 4 years, 10 months ago
dd6247f
IVGCVSW-3883 Add frontend for DepthToSpace layer
by Aron Virginas-Tar
· 4 years, 10 months ago
68c2c90
IVGCVSW-3723 Adding reference workload support for ArgMinMax
by Nikhil Raj
· 4 years, 10 months ago
0bd586c
CONSERV-3867 Fix typos in the Dynamic Backends readme file
by Matteo Martincigh
· 4 years, 10 months ago
92b9f87
IVGCVSW-3878 Add reference workload for SLICE
by Aron Virginas-Tar
· 4 years, 10 months ago
636ab40
IVGCVSW-3875 Add frontend for SLICE layer
by Aron Virginas-Tar
· 4 years, 10 months ago
4dc64a6
IVGCVSW-3694 Add ArgMinMax implementation for Ref
by Narumol Prangnawarat
· 4 years, 10 months ago
4f1e8e4
IVGCVSW-3687 Add INetworkProperties to LoadNetwork
by David Monahan
· 4 years, 10 months ago
0718ee9
IVGCVSW-3868 Add support of Int32 to Reshape layer
by Narumol Prangnawarat
· 4 years, 10 months ago
d9f7c8b
IVGCVSW-3858 Fix RefTensorHandleTests on Raspberry Pi
by Aron Virginas-Tar
· 4 years, 10 months ago
46ff1ca
IVGCVSW-3854 Fix QuantizedLstmEndToEndTest on Raspberry Pi
by Aron Virginas-Tar
· 4 years, 10 months ago
6095ba5
IVGCVSW-3660 Add SQRT unit tests for Neon and CL backends
by Sadik Armagan
· 4 years, 10 months ago
019c4b1
In CopyTensorContentsGeneric coalesce inner dimensions where possible
by Matthew Bentham
· 4 years, 10 months ago
efdbca6
Rename variables in CopyTensorContents to assume NHWC
by Matthew Bentham
· 4 years, 10 months ago
9bff144
IVGCVSW-3857 Add Reference FP16 workload support to remaining layers
by Matthew Jackson
· 4 years, 10 months ago
39f44af
Fix CL workload creation methods not using MakeWorkload
by Aron Virginas-Tar
· 4 years, 10 months ago
c81a300
IVGCVSW-3820 Remove backendsCommon/WorkloadDataFwd.hpp
by Aron Virginas-Tar
· 4 years, 10 months ago
b6482f3
IVGCVSW-3659 Add Float16 CLLayerTests for Abs
by Kevin May
· 4 years, 10 months ago
252df3a
IVGCVSW-3845 Add Reference FP16 support for required layers
by Matthew Jackson
· 4 years, 10 months ago
1a763dd
IVGCVSW-3829 Add CL workload for RSQRT
by Aron Virginas-Tar
· 4 years, 10 months ago
0dd3b43
IVGCVSW-3830 Add NEON workload for RSQRT
by Aron Virginas-Tar
· 4 years, 10 months ago
Next »