nvvm: FFI bindings to NVVM
The NVVM library compiles NVVM IR (a subset of LLVM IR) into PTX code which
can then be executed on NVIDIA GPUs. In contrast to the standard NVPTX target
built in to the LLVM toolchain, NVVM includes a set of proprietary
optimisations which are otherwise only available by compiling CUDA code with
the nvcc compiler.
The resulting PTX code can be loaded onto the GPU and executed using the
cuda package:
https://hackage.haskell.org/package/cuda
The NVVM library is a compiler component available a part of the CUDA toolkit:
https://developer.nvidia.com/cuda-toolkit
See the travis-ci.org build matrix for tested CUDA library versions.
[Skip to Readme]
Modules
[Index] [Quick Jump]
Downloads
- nvvm-0.10.0.1.tar.gz [browse] (Cabal source package)
- Package description (as included in the package)
Maintainer's Corner
For package maintainers and hackage trustees
Candidates
| Versions [RSS] | 0.7.5.0, 0.7.5.1, 0.7.5.2, 0.8.0.0, 0.8.0.1, 0.8.0.2, 0.8.0.3, 0.9.0.0, 0.10.0.0, 0.10.0.1 |
|---|---|
| Change log | CHANGELOG.md |
| Dependencies | base (>=4.6 && <5), bytestring, cuda (>=0.8), directory, filepath, template-haskell [details] |
| License | BSD-3-Clause |
| Copyright | [2016..2023] Trevor L. McDonell |
| Author | Trevor L. McDonell <trevor.mcdonell@gmail.com> |
| Maintainer | Trevor L. McDonell <trevor.mcdonell@gmail.com> |
| Category | Foreign |
| Home page | https://github.com/tmcdonell/nvvm |
| Source repo | head: git clone https://github.com/tmcdonell/nvvm this: git clone https://github.com/tmcdonell/nvvm(tag v0.10.0.1) |
| Uploaded | by TrevorMcDonell at 2023-08-15T13:47:35Z |
| Distributions | LTSHaskell:0.10.0.1, Stackage:0.10.0.1 |
| Reverse Dependencies | 2 direct, 6 indirect [details] |
| Downloads | 6460 total (49 in the last 30 days) |
| Rating | (no votes yet) [estimated by Bayesian average] |
| Your Rating | |
| Status | Docs uploaded by user Build status unknown [no reports yet] |
Readme for nvvm-0.10.0.1
[back to package description]Haskell FFI Bindings to NVVM
The NVVM library compiles NVVM IR (a subset of LLVM IR) into PTX code which can then be executed on NVIDIA GPUs.
In contrast to the standard NVPTX target built in to the LLVM
toolchain, NVVM includes a set of proprietary optimisations which are otherwise
only available by compiling CUDA code with the nvcc compiler. On the other
hand, the version of LLVM that NVVM is internally based on typically lags the
public release by several generations (years), so these secret optimisations may
or may not be worthwhile to your application.
The resulting PTX code can be loaded onto the GPU and executed using the cuda package.
The NVVM library is a compiler component available a part of the CUDA toolkit:
https://developer.nvidia.com/cuda-toolkit
The configure step will look for your CUDA installation in the standard places,
and if the nvcc compiler is found in your PATH, relative to that.