tvm.target

Target management API of TVM.

TVM’s target string is in fomat <target_name> [-option=value]....

Note

The list of options include:

  • -device=<device name>

    The device name.

  • -mtriple=<target triple> or -target

    Specify the target triple, which is useful for cross compilation.

  • -mcpu=<cpuname>

    Specify a specific chip in the current architecture to generate code for. By default this is infered from the target triple and autodetected to the current architecture.

  • -mattr=a1,+a2,-a3,…

    Override or control specific attributes of the target, such as whether SIMD operations are enabled or not. The default set of attributes is set by the current CPU.

  • -system-lib

    Build TVM system library module. System lib is a global module that contains self registered functions in program startup. User can get the module using tvm.module.system_lib. It is useful in environments where dynamic loading api like dlopen is banned. The system lib will be available as long as the result code is linked by the program.

We can use tvm.target.create to create a tvm.target.Target from the target string. We can also use other specific function in this module to create specific targets.

class tvm.target.GenericFunc

GenericFunc node reference. This represents a generic function that may be specialized for different targets. When this object is called, a specialization is chosen based on the current target.

Note

Do not construct an instance of this object, it should only ever be used as a return value from calling into C++.

register(func, key_list, allow_override=False)

Register a specialization for this GenericFunc.

Parameters:
  • func (function) – The function to be registered.
  • key (str or list of str) – The key to be registered.
  • allow_override (bool, optional) – Whether to allow existing keys to be overridden.
set_default(func, allow_override=False)

Set the default function to be used if no specializations match the current target.

Parameters:
  • func (function) – The default function
  • allow_override (bool) – Whether to allow the current default to be overridden
class tvm.target.Target

Target device information, use through TVM API.

Note

Do not use class constructor, you can create target using the following functions

tvm.target.arm_cpu(model='unknown', options=None)

Returns a ARM CPU target. This function will also download pre-tuned op parameters when there is none.

Parameters:
  • model (str) – SoC name or phone name of the arm board.
  • options (str or list of str) – Additional options
tvm.target.create(target_str)

Get a target given target string.

Parameters:target_str (str) – The target string.
Returns:target – The target object
Return type:Target

Note

See the note on tvm.target on target string format.

tvm.target.cuda(model='unknown', options=None)

Returns a cuda target.

Parameters:
  • model (str) – The model of cuda device (e.g. 1080ti)
  • options (str or list of str) – Additional options
tvm.target.current_target(allow_none=True)

Returns the current target.

Parameters:allow_none (bool) – Whether allow the current target to be none
Raises:ValueError if current target is not set.
tvm.target.generic_func(fdefault)

Wrap a target generic function.

Generic function allows registeration of further functions that can be dispatched on current target context. If no registered dispatch is matched, the fdefault will be called.

Parameters:fdefault (function) – The default function.
Returns:fgeneric – A wrapped generic function.
Return type:function

Example

import tvm
# wrap function as target generic
@tvm.target.generic_func
def my_func(a):
    return a + 1
# register specialization of my_func under target cuda
@my_func.register("cuda")
def my_func_cuda(a):
    return a + 2
# displays 3, because my_func is called
print(my_func(2))
# displays 4, because my_func_cuda is called
with tvm.target.cuda():
    print(my_func(2))
tvm.target.get_native_generic_func(name)

Get a generic function from the global registry. If no function is registered under the given name, a new generic function is created.

Parameters:name (string) – The name of the generic function to get
Returns:func – The generic function for the given name
Return type:GenericFunc
tvm.target.intel_graphics(model='unknown', options=None)

Returns an Intel Graphics target.

Parameters:
  • model (str) – The model of this device
  • options (str or list of str) – Additional options
tvm.target.mali(model='unknown', options=None)

Returns a ARM Mali GPU target.

Parameters:
  • model (str) – The model of this device
  • options (str or list of str) – Additional options
tvm.target.opengl(model='unknown', options=None)

Returns a OpenGL target.

Parameters:options (str or list of str) – Additional options
tvm.target.override_native_generic_func(func_name)

Override a generic function defined in C++

Generic function allows registration of further functions that can be dispatched on current target context. If no registered dispatch is matched, the fdefault will be called.

Parameters:func_name (string) – The name of the generic func to be overridden
Returns:fgeneric – A wrapped generic function.
Return type:function

Example

import tvm
# wrap function as target generic
@tvm.target.override_native_generic_func("my_func")
def my_func(a):
    return a + 1
# register specialization of my_func under target cuda
@my_func.register("cuda")
def my_func_cuda(a):
    return a + 2
# displays 3, because my_func is called
print(my_func(2))
# displays 4, because my_func_cuda is called
with tvm.target.cuda():
    print(my_func(2))
tvm.target.rasp(options=None)

Return a Raspberry 3b target.

Parameters:options (str or list of str) – Additional options
tvm.target.rocm(model='unknown', options=None)

Returns a ROCM target.

Parameters:
  • model (str) – The model of this device
  • options (str or list of str) – Additional options