C

Compute Library

Settings | Report Duplicate

1

I Use This!

Activity Not Available

Commits : Listings

Analyzed 12 months ago. based on code collected 12 months ago.

Commit Message	Contributor	Files Modified	Lines Added	Lines Removed	Code Location	Date
Nov 24, 2024 — Nov 24, 2025 Showing page 118 of 125 Search / Filter on:
COMPMID-477 - Optimized Direct Convolution 3x3 and 5x5 (f32) for Bifrost. Each work-item computes 4x3 output elements in case of 3x3 convolution and 4x2 in case of 5x5 convolution	Gian Marco Iodice	More...				about 9 years ago
COMPMID-479 Add GoogleNetInceptionV4 benchmarks	SiCong Li	More...				about 9 years ago
COMPMID-479 Restructure system tests datasets	SiCong Li	More...				about 9 years ago
COMPMID-477 - Optimized batched case in CLConvolutionLayer	Gian Marco Iodice	More...				about 9 years ago
COMPMID-417 - Fixed bug in CLCol2ImKernek related to the stride passed during the configuration	Gian Marco Iodice	More...				about 9 years ago
COMPMID-474 - Add support for QS8/QS16 DirectConvolution CL	mpekatsoula as Michalis Spyrou	More...				about 9 years ago
COMPMID-415: Update test documentation	Moritz Pflanzer	More...				about 9 years ago
COMPMID-417: Cleanup CL FullyConnectedLayer	Moritz Pflanzer	More...				about 9 years ago
COMPMID-417 - Added clFinish to CLSymbols	Gian Marco Iodice	More...				about 9 years ago
COMPMID-417 - Added method to set the Local Workgroup size hint	Gian Marco Iodice	More...				about 9 years ago
COMPMID-417 - Bug Fix WarpPerspective kernel	Isabella Gottardi	More...				about 9 years ago
COMPMID-345: Added support for 5x5 kernels in NEDirectConvolution	Pablo Tello	More...				about 9 years ago
COMPMID-417: Fix JSON printer	Moritz Pflanzer	More...				about 9 years ago
COMPMID-477 - Optimized CLNormalizationLayer CLPixelWiseMultiplication has been removed within the function	Gian Marco Iodice	More...				about 9 years ago
COMPMID-345: Optimization for NEFillBorder kernel.	Pablo Tello	More...				over 9 years ago
COMPMID-478 Implemnt CL direct convolution 5x5	steniu01	More...				over 9 years ago
COMPMID-415 Fixed JSON printer to output errors as an array of single lines instead of a multi-line string	Anthony Barbier	More...				over 9 years ago
COMPMID-345: Added benchmarking tests for profiling Neon Direct Convolution.	Pablo Tello	More...				over 9 years ago
COMPMID-415: Move FullyConnectedLayer to new validation	Moritz Pflanzer	More...				over 9 years ago
COMPMID-417: Cleanup NEON FullyConnectedLayer	Moritz Pflanzer	More...				over 9 years ago
COMPMID-476 L2 Normalization for CL	mpekatsoula as Michalis Spyrou	More...				over 9 years ago
COMPMID-417: Increase tolerance because of failures	Moritz Pflanzer	More...				over 9 years ago
COMPMID-415: Improve SimpleTensor and RawTensor	Moritz Pflanzer	More...				over 9 years ago
COMPMID-477 - Optimizing CLDirectConvolution 3x3 on OpenCL and added the auto configuration	Gian Marco Iodice	More...				over 9 years ago
COMPMID-417 - Fixed auto-config in NEConvolutionLayer and in CLConvolutionLayer	Gian Marco Iodice	More...				over 9 years ago
COMPMID-417: Fix invalid read in GEMM	Moritz Pflanzer	More...				over 9 years ago
COMPMID-363 Add Graph library support	Anthony Barbier	More...				over 9 years ago
COMPMID-415: Add autoconfigure to CLCol2ImKernel	Anthony Barbier	More...				over 9 years ago
COMPMID-415 Fixed bug in autoconfigure of NEPoolingLayerKernel	Anthony Barbier	More...				over 9 years ago
COMPMID-475 Enable more data format in the benchmark test	steniu01	More...				over 9 years ago

←
1
2
…
114
115
116
117
118
119
120
121
122
123
124
125
→