Deeploy.CommonExtensions.CodeTransformationPasses.MemoryAllocation.MemoryManagementGeneration

class Deeploy.CommonExtensions.CodeTransformationPasses.MemoryAllocation.MemoryManagementGeneration(memoryLevelRegex: str | None = None)

Bases: CodeTransformationPass, IntrospectiveCodeTransformationMixIn

Methods

__init__(memoryLevelRegex: str | None = None)

__init__([memoryLevelRegex])

apply(ctxt, executionBlock, name[, verbose])

Apply the CodeTransformation to an ExecutionBlock

dereferenceVars(template, varNames)

extractDynamicReferences(ctxt[, ...])

indexVars(template, varNames, index)

is_final_input(buffer, nodeName)

is_memory_level(buffer)

is_output(buffer, nodeName)

is_transient(buffer, nodeName)

topologicallySortBuffers(buffers)

Attributes

parseTreeDict

apply(ctxt: NetworkContext, executionBlock: ExecutionBlock, name: str, verbose: CodeGenVerbosity = CodeGenVerbosity(tilingProfiling=None, untiledProfiling=None)) → Tuple[NetworkContext, ExecutionBlock]

Apply the CodeTransformation to an ExecutionBlock

Parameters:

  • ctxt (NetworkContext) – Current NetworkContext

  • executionBlock (ExecutionBlock) – ExecutionBlock whose code you’d like to transform

  • name (str) – Graph node name of the operator being targetted

  • verbose (CodeGenVerbosity) – Control the verbosity of code generation

Returns:

Updated NetworkContext and ExecutionBlock

Return type:

Tuple[NetworkContext, ExecutionBlock]