Futhark.CodeGen.ImpGen.GPU.Base

Documentation

data KernelConstants

Constructors

KernelConstants

Fields

• kernelGlobalThreadId :: TExp Int32
• kernelLocalThreadId :: TExp Int32
• kernelGroupId :: TExp Int32
• kernelGlobalThreadIdVar :: VName
• kernelLocalThreadIdVar :: VName
• kernelGroupIdVar :: VName
• kernelNumGroups :: TExp Int64
• kernelGroupSize :: TExp Int64
• kernelNumThreads :: TExp Int32
• kernelWaveSize :: TExp Int32
• kernelThreadActive :: TExp Bool
• kernelLocalIdMap :: Map [SubExp] [TExp Int32]

  A mapping from dimensions of nested SegOps to already computed local thread IDs.

keyWithEntryPoint :: Maybe Name -> Name -> Name

type CallKernelGen = ImpM GPUMem HostEnv HostOp

type InKernelGen = ImpM GPUMem KernelEnv KernelOp

data Locks

Information about the locks available for accumulators.

Constructors

Locks

Fields

• locksArray :: VName
• locksCount :: Int

data HostEnv

Constructors

HostEnv

Fields

• hostAtomics :: AtomicBinOp
• hostTarget :: Target
• hostLocks :: Map VName Locks

data Target

Which target are we ultimately generating code for? While most of the kernels code is the same, there are some cases where we generate special code based on the ultimate low-level API we are targeting.

Constructors

CUDA

OpenCL

data KernelEnv

Constructors

KernelEnv

Fields

• kernelAtomics :: AtomicBinOp
• kernelConstants :: KernelConstants
• kernelLocks :: Map VName Locks

computeThreadChunkSize :: SplitOrdering -> TExp Int64 -> Count Elements (TExp Int64) -> Count Elements (TExp Int64) -> TV Int64 -> ImpM rep r op ()

groupReduce :: TExp Int32 -> Lambda GPUMem -> [VName] -> InKernelGen ()

groupScan :: Maybe (TExp Int32 -> TExp Int32 -> TExp Bool) -> TExp Int64 -> TExp Int64 -> Lambda GPUMem -> [VName] -> InKernelGen ()

isActive :: [(VName, SubExp)] -> TExp Bool

sKernelThread :: String -> Count NumGroups (TExp Int64) -> Count GroupSize (TExp Int64) -> VName -> InKernelGen () -> CallKernelGen ()

sKernelGroup :: String -> Count NumGroups (TExp Int64) -> Count GroupSize (TExp Int64) -> VName -> InKernelGen () -> CallKernelGen ()

sReplicate :: VName -> SubExp -> CallKernelGen ()

Perform a Replicate with a kernel.

sIota :: VName -> TExp Int64 -> Exp -> Exp -> IntType -> CallKernelGen ()

Perform an Iota with a kernel.

sCopy :: CopyCompiler GPUMem HostEnv HostOp

compileThreadResult :: SegSpace -> PatElem GPUMem -> KernelResult -> InKernelGen ()

compileGroupResult :: SegSpace -> PatElem GPUMem -> KernelResult -> InKernelGen ()

virtualiseGroups :: SegVirt -> TExp Int32 -> (TExp Int32 -> InKernelGen ()) -> InKernelGen ()

For many kernels, we may not have enough physical groups to cover the logical iteration space. Some groups thus have to perform double duty; we put an outer loop to accomplish this. The advantage over just launching a bazillion threads is that the cost of memory expansion should be proportional to the number of *physical* threads (hardware parallelism), not the amount of application parallelism.

groupLoop :: TExp Int64 -> (TExp Int64 -> InKernelGen ()) -> InKernelGen ()

Assign iterations of a for-loop to threads in the workgroup. The passed-in function is invoked with the (symbolic) iteration. For multidimensional loops, use groupCoverSpace.

kernelLoop :: IntExp t => TExp t -> TExp t -> TExp t -> (TExp t -> InKernelGen ()) -> InKernelGen ()

Assign iterations of a for-loop to all threads in the kernel. The passed-in function is invoked with the (symbolic) iteration. threadOperations will be in effect in the body. For multidimensional loops, use groupCoverSpace.

groupCoverSpace :: [TExp Int64] -> ([TExp Int64] -> InKernelGen ()) -> InKernelGen ()

Iterate collectively though a multidimensional space, such that all threads in the group participate. The passed-in function is invoked with a (symbolic) point in the index space.

precomputeSegOpIDs :: Stms GPUMem -> InKernelGen a -> InKernelGen a

atomicUpdateLocking :: AtomicBinOp -> Lambda GPUMem -> AtomicUpdate GPUMem KernelEnv

Do an atomic update corresponding to a binary operator lambda.

type AtomicBinOp = BinOp -> Maybe (VName -> VName -> Count Elements (TExp Int64) -> Exp -> AtomicOp)

Is there an atomic BinOp corresponding to this BinOp?

data Locking

Locking strategy used for an atomic update.

Constructors

Locking

Fields

• lockingArray :: VName

  Array containing the lock.

• lockingIsUnlocked :: TExp Int32

  Value for us to consider the lock free.

• lockingToLock :: TExp Int32

  What to write when we lock it.

• lockingToUnlock :: TExp Int32

  What to write when we unlock it.

• lockingMapping :: [TExp Int64] -> [TExp Int64]

  A transformation from the logical lock index to the physical position in the array. This can also be used to make the lock array smaller.

data AtomicUpdate rep r

The mechanism that will be used for performing the atomic update. Approximates how efficient it will be. Ordered from most to least efficient.

Constructors

AtomicPrim (DoAtomicUpdate rep r)

Supported directly by primitive.

AtomicCAS (DoAtomicUpdate rep r)

Can be done by efficient swaps.

AtomicLocking (Locking -> DoAtomicUpdate rep r)

Requires explicit locking.

type DoAtomicUpdate rep r = Space -> [VName] -> [TExp Int64] -> ImpM rep r KernelOp ()

A function for generating code for an atomic update. Assumes that the bucket is in-bounds.