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 9 of 125 Search / Filter on:
Reintroduce implementation of NEConvolutionLayer::get_convolution_method	Michele Di Giorgio	More...				over 5 years ago
Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1	Gian Marco Iodice	More...				over 5 years ago
Fix A55 performance constant for fp16 hybrid gemm kernel	Georgios Pinitas	More...				over 5 years ago
Benchmark and set default LWS for GEMM, Direct convolution and Winograd	Giorgio Arena	More...				over 5 years ago
Fix cpu GEMM fp16 issue	Freddie Liardet	More...				over 5 years ago
Reduce binary footprint of CpuConvertFullyConnectedWeightsKernel	Michele Di Giorgio	More...				over 5 years ago
Create custom flags for enabling fp16 support	Georgios Pinitas	More...				over 5 years ago
Port CLConvolutionLayer	Sheri Zhang	More...				over 5 years ago
Remove generated kernels that overlap hand-written ones	Georgios Pinitas	More...				over 5 years ago
Port ClFullyConnected to new API	Georgios Pinitas	More...				over 5 years ago
Fix bare metal build issues	Freddie Liardet	More...				over 5 years ago
Update GEMM assembly performance parameters	Georgios Pinitas	More...				over 5 years ago
Fix memory lifetime issue	Georgios Pinitas	More...				over 5 years ago
Reorganize the kernels into nhwc, nchw and common folders - Adding the flags for NCHW and NHWC	Adnan AlSinan	More...				over 5 years ago
Dispatch Conv2d using the Direct method when necessary	Georgios Pinitas	More...				over 5 years ago
Add support for non-constant weights and biases in CpuFullyConnected	Michele Di Giorgio	More...				over 5 years ago
Add missing limits include	Freddie Liardet	More...				over 5 years ago
Fix allocation of prepare tensor on ClWinogradConv2d	Georgios Pinitas	More...				over 5 years ago
Avoid allocation of auxiliary memory in CpuGemmConvolution	Georgios Pinitas	More...				over 5 years ago
Pass fast math flag for correct GEMM3D validation support	Georgios Pinitas	More...				over 5 years ago
Fix formatting issue with blank profiler header	Freddie Liardet	More...				over 5 years ago
Fix NN driver build script for Android R	Michele Di Giorgio	More...				over 5 years ago
Fix bare metal build error	Freddie Liardet	More...				over 5 years ago
Remove printing Android version detected by the build system	Pablo Marquez Tello	More...				over 5 years ago
Expose fast_math mode for GEMM through BFloat16	Georgios Pinitas	More...				over 5 years ago
Fix vector_length identification mechanism for SVE	Georgios Pinitas	More...				over 5 years ago
Port NEConvolutionLayer	mpekatsoula as Michalis Spyrou	More...				over 5 years ago
Inject temporary tensors to pack in they don't exist in CpuSoftmax	Georgios Pinitas	More...				over 5 years ago
Fix oclgrind int overflow warning	Freddie Liardet	More...				over 5 years ago
Print the Android version detected by the build system	Pablo Marquez Tello	More...				over 5 years ago

←
1
2
…
5
6
7
8
9
10
11
12
13
…
124
125
→