All Versions
10
Latest Version
Avg Release Cycle
39 days
Latest Release
659 days ago

Changelog History

  • v1.2.10616 Changes

    September 05, 2019

    ๐Ÿ›  fix #85
    ๐Ÿ‘ extended support for NPP

  • v1.2.10607 Changes

    August 29, 2019
    • ๐Ÿ‘ NPP partial support
    • ๐Ÿ›  minor bug fixes
  • v1.2.10484 Changes

    May 16, 2019
    • CUDA 10.1
    • Visual 2019
    • more generic functions
    • ๐Ÿ› bug fixes
    • ๐Ÿ‘ clang 8 (better AVX512 support)
  • v1.2.10341 Changes

    February 21, 2019

    ๐Ÿ†• New in this release :

    • [experimental] generic functions
    • [experimental] cooperative_groups (no multi device sync)
    • [CUDA only] pass virtual function as argument (ldvirtftn opcode)
    • [CUDA only] complete support of is/as keywords (requires type conversion support in hybridizer options)
    • ๐Ÿ“š documentation website
    • โž• add SingleStaticAssignment attribute - for types which must be assigned immediately after declaration, such as thread_block.
    • more options for script version of hybridizer (relocatable device code, additional libraries for jitter, intrinsics, etc)

    ๐Ÿ› Bug fixes:

    • ๐Ÿ›  fix atomicExpr C# implementation
    • ICustomMarshaller didn't marshal memory back to host
    • removal of hybdelegate, replaced by hybaction and hybfunc everywhere
    • static methods of generic types can be marshalled
  • v1.2.10271 Changes

    January 11, 2019

    ๐Ÿ›  Minor release -- mostly bugfixes.

    • ๐Ÿ‘ better cufft support
    • ๐Ÿ›  multiple bugfixes about delegates and marshalling
    • ๐Ÿ›  bugfix in the windows service (renew license was hanging forever for some unknown reason)
    • ๐Ÿšš move to c++14 as default standard (required because of "auto return type" feature, which we use for delegates)

    ๐Ÿ›  There is a bug (#71) in the CUDA 10.0 samples. It's now fixed in the master branch.

  • v1.2.10227 Changes

    December 20, 2018
    • ๐Ÿ‘ Func<> improvements : support of ldvirtftn : we can now pass a virtual function as parameter
    • AtomicExpr<> : invoke any Func<T, T, T> where T is int/long/float/double
      Example : AtomicExpr.apply(ref x, y, (u, v) => Math.Max(u, v))
    • Generic Resident array for value types.
    • ๐Ÿ“œ cusparse and curand for cuda 9.1, 9.2 and 10.0
    • value types constructors (they must be decorated with [Kernel])
    • ๐Ÿ‘ builtin support for double.MinValue/MaxValue/Epsilon and NegativeZero
    • initonly and literal static fields are automatically [HybConstant]
    • โš  warnings!
  • v1.2.10129 Changes

    November 21, 2018

    ๐Ÿ†• New features:

    • ๐Ÿ‘Œ Support of Func<> (up to four generic arguments)
    • ๐Ÿ‘Œ Support of passing static functions, or Func<> as argument.
    • ๐Ÿ‘ Basic support of as and is keywords
    • ๐Ÿง Linux improvements
    • hybridizer-cuda can work in any directory

    ๐Ÿ› Bug fixes:
    #64 and #63

    ๐Ÿ”Š MSI installer logs errors and exceptions into C:\Program Files\Altimesh\Hybridizer Essentials\

  • v1.2.10108 Changes

    November 16, 2018

    ๐Ÿ†• New features:

    • ๐Ÿ‘Œ Support of Func<,,> (up to four generic arguments)
    • ๐Ÿ‘Œ Support of passing static functions as argument.
    • ๐Ÿง Linux improvements
    • hybridizer-cuda can work in any directory

    An attempt fo fix #64 and #63

    ๐Ÿ”Š MSI installer logs errors and exceptions into C:\Program Files\Altimesh\Hybridizer Essentials\

  • v1.2.10021 Changes

    October 30, 2018

    ๐Ÿ‘ CUDA 10 basic support :
    no cudaGraph_t
    ๐Ÿ”€ no grid-wide synchronization

    ๐Ÿ‘ better error reporting

    ๐Ÿ‘ more early exit on unsupported code paths.

    ๐Ÿ›  many bug fixes about generic code

    ๐Ÿ› bug fixes about Func<>

  • v1.1.9833 Changes

    September 17, 2018
    • ๐Ÿ‘ AVX/AVX2/AVX512 support!

    ๐Ÿš€ We introduced support of AVX* instruction sets for Intel/AMD CPUs. You can keep the same C# code and target your CPU instead of your NVIDIA GPU. All the code and binaries are deployed, but you'll need a special license to use them. For now, those license are reserved to special customers. You can read more about that in our blog post. This is a very large feature, so it's still in beta with restricted access.

    Commercial licenses
    You can purchase commercial licenses from our website

    ๐Ÿ’ป Command line tool

    ๐Ÿง Our command line tool has been massively improved. It's been renamed hybcc.exe on windows, and just hybridizer on linux. It now supports:

    • project files : hybridizer MyProj.csproj -run
    • all target flavors : hybridizer Main.cs -flavor [CUDA]/AVX/AVX2/AVX512 -run
    • openmp for CPU targets : hybridizer Main.cs -flavor AVX -fopenmp -run
    • verbose mode

    • Notebooks

    ๐Ÿ‘€ We added new notebooks and completed existing. See them in our github!

    • Minor improvements
      • fix license query in Visual Studio : #55
      • move files around in the installer to get a cleaner installation.
      • completed cuda types (cudaError_t)
      • a few more bug fixes.