Mousius commented on code in PR #71: URL: https://github.com/apache/tvm-rfcs/pull/71#discussion_r876087210
########## rfcs/0070-target-preprocessing.md: ########## @@ -0,0 +1,217 @@ +- Feature Name: target-architecture-preprocessor +- Start Date: 2022-04-04 +- RFC PR: [apache/tvm-rfcs#0070](https://github.com/apache/tvm-rfcs/pull/0000) +- GitHub Issue: [apache/tvm#0000](https://github.com/apache/tvm/issues/0000) + +# Summary +[summary]: #summary +Provide a standard and easily testable way to inspect architecture extensions and provide them to the various parts of TVM which utilise that information. + +# Motivation +[motivation]: #motivation +TVM has multiple ways to define a `Target`s architectural features for use in deciding on schedules or other calculations, here's a few different ways we do this: + +* CPU to Feature Mapping: https://github.com/apache/tvm/blob/d2db9cb0d839e32778f461b77e59f6418282a511/python/tvm/target/arm_isa.py#L22-L39 +* Inspecting `Target` in utility functions: https://github.com/apache/tvm/blob/d2db9cb0d839e32778f461b77e59f6418282a511/python/tvm/topi/arm_cpu/arm_utils.py#L24-L70 +* Inspecting `Target` in utility functions inside legalization code: https://github.com/apache/tvm/blob/02fbaf0ed9120a8f95155e63de42459f230584aa/python/tvm/relay/qnn/op/legalizations.py#L350-L359 +* Inspecting `Target` inside the definition a strategy: https://github.com/apache/tvm/blob/b542724873140bb051492530d97a78b9b7b7983d/python/tvm/relay/op/strategy/arm_cpu.py#L232 +* Processing bespoke Compiler arguments: https://github.com/apache/tvm/blob/d2db9cb0d839e32778f461b77e59f6418282a511/src/relay/backend/contrib/cmsisnn/compiler_attrs.cc#L47-L70 +* Registered as a `PackedFunc` (https://github.com/apache/tvm/blob/24e5498021cecca2fe7d44149ce90efe28b6d930/python/tvm/topi/x86/utils.py#L21-L34) and then used as part of `Op` processing: https://github.com/apache/tvm/blob/24e5498021cecca2fe7d44149ce90efe28b6d930/src/relay/qnn/op/requantize_config.h#L58-L73 + +This RFC aims to standardise the way in which we convert `Target` attributes into architectural features by processing them ahead of time. + +# Guide-level explanation +[guide-level-explanation]: #guide-level-explanation + +Two additional pre-processors can be added to the `Target`, for users to preprocess architectural information when the `Target` is created: +* Architecture Pre-processing - maps `Target` `attrs` to a new `arch` object +* Keys Pre-processing - maps `Target` `attrs` and `keys` to a new set of `keys` + +These new preprocessors will be illustrated using examples targeting TVM for Arm(R) Cortex(R)-M4. + +## Architecture Pre-processing +```c++ +TVM_REGISTER_TARGET_KIND("c", kDLCPU) + .set_arch_preprocessor(MyArchPreprocessor) +``` + +This takes the `attrs` from `Target` and converts them into an object representing the architectural features of the `Target`, which can then be accessed using the `GetArch` method similar to `GetAttr`: + +```c++ +Target my_target("c -mcpu=cortex-m4"); +my_target->GetArch<Bool>("is_aarch64", false); // false +my_target->GetArch<Bool>("has_dsp", false); // true Review Comment: The main distinction is the architecture features are inferred from the `Target` `attrs`, if we want users to pass it in then it would need to be in `attrs` as you're correct there's no way of modifying it from a users point of view. > * I think this would be a useful feature in order to selectively disable features for debugging and performance comparison. Alternatively, we'd get this same benefit if `GetAttr` is allowed to delegate to `GetArch` for undefined values, and and `GetArch` is only used internally. I referenced this a bit here: https://github.com/apache/tvm-rfcs/pull/71/files#diff-c04c196e8069297e1fcfdd5a514a268b971943b265649eaa41edd8d47052d56aR174-R182 I'd rather keep `Target` `attrs` separated out from `arch` so as not to confuse the `Target` API by having too many things accessible as direct properties of it? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
