catalyst.debug.compile_from_mlir¶
- compile_from_mlir(ir, compiler=None, compile_options=None)[source]¶
Compile a Catalyst function to binary code from the provided MLIR.
- Parameters
ir (str) – the MLIR to compile in string form
compile_options – options to use during compilation
- Returns
A callable that manages the compiled shared library and its invocation.
- Return type
CompiledFunction
See also
Example
The main entry point of the program is required to start with
catalyst.entry_point
, and the program is required to containsetup
andteardown
functions.ir = r\""" module @workflow { func.func public @catalyst.entry_point(%arg0: tensor<f64>) -> tensor<f64> attributes {llvm.emit_c_interface} { return %arg0 : tensor<f64> } func.func @setup() { quantum.init return } func.func @teardown() { quantum.finalize return } } \""" compiled_function = debug.compile_from_mlir(ir)
>>> compiled_function(0.1) [0.1]
code/api/catalyst.debug.compile_from_mlir
Download Python script
Download Notebook
View on GitHub