Foreign.CUDA.Runtime.Exec

Kernel execution control for C-for-CUDA runtime interface

Kernel Execution

type Fun = FunPtr ()

A global device function.

Note that the use of a string naming a function was deprecated in CUDA 4.1 and removed in CUDA 5.0.

data FunAttributes

Constructors

FunAttributes

Fields

• constSizeBytes :: !Int64
• localSizeBytes :: !Int64
• sharedSizeBytes :: !Int64
• maxKernelThreadsPerBlock :: !Int

  maximum block size that can be successively launched (based on register usage)

• numRegs :: !Int

  number of registers required for each thread

Instances

Show FunAttributes

Defined in Foreign.CUDA.Runtime.Exec

Methods

showsPrec :: Int -> FunAttributes -> ShowS

show :: FunAttributes -> String

showList :: [FunAttributes] -> ShowS

Storable FunAttributes

Defined in Foreign.CUDA.Runtime.Exec

Methods

sizeOf :: FunAttributes -> Int

alignment :: FunAttributes -> Int

peekElemOff :: Ptr FunAttributes -> Int -> IO FunAttributes

pokeElemOff :: Ptr FunAttributes -> Int -> FunAttributes -> IO ()

peekByteOff :: Ptr b -> Int -> IO FunAttributes

pokeByteOff :: Ptr b -> Int -> FunAttributes -> IO ()

peek :: Ptr FunAttributes -> IO FunAttributes

poke :: Ptr FunAttributes -> FunAttributes -> IO ()

data FunParam where

Kernel function parameters. Doubles will be converted to an internal float representation on devices that do not support doubles natively.

Constructors

IArg :: !Int -> FunParam

FArg :: !Float -> FunParam

DArg :: !Double -> FunParam

VArg :: Storable a => !a -> FunParam

data CacheConfig

Cache configuration preference

Constructors

None

Shared

L1

Equal

Instances

Enum CacheConfig

Defined in Foreign.CUDA.Runtime.Exec

Methods

succ :: CacheConfig -> CacheConfig

pred :: CacheConfig -> CacheConfig

toEnum :: Int -> CacheConfig

fromEnum :: CacheConfig -> Int

enumFrom :: CacheConfig -> [CacheConfig]

enumFromThen :: CacheConfig -> CacheConfig -> [CacheConfig]

enumFromTo :: CacheConfig -> CacheConfig -> [CacheConfig]

enumFromThenTo :: CacheConfig -> CacheConfig -> CacheConfig -> [CacheConfig]

Eq CacheConfig

Defined in Foreign.CUDA.Runtime.Exec

Methods

(==) :: CacheConfig -> CacheConfig -> Bool

(/=) :: CacheConfig -> CacheConfig -> Bool

Show CacheConfig

Defined in Foreign.CUDA.Runtime.Exec

Methods

showsPrec :: Int -> CacheConfig -> ShowS

show :: CacheConfig -> String

showList :: [CacheConfig] -> ShowS

attributes :: Fun -> IO FunAttributes

Obtain the attributes of the named global device function. This itemises the requirements to successfully launch the given kernel.

setConfig

Arguments

:: (Int, Int)

grid dimensions

-> (Int, Int, Int)

block dimensions

-> Int64

shared memory per block (bytes)

-> Maybe Stream

associated processing stream

-> IO ()

Specify the grid and block dimensions for a device call. Used in conjunction with setParams, this pushes data onto the execution stack that will be popped when a function is launched.

setParams :: [FunParam] -> IO ()

Set the argument parameters that will be passed to the next kernel invocation. This is used in conjunction with setConfig to control kernel execution.

setCacheConfig :: Fun -> CacheConfig -> IO ()

On devices where the L1 cache and shared memory use the same hardware resources, this sets the preferred cache configuration for the given device function. This is only a preference; the driver is free to choose a different configuration as required to execute the function.

Switching between configuration modes may insert a device-side synchronisation point for streamed kernel launches

launch :: Fun -> IO ()

Invoke the global kernel function on the device. This must be preceded by a call to setConfig and (if appropriate) setParams.

launchKernel

Arguments

:: Fun

Device function symbol

-> (Int, Int)

grid dimensions

-> (Int, Int, Int)

thread block shape

-> Int64

shared memory per block (bytes)

-> Maybe Stream

(optional) execution stream

-> [FunParam]

-> IO ()

Invoke a kernel on a (gx * gy) grid of blocks, where each block contains (tx * ty * tz) threads and has access to a given number of bytes of shared memory. The launch may also be associated with a specific Stream.