Foreign.CUDA.Driver.Context

Context management for low-level driver interface

Context Management

newtype Context

A device context

Constructors

Context

Fields

useContext :: Ptr ()

Instances

Eq Context

Show Context

data ContextFlag

Context creation flags

Constructors

SchedAuto

SchedSpin

SchedYield

SchedBlockingSync

BlockingSync

Deprecated: use SchedBlockingSync instead

SchedMask

MapHost

LmemResizeToMax

FlagsMask

Instances

Enum ContextFlag

Eq ContextFlag

Show ContextFlag

create :: Device -> [ContextFlag] -> IO Context

Create a new CUDA context and associate it with the calling thread

attach :: Context -> [ContextFlag] -> IO ()

Deprecated: deprecated as of CUDA-4.0

Increments the usage count of the context. API: no context flags are currently supported, so this parameter must be empty.

detach :: Context -> IO ()

Deprecated: deprecated as of CUDA-4.0

Detach the context, and destroy if no longer used

destroy :: Context -> IO ()

Destroy the specified context. This fails if the context is more than a single attachment (including that from initial creation).

device :: IO Device

Return the device of the currently active context

pop :: IO Context

Pop the current CUDA context from the CPU thread. The context must have a single usage count (matching calls to attach and detach). If successful, the new context is returned, and the old may be attached to a different CPU.

push :: Context -> IO ()

Push the given context onto the CPU's thread stack of current contexts. The context must be floating (via pop), i.e. not attached to any thread.

sync :: IO ()

Block until the device has completed all preceding requests

get :: IO Context

Return the context bound to the calling CPU thread. Requires cuda-4.0.

set :: Context -> IO ()

Bind the specified context to the calling thread. Requires cuda-4.0.

Peer Access

data PeerFlag

Possible option values for direct peer memory access

Instances

Enum PeerFlag

accessible :: Device -> Device -> IO Bool

Queries if the first device can directly access the memory of the second. If direct access is possible, it can then be enabled with add. Requires cuda-4.0.

add :: Context -> [PeerFlag] -> IO ()

If the devices of both the current and supplied contexts support unified addressing, then enable allocations in the supplied context to be accessible by the current context. Requires cuda-4.0.

remove :: Context -> IO ()

Disable direct memory access from the current context to the supplied context. Requires cuda-4.0.

Cache Configuration

data Cache

Device cache configuration preference

Constructors

PreferNone

PreferShared

PreferL1

PreferEqual

Instances

Enum Cache

Eq Cache

Show Cache

data Limit

Device limits flags

Constructors

StackSize

PrintfFifoSize

MallocHeapSize

DevRuntimeSyncDepth

DevRuntimePendingLaunchCount

Max

Instances

Enum Limit

Eq Limit

Show Limit

getLimit :: Limit -> IO Int

Query compute 2.0 call stack limits. Requires cuda-3.1.

setLimit :: Limit -> Int -> IO ()

Specify the size of the call stack, for compute 2.0 devices. Requires cuda-3.1.

setCacheConfig :: Cache -> IO ()

On devices where the L1 cache and shared memory use the same hardware resources, this sets the preferred cache configuration for the current context. This is only a preference. Requires cuda-3.2.