Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
b9070a42a44ec1a0102e2f0b04523d2e96392903
« Previous
37d080f
COMPMID-2378: Sanitize GEMM configuration for NEON
by Georgios Pinitas
· 5 years ago
11de30d
COMPMID-2193: Improve permute documentation.
by Pablo Tello
· 5 years ago
95f9361
COMPMID-2185: Implement direct convolution 9x9 (NHWC) on NEON
by Gian Marco Iodice
· 5 years ago
53860dd
COMPMID-2432 Fix defects reported by Coverity
by Michalis Spyrou
· 5 years ago
7bb56c6
COMPMID-2409: Add QSYMM16 support for PixelWiseMultiplication for NEON
by Manuel Bottini
· 5 years ago
6b9f388
COMPMID-2336: Fix enable tuning of kernels targeted in COMPUTE-10611
by Michele Di Giorgio
· 5 years ago
4646d2e
COMPMID-2072: Use a constexpr for num_elems_processed_per_iteration where possible
by Michele Di Giorgio
· 5 years ago
cbe3905
COMPMID-2433: (Nightly) Bug in CLDequantizationLayer
by Michele Di Giorgio
· 5 years ago
a748436
COMPMID-2336 Fix FuseBatchNormalizationFixture
by Michalis Spyrou
· 5 years ago
c9573f3
COMPMID-2407: Add (logistic and tanh) activation support for QSYMM16 for NEON
by giuros01
· 5 years ago
5a1320b
COMPMID-2429: Unexpected exception in destructor
by Georgios Pinitas
· 5 years ago
7b735dc
COMPMID-2427: Remove structurally dead code
by Georgios Pinitas
· 5 years ago
3262042
COMPMID-2426: Logical dead code fix
by Georgios Pinitas
· 5 years ago
338595b
COMPMID-2234 : Add support for axis 3 in NE/CLConcatenateLayer
by Vidhya Sudhan Loganathan
· 5 years ago
7026b30
COMPMID-1979: Fuse Activation Function in CLGEMM - part 1
by Gian Marco Iodice
· 5 years ago
49f8349
COMPMID-2428: Missing break statement.
by Georgios Pinitas
· 5 years ago
96aa6b1
COMPMID-2431: Add a comment to max_offset in CLDepthwiseConvolutionLayer3x3NHWCKernel
by Gian Marco Iodice
· 5 years ago
fffbdbc
COMPUTE-10611: CL: Set config_id to enabling LWS tuning
by Gary Antcliffe
· 5 years ago
d8a468f
COMPMID-2413: Add QSYMM16 support for PixelWiseMultiplication for CL
by Michele Di Giorgio
· 5 years ago
1109176
COMPMID-2245: Extend NEFuseBatchNormalization to support DepthwiseConvolution weights
by Manuel Bottini
· 5 years ago
26dcbc7
COMPMID-2158 Add SRGAN shapes in ConvolutionLayer heurists to dispatch direct convolution
by Michalis Spyrou
· 5 years ago
bc415af
COMPMID-2406: Create a new GEMMLowpQuantizeDownInt32ToInt16ScaleKernel for NEON
by Gian Marco Iodice
· 5 years ago
e99196c
COMPMID-2391: Created optical flow example
by Pablo Tello
· 5 years ago
6997fc9
COMPMID-2412: Add QSYMM16 support for ElementwiseAddition for CL
by Michele Di Giorgio
· 5 years ago
944170e
COMPMID-2172: Fuse bias addition with CLGEMMMatrixMultiplyNativeKernel
by Gian Marco Iodice
· 5 years ago
65383e2
COMPMID-2336: Fix Nightly bug NEArithmeticAddition
by Manuel Bottini
· 5 years ago
3d13af8
COMPMID-2235: Extend type support for CL/NEON DequantizationLayer.
by Georgios Pinitas
· 5 years ago
db09b37
COMPMID-2392: Add documentation for import_memory interface
by Georgios Pinitas
· 5 years ago
3689fcd
COMPMID-2408: Add QSYMM16 support for ElementwiseAddition for NEON
by Manuel Bottini
· 5 years ago
a28aebc
COMPMID-2383: DepthwiseConv use output qinfo
by Pablo Tello
· 5 years ago
e16c890
COMPMID-2053: Fuse bias addition with CLGEMMMatrixMultiplyReshapedKernel
by Gian Marco Iodice
· 5 years ago
0cbfda6
COMPMID-2343: Add layer normalization support in NELSTMLayer
by Michele Di Giorgio
· 5 years ago
75bde5e
COMPMID-2336: Account for padding in NEIm2ColKernel for NHWC.
by Georgios Pinitas
· 5 years ago
51403b5
COMPMID-2336: Fix argument type for epsilon in CLL2NormalizeLayer.
by Georgios Pinitas
· 5 years ago
9175392
COMPMID-2387: Add support for NEMeanStdDevNormalizationLayer
by Michele Di Giorgio
· 5 years ago
e71eb6f
COMPMID-2079: Print positional argument help
by Georgios Pinitas
· 5 years ago
705fd3d
COMPMID-2401: Fix CLGemmLowp macro expansion on no-dot platforms
by Georgios Pinitas
· 5 years ago
4509173
COMPMID-2184: Implement direct convolution 9x9 (NHWC) on OpenCL
by Michalis Spyrou
· 5 years ago
2b52add
COMPMID-2405: Add lws_hint to CLGEMMLowpMatrixAReductionKernel
by Gian Marco Iodice
· 5 years ago
2732cca
COMPMID-2244: Extend CLFuseBatchNormalization to support DepthwiseConvolution weights
by Manuel Bottini
· 5 years ago
b3a0a60
COMPMID-2336: Fix armv8.2-a build on Android
by Michele Di Giorgio
· 5 years ago
39438b4
COMPMID-2342: Add layer normalization support in CLLSTMLayer
by Michele Di Giorgio
· 5 years ago
c86633e
COMPMID-2336: Remove unused variable in PRelu
by Michalis Spyrou
· 5 years ago
5201654
COMPMID-2336: Enable implicit fallthrough warnings
by Michalis Spyrou
· 5 years ago
82d9dd1
COMPMID-2380: Create utility functions for is_one and is_zero with float
by Gian Marco Iodice
· 5 years ago
62404a5
COMPMID-2376: (Nightly) NEON ArgMinMax QASYMM8
by Manuel Bottini
· 5 years ago
5b48ad7
COMPMID-2386: Add support for CLMeanStdNormalizationLayer
by Michele Di Giorgio
· 5 years ago
761c8d0
COMPMID-2398: Add test for CLFuseBatchNormalizationLayer
by Gian Marco Iodice
· 5 years ago
d513436
COMPMID-2321: PRELU support in NEActivationLayer
by giuros01
· 5 years ago
e751062
COMPMID-2094: Implement CLGEMMLowpNative
by Gian Marco Iodice
· 5 years ago
e6bcb5b
COMPMID-2397: 64bit bare metal build failure
by Michalis Spyrou
· 5 years ago
151fa87
COMPMID-2393: Fix QASYMM8 activation failures.
by Georgios Pinitas
· 5 years ago
e4cad15
COMPMID-2195: DepthwiseConv allow padding > 1 (top/bottom)
by Pablo Tello
· 5 years ago
6260e19
COMPMID-2394: (Nightly) Clang-tidy errors
by Michalis Spyrou
· 5 years ago
d69b3b2
COMPMID-2238: Implement SPACE_TO_DEPTH for CL
by Michalis Spyrou
· 5 years ago
fad1838
COMPMID-2336: Fix warnings present in latest gcc
by Georgios Pinitas
· 5 years ago
775c7f5
COMPMID-2336: Fix armv7a build on linux
by Michalis Spyrou
· 5 years ago
18574c1
COMPMID-2336: Fix clang-tidy issues
by Michalis Spyrou
· 5 years ago
4b3fba1
COMPMID-2372: Add support for QASYMM8 for Tanh
by Georgios Pinitas
· 5 years ago
c625acd
COMPMID-2385: Fix CLGEMM
by Gian Marco Iodice
· 5 years ago
b0f342e
COMPMID-2171: Fuse bias addition with CLGEMMMatrixMultiplyReshapedOnlyRHSKernel
by Georgios Pinitas
· 5 years ago
bbac660
COMPMID-2366: (Nightly) Failure in CLGEMMLowp
by Georgios Pinitas
· 5 years ago
4c5469b
COMPMID-2225: Add interface support for new quantized data types.
by Georgios Pinitas
· 5 years ago
43a129e
COMPMID-2379: Use the macros available in gemm_helpers.h in GEMMLowp OpenCL kernels
by Gian Marco Iodice
· 5 years ago
d7dd15c
COMPMID-2218: 19.05 Release notes
by Michalis Spyrou
· 5 years ago
57aa98e
COMPMID-2377: (Nightly) NEON SpaceToDepthLayer errors
by Michalis Spyrou
· 5 years ago
db18a6f
COMPMID-2373: Remove unused gemmlowp opencl kernels
by Gian Marco Iodice
· 5 years ago
5b7d537
COMPMID-2237 Implement SPACE_TO_DEPTH for NEON
by Manuel Bottini
· 5 years ago
088d7b4
COMPMID-2059: (3RDPARTY_UPDATE) Add import memory testing.
by Georgios Pinitas
· 5 years ago
649962c
COMPMID-2239 Implement DEPTH_TO_SPACE for CL
by Michalis Spyrou
· 5 years ago
97b2bb1
COMPMID-2336: Reduce large and medium shapes
by Michalis Spyrou
· 5 years ago
c2a4716
COMPMID-2216: Update Readme
by Michalis Spyrou
· 5 years ago
6a4d542
COMPMID-2159 Implement Round for CL
by Usama Arif
· 5 years ago
0a5a57a
COMPMID-2160: Implement Round for NEON
by Usama Arif
· 5 years ago
43c1bf8
COMPMID-2336: Add clang-tidy checks in assembly subfolder
by Michalis Spyrou
· 5 years ago
c5c750d
COMPMID-2252: Saturate when converting from S32 to U8 IN NEDepthConvertLayerKernel
by Usama Arif
· 5 years ago
22f917c
COMPMID-2240 Implement DEPTH_TO_SPACE for NEON
by Michalis Spyrou
· 5 years ago
1e6e1b8
COMPMID-2322: PRELU support in CLActivationLayer
by giuros01
· 5 years ago
048b0f3
COMPMID-2278: Implement REDUCE_MAX operator for CL.
by Usama Arif
· 5 years ago
9e631c2
COMPMID-2252 NECast.
by Usama Arif
· 5 years ago
dd0bf48
COMPMID-2336: Initialize zerobuf arrays in gemm transform kernels.
by Georgios Pinitas
· 5 years ago
da2cbe1
COMPMID-2336 Remove redundant tests in Winograd
by Michalis Spyrou
· 5 years ago
28f0dd9
COMPMID-2279: Implement REDUCE_MAX operator for NEON
by Usama Arif
· 5 years ago
a4a08ad
COMPMID-2280: Implement REDUCE_MIN operator for NEON
by Usama Arif
· 5 years ago
b289050
COMPMID-2281: Implement REDUCE_MIN operator for CL
by Usama Arif
· 5 years ago
725b173
COMPMID-2214: Remove std::vector<std::unique_ptr<>> where possible.
by Georgios Pinitas
· 5 years ago
b8d5b95
COMPMID-2166: Add tests for importing memory mapped files.
by Georgios Pinitas
· 5 years ago
ac33d7e
COMPMID-2264: Implement LOG operator for CL
by Usama Arif
· 5 years ago
1f103d3
Optimizes stride 2 NEDirectConvolution
by alankelly
· 5 years ago
09f2497
COMPMID-2109: Remove CL/NE Width/Depth ConcatenateLayer functions.
by Georgios Pinitas
· 5 years ago
f24411f
COMPMID-2255: Implement ABS operator for CL
by giuros01
· 5 years ago
2ef70cf
COMPMID-2336: (DATA_UPDATE) Update Mobilenet v1 data
by Isabella Gottardi
· 5 years ago
8baaa45
COMPMID-2336: Replace Mobilenet v1 graph example quantization info with values from tflite hosted model
by Isabella Gottardi
· 5 years ago
5fc07aa
COMPMID-2338: Remove CLGEMMInterleave4x4 and CLGEMMTranspose1xW
by Gian Marco Iodice
· 5 years ago
b9626ab
COMPMID-2243 ArgMinMaxLayer: support new datatypes
by Michalis Spyrou
· 5 years ago
0af4418
COMPMID-2282: Implement SIN operator for CL
by Michalis Spyrou
· 5 years ago
3db1ba9
COMPMID-2362: Add Quantization Layer to the graph API
by Isabella Gottardi
· 5 years ago
0eb16cf
Puts duplicate code into a function in NEBox3x3Kernel
by Alan Kelly
· 5 years ago
efcefea
Optimizes NEBox3x3FP16Kernel by removing unnecessary int to float conversions
by Alan Kelly
· 5 years ago
a400334
Optimizes NEBox3x3Kernel by replacing floating point computations with fixed point
by Alan Kelly
· 5 years ago
Next »