accelerate-cuda-0.13.0.2: accelerate-cuda.cabal
Name: accelerate-cuda
Version: 0.13.0.2
Cabal-version: >= 1.6
Tested-with: GHC >= 7.4
Build-type: Custom
Synopsis: Accelerate backend for NVIDIA GPUs
Description:
This library implements a backend for the /Accelerate/ language instrumented
for parallel execution on CUDA-capable NVIDIA GPUs. For further information,
refer to the main /Accelerate/ package:
<http://hackage.haskell.org/package/accelerate>
.
To use this backend you will need:
.
1. A CUDA-enabled NVIDIA GPU with, for full functionality, compute
capability 1.2 or greater. See the table on Wikipedia for supported GPUs:
<http://en.wikipedia.org/wiki/CUDA#Supported_GPUs>
.
2. The CUDA SDK, available from the NVIDIA Developer Zone:
<http://developer.nvidia.com/cuda-downloads>
.
See the Haddock documentation for additional information related to using this
backend.
.
Compile modules that use the CUDA backend with the @-threaded@ flag.
.
License: BSD3
License-file: LICENSE
Author: Manuel M T Chakravarty,
Robert Clifton-Everest,
Gabriele Keller,
Sean Lee,
Trevor L. McDonell
Maintainer: Trevor L. McDonell <tmcdonell@cse.unsw.edu.au>
Bug-reports: https://github.com/AccelerateHS/accelerate/issues
Homepage: https://github.com/AccelerateHS/accelerate-cuda/
Category: Compilers/Interpreters, Concurrency, Data, Parallelism
Stability: Experimental
-- We require 'accelerate_cuda_shape.h' to be in this list so that it is copied
-- as part of the installation, although 'cabal sdist' does not grok that it is
-- generated by the configure script.
--
Data-files: cubits/accelerate_cuda_extras.h
cubits/accelerate_cuda_function.h
cubits/accelerate_cuda_shape.h
cubits/accelerate_cuda_stencil.h
cubits/accelerate_cuda_texture.h
cubits/accelerate_cuda_type.h
cubits/accelerate_cuda_util.h
Extra-tmp-files: config.status
config.log
autom4te.cache
accelerate-cuda.buildinfo -- generated by configure
cubits/accelerate_cuda_shape.h -- generated by configure
Extra-source-files: configure
accelerate-cuda.buildinfo.in
cubits/accelerate_cuda_shape.h.in
include/accelerate.h
Flag debug
Description:
Enable tracing message flags. These are read from the command-line
arguments, which is convenient but may cause problems interacting with the
user program, so is not enabled by default. The available options:
.
* -ddump-cc: print the generated code, kernel table management information,
nvcc compiler warnings, and thread & resource statistics
.
* -ddebug-cc: compile code with debugging symbols, suitable for 'cuda-gdb'
.
* -ddump-exec: print each kernel name as it is invoked
.
* -ddump-gc: print memory management information
.
* -dverbose: other, uncategorised messages
.
* -fflush-cache: delete the persistent kernel cache
.
Default: False
Flag bounds-checks
Description: Enable bounds checking
Default: True
Flag unsafe-checks
Description: Enable bounds checking in unsafe operations
Default: False
Flag internal-checks
Description: Enable internal consistency checks
Default: False
Library
include-dirs: include
build-depends: accelerate == 0.13.*,
base == 4.*,
array >= 0.3 && < 0.5,
binary >= 0.5 && < 0.7,
bytestring >= 0.9 && < 0.11,
cryptohash >= 0.7 && < 0.10,
cuda >= 0.5.0.2 && < 0.6,
directory >= 1.0 && < 1.3,
fclabels >= 1.0 && < 1.2,
filepath >= 1.0 && < 1.4,
hashable >= 1.1 && < 1.3,
hashtables >= 1.0 && < 1.2,
language-c-quote >= 0.4.4 && < 0.8,
mainland-pretty >= 0.2 && < 0.3,
mtl >= 2.0 && < 2.2,
old-time >= 1.0 && < 1.2,
pretty >= 1.0 && < 1.2,
process >= 1.0 && < 1.2,
SafeSemaphore >= 0.9 && < 0.10,
srcloc >= 0.2 && < 0.5,
text >= 0.11 && < 0.12,
transformers >= 0.2 && < 0.4,
unordered-containers >= 0.1.4 && < 0.3
if os(windows)
cpp-options: -DWIN32
build-depends: Win32 >= 2.2.1
else
cpp-options: -DUNIX
build-depends: unix >= 2.4
Exposed-modules: Data.Array.Accelerate.CUDA
Data.Array.Accelerate.CUDA.Foreign
Other-modules: Data.Array.Accelerate.CUDA.AST
Data.Array.Accelerate.CUDA.Analysis.Device
Data.Array.Accelerate.CUDA.Analysis.Launch
Data.Array.Accelerate.CUDA.Array.Data
Data.Array.Accelerate.CUDA.Array.Nursery
Data.Array.Accelerate.CUDA.Array.Prim
Data.Array.Accelerate.CUDA.Array.Sugar
Data.Array.Accelerate.CUDA.Array.Table
Data.Array.Accelerate.CUDA.Async
Data.Array.Accelerate.CUDA.CodeGen
Data.Array.Accelerate.CUDA.CodeGen.Base
Data.Array.Accelerate.CUDA.CodeGen.IndexSpace
Data.Array.Accelerate.CUDA.CodeGen.Mapping
Data.Array.Accelerate.CUDA.CodeGen.Monad
Data.Array.Accelerate.CUDA.CodeGen.PrefixSum
Data.Array.Accelerate.CUDA.CodeGen.Reduction
Data.Array.Accelerate.CUDA.CodeGen.Stencil
Data.Array.Accelerate.CUDA.CodeGen.Type
Data.Array.Accelerate.CUDA.Compile
Data.Array.Accelerate.CUDA.Context
Data.Array.Accelerate.CUDA.Debug
Data.Array.Accelerate.CUDA.Execute
Data.Array.Accelerate.CUDA.FullList
Data.Array.Accelerate.CUDA.Persistent
Data.Array.Accelerate.CUDA.State
Data.Array.Accelerate.Internal.Check
Paths_accelerate_cuda
if flag(debug)
cpp-options: -DACCELERATE_DEBUG
if flag(bounds-checks)
cpp-options: -DACCELERATE_BOUNDS_CHECKS
if flag(unsafe-checks)
cpp-options: -DACCELERATE_UNSAFE_CHECKS
if flag(internal-checks)
cpp-options: -DACCELERATE_INTERNAL_CHECKS
ghc-options: -O2
-Wall
-fwarn-tabs
-- Don't add the extensions list here. Instead, place individual LANGUAGE
-- pragmas in the files that require a specific extension. This means the
-- project loads in GHCi, and avoids extension clashes.
--
-- Extensions:
source-repository head
type: git
location: https://github.com/AccelerateHS/accelerate-cuda