Hybrid Frontend Language Reference¶
This hybrid frontend allows users to write preliminary versions of some idioms that yet have been supported by TVM officially.
Both software emulation and compilation are supported. To define a function,
you need to use
tvm.hybrid.script decorator to indicate this is a hybrid function:
@tvm.hybrid.script def outer_product(a, b, c): for i in range(a.shape): for j in range(b.shape): c[i, j] = a[i] * b[j] a = numpy.random.rand(100) b = numpy.random.rand(99) c = numpy.zeros((100, 99)) outer_product(a, b, c)
This decorator will import Keywords required spontaneously when software emulation. After software emulation is done, the imported keywords will be cleaned up. Users do not need worry about keyword conflict and pollution.
Every element passed for software emulation in the argument list is either a python variable
numpy numeric type.
The current parse interface looks like:
a = tvm.placeholder((100, ), name='a') b = tvm.placeholder((99, ), name='b') c = tvm.placeholder((100, 99), name='c') tvm.hybrid.parse(outer_product, [a, b, c]) # return an ir root of this function
If we pass these tvm tensors to this function, it returns a op node:
Under construction, we are still deciding what kind of node should be returned.
a = tvm.placeholder((100, ), name='a') b = tvm.placeholder((99, ), name='b') c = tvm.placeholder((100, 99), name='c') op = outer_product(a, b, c) # return the corresponding op node
Under construction, not truly supported yet.
Follow up the example above, you can use some tvm like interfaces to tune the code:
sch = tvm.create_schedule(op) jo, ji = sch.split(j, 4) sch.vectorize(ji)
reorder, and loop_annotation will be supported!
In HalideIR, loops have in total 4 types:
Here we use
these 4 keywords to annotate the corresponding types of for loops.
The the usage is roughly the same as Python standard
All the mutatable variables will be lowered to an array with size 1. It regards the first store of a variable as its declaration.
Unlike conventional Python, in hybrid script, the declared variable can only be used in the scope level it is declared.
Currently, you can ONLY use basic-typed variables, i.e. the type of the
variable should be either
for i in range(5): s = 0 # declaration, this s will be a 1-array in lowered IR for j in range(5): s += a[i, j] # do something with sum b[i] = sum # you can still use sum in this level a = s # you CANNOT use s here, even though it is allowed in conventional Python b = (1, 2) # this has NOT been supported yet!
So far, ONLY tensors’
shape attribute is supported! The
shape atrribute is essentailly a
tuple, so you MUST access it as an array. Also, currently, only constant-indexed access is supported.
x = a.shape # OK! for i in range(3): for j in a.shape[i]: # BAD! i is not a constant! # do something
Conditional Statement and Expression¶
if condition: # do something a = b if condition else c
False keyword supported yet.
So far, these math intrinsics,
popcount, are supported.
No import is required, just as it is mentioned in Software Emulation, just use it!
Under construction, this function will be supported later!
Use a function call
allocation(shape, type, share/local) to declare an array buffer.
The basic usage is roughly the same as a normal array.
You can also do loop-thread bind by writing code like this:
for tx in bind("threadIdx.x", 100): a[tx] = b[tx]
- For keywords:
- Math keywords: