m4rs-mt/ILGPU

Issues

• [QUESTION]: Kernel runs much slower on NVIDIA GPU than on Intel onboard GPU. Any ideas?

  #1286 opened 2 months ago by AmosEgel
  0

• [BUG]: cublasIsamax_v2

  #1269 opened 3 months ago by Ruberik
  0

• [QUESTION]: <title>How can I restore the program after a cuda kernel error?

  #1268 opened 3 months ago by delverOne25
  0

• [QUESTION]: Random number generator yields unexpected results for larger number of threads

  #1250 opened 4 months ago by AmosEgel
  3

• [BUG]: Radix sort - too many resources requested for launch

  #1263 opened 4 months ago by dellamonica
  0

• [FEATURE REQUEST]: Improve check-required workflow

  #1248 opened 5 months ago by pavlovic-ivan
  7

• [BUG]: What is the kernel compilation error?

  #1257 opened 4 months ago by delverOne25
  2

• [QUESTION]: Help/Orientation/Documentation to use ILGPU.Algorithms

  #1219 opened 4 months ago by poldap
  4

• [QUESTION]: Cannot find reason for "internal compiler error"

  #1251 opened 5 months ago by AmosEgel
  4

• [QUESTION]: How to resolve the calculation accuracy error between CPU and GPU.

  #1246 opened 5 months ago by qian-o
  0

• [BUG]: Variable naming

  #1240 opened 6 months ago by laurentchougrani
  1

• XMath.Exp : An internal compiler error has been detected

  #1234 opened 6 months ago by ShagufthaT
  4

• A Tensor Library

  #1107 opened a year ago by 12345swordy
  7

• Side by side comparison with CUDA and OpenCL

  #1229 opened 6 months ago by epsi1on
  0

• [POTENTIAL BUG]: CopyToCpu is using refs in unsafe way but there is no indication of that.

  #1209 opened 7 months ago by En3Tho
  3

• [BUG]: NET v8.0.5 SDK has broken CI pipeline

  #1223 opened 6 months ago by MoFtZ
  0

• [BUG]: `IRContext.Import(Method)` does not correctly duplicate the full IR graph

  #1222 opened 6 months ago by IsaMorphic
  2

• [BUG]: Unit tests failing on GitHub runner with MacOS 14

  #1213 opened 7 months ago by MoFtZ
  2

• [BUG] Cuda 12 SDK not supported with ILGPU 1.5.X

  #1194 opened 7 months ago by m4rs-mt
  2

• Cuda support not working on WSL2

  #1008 opened 7 months ago by Juff-Ma
  6

• Passing Int128 as kernel parameter is not working

  #1145 opened 7 months ago by MoFtZ
  3

• Iteration of value with loops on GPU slows down significantly

  #1137 opened a year ago by p66114129
  5

• [QUESTION]: Exception in Accelerator.Synchronize on CUDA

  #1179 opened 8 months ago by harrison314
  2

• Higher precision float (decimal) support?

  #1143 opened a year ago by chrisaliotta
  2

• OpenCL.CLException

  #1169 opened 9 months ago by fcogneaux
  2

• System.BadImageFormatException in System.Reflection.Metadata.dll

  #1155 opened 9 months ago by DorloBorlo
  4

• Feature request: cudaStreamWaitEvent

  #1139 opened a year ago by Ruberik
  7

• Add a CPU-GPU-Shared MemoryBuffer for systems that support it

  #1130 opened a year ago by RationalFragile
  2

• `NullReferenceException` when passing empty `ArrayView`s to OpenCL kernel

  #1121 opened a year ago by computablee
  1

• Better error messages when kernel program failed to run.

  #1124 opened a year ago by 12345swordy
  1

• Is it possible to use a stored dataset on GPU again and again with throwing extra data to GPU, and even change the value of the established dataset?

  #1127 opened a year ago by p66114129
  1

• Sample of "AlgorithmsRadixSort" failed on OpenCL device

  #1116 opened a year ago by GeoBIM2020
  4

• XMath.Pow() only work on CPU

  #1122 opened a year ago by wzhou-grid
  3

• VelocityDevice and MaxGridSize

  #1115 opened a year ago by m0bygit
  3

• Are vector data types supported?

  #1101 opened a year ago by yblainm
  3

• Intel GPUs ,float64 type is not supported on this device

  #1089 opened a year ago by sunxiaotianmg
  5

• System.AccessViolationException when adding useless if statement in kernel

  #1076 opened a year ago by GijsVanoppen
  8

• Compilation fails if there are more than two loops,why ?

  #1075 opened a year ago by sunxiaotianmg
  28

• Debug.Assert is not take effect on opencl

  #1049 opened a year ago by tianmafly
  4

• CUDA tests are broken on .NET 7.0.400

  #1047 opened a year ago by jgiannuzzi
  1

• RNG<XorShift64Star> corrupts data in ArrayView

  #1030 opened a year ago by uler3161
  4

• ArrayView.Cast should support unaligned byte offsets

  #1018 opened a year ago by TriceHelix
  3

• Question about hardware memory alignments

  #1016 opened a year ago by TriceHelix
  3

• Triton like optimisations?

  #1012 opened a year ago by fuadAbdallah
  3

• Support for OpenCL 1.2

  #1013 opened a year ago by queequac
  2

• Can CuFFT or CuFFTW be used internally in the kernel?

  #992 opened 2 years ago by xxl-cc
  5

• Tensor Cores

  #996 opened 2 years ago by lostmsu
  1

• Integration with current app

  #990 opened 2 years ago by ilkerccom
  2

• Access violation exception caused by the OpenCL module, while using default context builder.

  #983 opened 2 years ago by wberdowski
  2

• Is there a similar function to thrust::fill(stream, arrayStart, arrayEnd, -1)

  #987 opened 2 years ago by Liudeke
  2