brian-team/brian2cuda

Issues

• Why the volatile GPU utilization is so low? I run the same code respectively on the CPU(cpp_standalone) and GPU(brian2cuda), and i expect that it can run quickly by using brian2ccuda. However, it runs much slower... Can someone explain this?

  #313 opened 4 months ago by LiYuan-0709
  1

• Bypass nvidia-smi when using a Jetson platform

  #312 opened 4 months ago by NikVard
  6

• Support Windows

  #225 opened 3 years ago by denisalevi
  1

• Optimise brian2CUDA

  #309 opened a year ago by bdevans
  2

• Brian2Hears and Brian2CUDA

  #308 opened a year ago by slyyyle
  3

• Brian2Cuda Uninstalls Brian2 2.5.1 and Installs 2.4.2 Which Won't Import

  #307 opened a year ago by slyyyle
  3

• Recent Brian2 update PR broke benchmark scripts

  #304 opened 2 years ago by denisalevi
  1

• Circular eventspaces fail when source group runs on a different clock than synapses

  #222 opened 3 years ago by denisalevi
  0

• Spikes are lost when changing delays between `run` calls

  #302 opened 2 years ago by denisalevi
  3

• Fix memory leak when having multiple `run` calls

  #301 opened 2 years ago by denisalevi
  0

• Fix `ReferencError` in spatialneuron tests

  #296 opened 2 years ago by denisalevi
  3

• Refactor test suite scripts

  #295 opened 2 years ago by denisalevi
  0

• Optimize our `SpikeMonitor` for `Subgroups`

  #293 opened 2 years ago by denisalevi
  0

• Fix `SpikeMonitor` for `Subgroup`s

  #286 opened 2 years ago by denisalevi
  1

• Make sure default compile flags are used correctly and are well documented

  #239 opened 3 years ago by denisalevi
  0

• Investigate and document performance effects when working with `Subgroup`s

  #283 opened 2 years ago by denisalevi
  1

• Consider partitioning eventspaces when using `Subgroup`s

  #284 opened 2 years ago by denisalevi
  4

• Copy all eventspace counters to host efficiently at each time step

  #282 opened 2 years ago by denisalevi
  0

• Optimize `PopulationRateMonitor`

  #285 opened 2 years ago by denisalevi
  0

• Impelement brian2cuda preference file support

  #281 opened 2 years ago by denisalevi
  0

• Investigate if reducing registers by modifying code generation is possible

  #268 opened 2 years ago by denisalevi
  1

• Optimize `StateMonitor`

  #278 opened 2 years ago by denisalevi
  0

• Implement special case connectivity matrices with pre/post IDs for models that effect only pre/post variables

  #271 opened 2 years ago by denisalevi
  5

• Needs patch to run with Brian 2.4.2

  #276 opened 2 years ago by mstimberg
  2

• Check if storing the size of synapse groups is necessary?

  #275 opened 2 years ago by denisalevi
  1

• Refactor benchmarking scripts and update generated plots

  #274 opened 2 years ago by denisalevi
  0

• Compilation is failing with CUDA 11.4

  #224 opened 2 years ago by denisalevi
  6

• Call reset kernel only with as many threads as there are spiking neurons (not as there are neurons in total)

  #272 opened 2 years ago by denisalevi
  0

• Parallelize effect application in heterogeneous delay mode over additional CUDA blocks

  #269 opened 2 years ago by denisalevi
  1

• Reduce number of threads in push kernel for heterogeneous delays in bundle mode

  #270 opened 2 years ago by denisalevi
  0

• Report when models are using too many registers for full occupancy

  #267 opened 2 years ago by denisalevi
  0

• Block dimension calculation can lead to non-optimal occupancy

  #266 opened 2 years ago by denisalevi
  1

• Single precision mode is broken

  #234 opened 2 years ago by denisalevi
  3

• Fix remaining issues in single precision mode

  #264 opened 2 years ago by denisalevi
  0

• Check if single precision math functions are used correctly

  #263 opened 2 years ago by denisalevi
  0

• Single precision f-literal replacement fails for variables with double digit + dot in name

  #254 opened 3 years ago by denisalevi
  3

• Make inverted assertion tests single precision compatible

  #262 opened 2 years ago by denisalevi
  0

• [how to] changing Synapses Weights after run with cpp/cuda

  #261 opened 2 years ago by davideschiavone
  3

• Failing getting CUDA code

  #260 opened 2 years ago by davideschiavone
  2

• Implement better metric for automatically choosing the best GPU

  #255 opened 3 years ago by denisalevi
  0

• Support GSL integration

  #242 opened 3 years ago by denisalevi
  1

• Profiling failed on SCIoI GPU node

  #252 opened 3 years ago by denisalevi
  1

• Implement testst that make sure the compiler, CUDA and preferences are compatible

  #251 opened 3 years ago by denisalevi
  0

• Clean up and simplify thresholder template

  #250 opened 3 years ago by denisalevi
  0

• Decide on debug mode for CUDA Standalone

  #226 opened 3 years ago by denisalevi
  1

• Make single-precision version of `exprel` and `clip` typesafe

  #233 opened 3 years ago by denisalevi
  1

• Use `size_t` datatype instead of `int` for indices and sizes

  #230 opened 3 years ago by denisalevi
  0

• Verify that our checks for poisson function calls with scalar lambda are correct

  #228 opened 3 years ago by denisalevi
  0

• SpikeMonitor fails for multiple runs

  #221 opened 3 years ago by denisalevi
  1

• Call kernels with maximum the number of units instead of always multiples of 1024

  #220 opened 3 years ago by denisalevi
  0