Recherche avancée

Sur d’autres sites (5906)

• Analytics for the Internet of Things : collecting all your things’ data with Piwik to stay in control ?

  25 novembre 2015, par Matthieu Aubry — About

  At Piwik our mission is to create the leading free and open source analytics platform, and supporting global organisations and communities to keep full control over their data.

  Our broad mission started 8 years ago and we focused at first helping people to liberate their website analytics data, then liberate their mobile app analytics data. But it is clear that there is much more than Web + Mobile : data is everywhere and a lot more data is being generated by software, people and their activities, robots, sensors…

  I’d like to share an interesting article which highlights one of the growing trends of technology : the rise of the Internet Of Things : 6 Ways Analytics And The Internet Of Things Will Transform Business.

  Here is an extract :

  The tech industry is no stranger to change, but the data derived from the IoT is taking disruption to a new level.

  At IBM’s Insight conference last month, Bob Picciano, senior vice president of IBM Analytics, talked about the rise of the “cognitive business”, or an enterprise that engages with analytics to improve its customer relations, business processes, and decision-making capabilities.

  There are dueling predictions over how ubiquitous the Internet of Things will be, but most indicate that the marketplace will host between 50 and 75 billion connected objects by 2020, signaling novel challenges for hardware manufacturing and development. Software engineers, likewise, may need to completely revamp programs to better exploit the influx of data, while innovators need to wrestle with the changes wrought by analytics.

  IBM’s Insight event unfolded in light of this wave of disruption. The lineup of corporate presenters converged on the same message : Analytics is for everyone, and your viability in the marketplace depends on it.

  […]

  IBM’s Insight 2015 conference sounded off on the most important trends in data usage and management. It also served a wake-up call for developers, engineers, and tech leaders. As the Internet of Things alters the landscape of analytics, hardware design needs to change, software development requires novel approaches, and tech management must become more agile in order to realize data’s greatest benefits.

  So far there are 1 million websites using Piwik… but what if there could be 10 or 50 million things (sensors, devices) being measured by Piwik ?

  Together we will be creating the best open source and generic analytics platform, that is engineered to last, and designed to help humanity keep control and gain Freedom.

  We aim for Piwik to be the ideal platform to measure the Internet Of Things.

  We’re still at the beginning of this journey and it will take the best of all of us to get there.

  See you on the way !

  PS : if you’d like to get involved with Piwik, we would be glad to welcome you !

• arm : add ff_int32_to_float_fmul_array8_neon

  3 décembre 2015, par Janne Grunau

  arm : add ff_int32_to_float_fmul_array8_neon
  Quite a bit faster than int32_to_float_fmul_array8_c calling
  
  ff_int32_to_float_fmul_scalar_neon through FmtConvertContext.
  
  Number of cycles per int32_to_float_fmul_array8 call while decoding
  
  padded.dts on exynos5422 :
                 before  after   change
  
  cortex-a7 :     1270     951    -25%
  
  cortex-a15 :     434     285    -34%
  checkasm —bench cycle counts :     cortex-a15   cortex-a7
  
  int32_to_float_fmul_array8_c :      1730.4       4384.5
  
  int32_to_float_fmul_array8_neon_c :  571.5       1694.3
  
  int32_to_float_fmul_array8_neon :    374.0       1448.8
  Interesting are the differences between
  
  int32_to_float_fmul_array8_neon_c and int32_to_float_fmul_array8_neon.
  
  The former is current behaviour of calling
  
  ff_int32_to_float_fmul_scalar_neon repeatedly from the c function,
  
  The raw numbers differ since checkasm uses different lengths than the
  
  dca decoder.
  

  • [DBH] libavcodec/arm/fmtconvert_init_arm.c
  • [DBH] libavcodec/arm/fmtconvert_neon.S

• ffmpeg GPU use cuvid with hwdownload will never finished, Appeared only recently

  28 mai 2020, par tags bt

  ffmpeg :

  



  ffmpeg version N-97331-g10a68cc Copyright (c) 2000-2020 the FFmpeg developers
  built with gcc 7 (Ubuntu 7.3.0-16ubuntu3)
  configuration: --pkg-config-flags=--static --prefix=/usr/local/ffmpeg --bindir=/usr/local/ffmpeg/bin --extra-cflags='-I /usr/local/ffmpeg/include -I /usr/local/cuda/include/' --extra-ldflags='-L /usr/local/ffmpeg/lib -L /usr/local/cuda/lib64/' --extra-libs=-lpthread --enable-cuda --enable-cuda-nvcc --enable-cuvid --enable-libnpp --enable-gpl --enable-libass --enable-libfdk-aac --enable-vaapi --enable-libfreetype --enable-libmp3lame --enable-libopus --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libx264 --enable-libx265 --enable-nonfree --enable-libaom --enable-nvenc


  



  nvidia-msi

  



  +-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.82       Driver Version: 440.82       CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 1080    Off  | 00000000:02:00.0 Off |                  N/A |
|  0%   51C    P8    13W / 200W |     18MiB /  8119MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0     23224      C   ffmpeg                                         8MiB |
+-----------------------------------------------------------------------------+



  



  if i use this command :

  



  ffmpeg -re -threads 0 -loglevel debug -hwaccel cuvid -hwaccel_output_format cuda -i 1.mp4 -c:v h264_nvenc -c:a aac -ac 2 -b:a 128k -strict -2 -filter_complex "[0:v]scale_npp=1280:-2" ouzz2t.mp4


  



  it will very fast.

  



  but if i use this command :

  



  ffmpeg -re -threads 0 -loglevel debug -vsync 0 -hwaccel cuvid -hwaccel_output_format cuda -hwaccel_device intel -i 1.mp4 -c:v h264_nvenc -c:a aac -ac 2 -b:a 128k -strict -2 -filter_complex "[0:v]scale_npp=1280:-2:format=yuv420p[tmp],[tmp]hwdownload,format=yuv420" ouzz2t.mp4


  



  it will never finished, one 40MB mp4 will transcode 44 minutes and not finished.

  



  as you see

  



  +-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|    0     23224      C   ffmpeg                                         8MiB |
+-----------------------------------------------------------------------------+


  



  it will only use GPU memory 8mib.

  



  and top will show :
enter image description here

  



  delug log :

  



  [AVHWDeviceContext @ 0x561cfaef92c0] Loaded lib: libcuda.so.1
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuInit
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceGetCount
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceGet
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceGetAttribute
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceGetName
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceComputeCapability
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxCreate_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxSetLimit
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxPushCurrent_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxPopCurrent_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxDestroy_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemAlloc_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemAllocPitch_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemsetD8Async
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemFree_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemcpy2D_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMemcpy2DAsync_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGetErrorName
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGetErrorString
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuCtxGetDevice
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDevicePrimaryCtxRetain
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDevicePrimaryCtxRelease
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDevicePrimaryCtxSetFlags
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDevicePrimaryCtxGetState
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDevicePrimaryCtxReset
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuStreamCreate
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuStreamQuery
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuStreamSynchronize
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuStreamDestroy_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuStreamAddCallback
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuEventCreate
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuEventDestroy_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuEventSynchronize
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuEventQuery
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuEventRecord
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuLaunchKernel
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuModuleLoadData
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuModuleUnload
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuModuleGetFunction
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuTexObjectCreate
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuTexObjectDestroy
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGLGetDevices_v2
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGraphicsGLRegisterImage
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGraphicsUnregisterResource
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGraphicsMapResources
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGraphicsUnmapResources
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuGraphicsSubResourceGetMappedArray
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDeviceGetUuid
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuImportExternalMemory
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDestroyExternalMemory
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuExternalMemoryGetMappedBuffer
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuExternalMemoryGetMappedMipmappedArray
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMipmappedArrayGetLevel
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuMipmappedArrayDestroy
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuImportExternalSemaphore
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuDestroyExternalSemaphore
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuSignalExternalSemaphoresAsync
[AVHWDeviceContext @ 0x561cfaef92c0] Loaded sym: cuWaitExternalSemaphoresAsync



  



  Stop at Loaded sym : cuWaitExternalSemaphoresAsync, and ffmpeg will always 100% cpu and never finished.

  



  Appeared only recently, last week it work fine, but today it work worse.

  



  somebody know what happen to me ?