The accelerate-llvm-ptx package

[Tags:bsd3, library]

This library implements a backend for the Accelerate language which generates LLVM-IR targeting CUDA capable GPUs. For further information, refer to the main Accelerate package:


Dependencies accelerate (==1.0.*), accelerate-llvm (==1.0.*), base (>=4.7 && <4.10), bytestring (>=0.9), containers (==0.5.*), cuda (>=0.7), directory (>=1.0), dlist (>=0.6), fclabels (>=2.0), filepath (>=1.0), hashable (>=1.2), llvm-hs (==4.0.*), llvm-hs-pure (==4.0.*), mtl (>=2.2.1), nvvm (>=0.7.5), pretty (>=1.1), time (>=1.4), unordered-containers (>=0.2) [details]
License BSD3
Author Trevor L. McDonell
Maintainer Trevor L. McDonell <>
Category Compilers/Interpreters, Concurrency, Data, Parallelism
Bug tracker
Source repository head: git clone
this: git clone
Uploaded Thu May 25 10:29:56 UTC 2017 by TrevorMcDonell
Updated Thu May 25 10:32:56 UTC 2017 by TrevorMcDonell to revision 1
Distributions NixOS:
Downloads 147 total (30 in the last 30 days)
0 []
Status Docs uploaded by user
Build status unknown [no reports yet]
Hackage Matrix CI




nvvmUse the NVVM library to generate optimised PTXDisabledAutomatic
debugEnable debug tracing message flags. Note that 'debug' must be enabled in the base 'accelerate' package as well. See the 'accelerate' package for usage and available options.DisabledAutomatic
bounds-checksEnable bounds checkingEnabledAutomatic
unsafe-checksEnable bounds checking in unsafe operationsDisabledAutomatic
internal-checksEnable internal consistency checksDisabledAutomatic

Use -f <flag> to enable a flag, or -f -<flag> to disable that flag. More info


Maintainer's Corner

For package maintainers and hackage trustees