Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
70d33bdfd36e1b44b0573189dca67ed7c63dd59e
« Previous
b8fc60f
COMPMID-1086: Optimizing GCGEMM - Add helpers to get target GPU information
by Michele Di Giorgio
· 6 years ago
62385bc
COMPMID-948: Add validation to CLL2NormalizeLayer
by John Richardson
· 6 years ago
657bdb3
COMPMID-1050 CL/NEON: Create a function to convert the 2D weights of FC layer from NHWC to NCHW and viceversa
by Giorgio Arena
· 6 years ago
3d1489d
COMPMID-605: Transition buffer memory manager
by Georgios Pinitas
· 6 years ago
54d6fae
COMPMID-959: Remove invalid switch log info on default method.
by Georgios Pinitas
· 6 years ago
750641d
COMPMID-1052 - Rework validate method in CLGEMM
by Gian Marco Iodice
· 6 years ago
aa3240d
COMPMID-959: Fixed Clang-tidy error
by Anthony Barbier
· 6 years ago
fa955be
COMPMID-1135 Fix CLGEMMDilatedConvolution mismatch
by Giorgio Arena
· 6 years ago
ab65e48
COMPMID-761: Add CL/NEON MeanStdDev benchmark tests
by John Richardson
· 6 years ago
e250389
COMPMID-810 Add NHWC data format support for NEON convolution
by Michalis Spyrou
· 6 years ago
79ffade
COMPMID-1112: Enabled multithreading transforms in Winograd.
by Pablo Tello
· 6 years ago
7f4a819
COMPMID-597: Port HOGMultiDetection to new framework
by John Richardson
· 7 years ago
c13021e
COMPMID-1109 - Enabling Winograd in the graph when possible
by Gian Marco Iodice
· 6 years ago
e29e0d4
COMPMID-959: Add missing header in Workload.h
by Georgios Pinitas
· 6 years ago
28a8493
COMPMID-1131: Fix SIGBUS error
by Georgios Pinitas
· 6 years ago
71ac9c0
COMPMID-1134: Fixing the Window reconstruction in gemm_native
by Anthony Barbier
· 6 years ago
5c2fb3f
COMPMID-997: Add support for node's name in GraphAPI.
by Georgios Pinitas
· 6 years ago
cac13b1
COMPMID-1097: Port mobilenet to NHWC
by Georgios Pinitas
· 6 years ago
ad0c738
COMPMID-1068 Create validate method to CLDepthWiseConvolution
by Giorgio Arena
· 6 years ago
1ed442a
COMPMID-1046 - Enabling Winograd VGG19 to use Winograd on NEON and OpenCL
by Gian Marco Iodice
· 6 years ago
d8cde85
COMPMID-959: Assembly kernel marks weights as unused when pretranspose
by Georgios Pinitas
· 6 years ago
bb36a8e
COMPMID-922 - CLGEMM FP16 optimizations - part2
by Gian Marco Iodice
· 6 years ago
4dcb583
COMPMID-1122: Store the cl_context only in one place
by Anthony Barbier
· 6 years ago
d24af8a
COMPMID-1125: Add support for FP16 in CLDepthwiseConvolution
by Michele Di Giorgio
· 6 years ago
932b561
COMPMID-959: Perform pretranspose if allowed on NEON assembly
by Georgios Pinitas
· 6 years ago
563494c
COMPMID-1084 Rework the way validation is performed for NHWC data layout
by Giorgio Arena
· 6 years ago
b7f5d17
COMPMID-1115: Valgrind: asserts triggered in NEPoolingLayerKernel
by Georgios Pinitas
· 6 years ago
4497e81
COMPMID-1123 - Enabling Winograd 2x2,3x3 and Winograd 4x4,3x3 without fast_math
by Gian Marco Iodice
· 6 years ago
e043767
COMPMID-920: Introduce prepare() stage
by Georgios Pinitas
· 6 years ago
019634f
COMPMID-1110 Add QASYMM8 to supported types for NE/CLActivationLayer
by Michalis Spyrou
· 6 years ago
654c644
COMPMID-761: Add CL/NEON IntegralImage benchmark tests
by John Richardson
· 6 years ago
535fedd
COMPMID-1117: TransposeAccessWindow leads to high padding
by Georgios Pinitas
· 6 years ago
6cf188c
COMPMID-1116 - Increase the tolerance for CLWinogradConvolutionLayer
by Gian Marco Iodice
· 6 years ago
7217563
COMPMID-1107: Add support for ChannelShuffle in CL
by Michele Di Giorgio
· 6 years ago
c0f5443
COMPMID-808 Add NHWC data format support for NEON direct convolution
by Giorgio Arena
· 6 years ago
3c520c5
COMPMID-1089 CLPoolingLayer fix padding and add output shape computation to ShapeCalculator
by Giorgio Arena
· 6 years ago
6c42127
COMPMID-1105: Fix mismatches conv layer when using NativeGemm with multiple threads
by Pablo Tello
· 6 years ago
7f60f7e
COMPMID-761: Add CL/NEON Median3x3 benchmark tests
by John Richardson
· 6 years ago
7657224
COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution
by Giorgio Arena
· 6 years ago
e74b201
COMPMID-805 Add NHWC data format support for CL pooling
by Michalis Spyrou
· 6 years ago
2213d4b
COMPMID-1096 - Add fast_math flag to CLConvolutionLayer
by Gian Marco Iodice
· 6 years ago
ebf14a5
COMPMID-761: Add CL/NEON Phase benchmark tests
by John Richardson
· 6 years ago
ae70072
COMPMID-959: Fail when graph is already registered
by Georgios Pinitas
· 6 years ago
edf357c
COMPMID-1085 : runtime_error thrown by QASYMM8 CLGEMMConvolutionLayer::validate
by Vidhya Sudhan Loganathan
· 6 years ago
b3b1e0b
COMPMID-1010: Remove RSH profiler header
by Georgios Pinitas
· 6 years ago
57dac84
COMPMID-806 Add NHWC data format support format for NEON pooling
by Michalis Spyrou
· 6 years ago
0ef7e67
COMPMID-761: Add CL/NEON HOGDescriptor benchmark tests
by John Richardson
· 6 years ago
5e20753
COMPMID-1092: Fix CL GEMMConvolutionLayer FP32 mismatches
by Georgios Pinitas
· 6 years ago
6b06953
COMPMID-1087: Fix CLHOGDetector failure.
by John Richardson
· 6 years ago
9fb1159
COMPMID-1074: Rename WinograLayer.cpp to WinogradConvolutionLayer.cpp
by Georgios Pinitas
· 6 years ago
43f6afe
COMPMID-1079: Removed tests asking for too much memory.
by Pablo Tello
· 6 years ago
184a95c
COMPMID-1077 Fixed SVM memory tracking instrument
by Anthony Barbier
· 6 years ago
2b3129e
COMPMID-1041 NEON Winograd: update function to use GEMM function
by Michalis Spyrou
· 6 years ago
99d4095
COMPMID-1023: Import memory for OpenCL
by Georgios Pinitas
· 6 years ago
cda0c38
COMPMID-1080 - Fix CLFullyConnectedLayer validate() tests failing
by Gian Marco Iodice
· 6 years ago
e91abd7
COMPMID-959 : Disables HogDetector test on CL
by Georgios Pinitas
· 6 years ago
84ce1f9
COMPMID-718 : Winograd: add validate method and tests
by Vidhya Sudhan Loganathan
· 6 years ago
764b1af
COMPMID-1070: Rewrote im2col nhwc reference
by Pablo Tello
· 6 years ago
3ca9786
COMPMID-718 : Winograd: add validate method and tests
by Vidhya Sudhan Loganathan
· 6 years ago
bf3c662
COMPMID-803: Add NHWC data format support for CL batch normalisation
by Michele Di Giorgio
· 6 years ago
164b65d
COMPMID-1043: Rework GCGEMMMatrixMultiplyKernel interface and allow auto initialization of the tensors
by Michele Di Giorgio
· 6 years ago
0cbb927
COMPMID-804: Add NHWC data format support for NEON batch normalisation
by Michele Di Giorgio
· 6 years ago
82b5148
COMPMID-959: Sets memory manager to CLWinograd
by Georgios Pinitas
· 6 years ago
35aa6a3
COMPMID-1077 Add OpenCL Memory Usage instrument
by Anthony Barbier
· 6 years ago
9fb0cac
COMPMID-1081: Introduced test-wide instruments
by Anthony Barbier
· 6 years ago
fda901f
COMPMID-1078 Fix CL DepthwiseConvolutionLayer QASYMM8 failing validation
by Giorgio Arena
· 6 years ago
f485a10
COMPMID-802 Fix NEIm2Col NHWC
by Giorgio Arena
· 6 years ago
48c19f1
COMPMID-959 Refactor OpenCL interceptors to use lambda functions
by Anthony Barbier
· 6 years ago
b34690b
COMPMID-1012 : Add OpenCL benchmarks for Winograd
by Vidhya Sudhan Loganathan
· 6 years ago
d727e85
COMPMID-855: Get the library to work on non Mali GPUs
by Anthony Barbier
· 6 years ago
e52a300
COMPMID-1026 - Add support for 4x4 output tile in CLWinogradConvolutionLayer
by Gian Marco Iodice
· 6 years ago
dd03870
COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradOutputTransformKernel
by Giorgio Arena
· 6 years ago
bb54e4e
COMPMID-797 Integrate Mobilenet QASYMM8 with new graph.
by Giorgio Arena
· 6 years ago
4d33630
COMPMID-987: Make beta and gamma optional in BatchNormalization
by Michele Di Giorgio
· 6 years ago
1cd4149
COMPMID-577: Implement CL validation for GaussianPyramid
by Sanghoon Lee
· 6 years ago
c9c62c2
COMPMID-1056 - Optimizing CLGEMMMatrixMultiplyKernel refactoring the inner loop
by Gian Marco Iodice
· 6 years ago
3ab6804
COMPMID-761: Add CL/NEON Histogram benchmark tests
by John Richardson
· 6 years ago
7da55aa
COMPMID-959: Add accessors for the OpenCL program cache
by Anthony Barbier
· 6 years ago
fd68311
COMPMID-922 - CLGEMM FP16 optimizations - part1
by Gian Marco Iodice
· 6 years ago
dfca60b
COMPMID-811 Add NHWC data format support for CL depthwise convolution QASYMM8
by Giorgio Arena
· 7 years ago
fe5ef38
COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradInputTransformKernel
by Giorgio Arena
· 6 years ago
f0cefbf
COMPMID-959 - Fixing subtensor validation
by Gian Marco Iodice
· 6 years ago
41c482d
COMPMID-1042: Graph / Stream not working on x86
by Georgios Pinitas
· 6 years ago
ecb1c62
COMPMID-959: Fixed order of init/destruction of CLSymbols / CLKernelLibrary
by Anthony Barbier
· 6 years ago
56e8e86
COMPMID-1031: Use LWS hints for G51, G51BIG, G51LIT, and TNOX
by Sam Laynton
· 6 years ago
9fb2b66
COMPMID-761: Add CL/NEON EqualizeHistogram benchmark tests
by John Richardson
· 6 years ago
e7e96e0
COMPMID-1054 Update RSH's GEMM to add batch+multi support
by Michalis Spyrou
· 6 years ago
1ed1fc6
COMPMID-812 Add NHWC data format support for NEON depthwise convolution (optimized case).
by Giorgio Arena
· 6 years ago
9373c8b
COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradFilterTransformKernel
by Giorgio Arena
· 6 years ago
fc1d1e2
COMPMID-959: Add FP32 support to GLES GEMMConvolution
by Michele Di Giorgio
· 6 years ago
a72300a
COMPMID-1051 - Fix validate method in NEGEMMConvolutionLayer
by Gian Marco Iodice
· 6 years ago
95a3f55
COMPMID-959: Disabled winograd on Arm Cortex-A53 while we're working on a fix
by Anthony Barbier
· 6 years ago
5f0124d
COMPMID-959: Fixed clang-tidy formatting, made GLES builds fail for standalone=1
by Anthony Barbier
· 6 years ago
ae3c8ab
COMPMID-584: Add validation to channel_combine kernels
by Ioan-Cristian Szabo
· 7 years ago
156fcf3
COMPMID-802 Add NHWC data format support for NEON im2col.
by Giorgio Arena
· 6 years ago
8de9261
COMPMID-585: Port OpticalFlow to new validation
by John Richardson
· 6 years ago
2abb216
COMPMID-1045 - Fix shape_to_valid_region_gaussian_pyramid_half()
by Gian Marco Iodice
· 6 years ago
a1be5ba
COMPMID-959: Number of threads was overwritten in benchmark_graph tests
by Anthony Barbier
· 6 years ago
50b2254
COMPMID-959 Removed assert on cpuid because valgrind always passes '-1'
by Anthony Barbier
· 6 years ago
a1667fb
COMPMID-959 - Fix doxygem comment in CLGEMMConvolutionLayer
by Isabella Gottardi
· 6 years ago
Next »