@hackage accelerate-cuda0.12.1.1
Accelerate backend for NVIDIA GPUs
Categories
License
BSD-3-Clause
Maintainer
Trevor L. McDonell <tmcdonell@cse.unsw.edu.au>
Links
Versions
Deprecated
Tested Compilers
Dependencies (24)
- Win32 >=2.2.1
- accelerate >=0.12.1 && <0.13
- array >=0.3 && <0.5
- base >=4 && <5
- binary >=0.5 && <0.6
- blaze-builder >=0.3 && <0.4 Show all…
Dependents (13)
@hackage/accelerate-fourier, @hackage/meta-par-accelerate, @hackage/gloss-raster-accelerate, @hackage/parconc-examples, @hackage/acme-everything, @hackage/accelerate-cufft, Show all…-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
Package Flags
debug
(off by default)
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:
bounds-checks
(on by default)
Enable bounds checking
unsafe-checks
(off by default)
Enable bounds checking in unsafe operations
internal-checks
(off by default)
Enable internal consistency checks
This library implements a backend for the Accelerate language instrumented for parallel execution on CUDA-capable NVIDIA GPUs.
To use this backend you need CUDA version 3.x or later installed, which you can find at the NVIDIA Developer Zone.