Google Git
Sign in
opensecura / sw / vec_iree / 6243e9e870d6c42fc2a622e44426357c6f07ff79
commit6243e9e870d6c42fc2a622e44426357c6f07ff79[log] [tgz]
authorLun Dong <lundong@google.com>Tue Sep 06 15:25:07 2022 -0700
committerLun Dong <lundong@google.com>Tue Sep 06 19:53:27 2022 -0700
tree1a2c1e5057c26e384f76de4774926bb797412141
parent6b5469bce456139ee049c909fab3fc8d21cb9e08 [diff]
Add support for VMVX backend

Add support for VMVX backend for both bytecode and emitc.

Buid VMVX targets in simple_vec_mul for illustration.

Note: IREE currently doesn't well support VMVX backend (LLVM is ok though) for TOSA imported TFLite models: TOSA IR can't be compiled to VMFB. (https://github.com/iree-org/iree/issues/10253)

Change-Id: I69dc84ce848f75e031d68ec21fc03cc3484efd58
11 files changed
tree: 1a2c1e5057c26e384f76de4774926bb797412141
  1. audio_prep/
  2. build_tools/
  3. cmake/
  4. device/
  5. model_util/
  6. native_log/
  7. risp4ml/
  8. samples/
  9. ssd_postprocess/
  10. CMakeLists.txt
  11. README.md
  12. springbok_config.h
README.md

Springbok Model Execution Repository

This project contains ML model codegen and execution libraries/examples. The artifacts built from this project is targeted for RISC-V 32-bit baremetal machine (Springbok).

Prerequisite

If you get this project from Project Shodan manifest, you are all set. If not, you need to have following projects as well to build the project successfully.

This project needs to be at <dir>/sw/vec_iree

Code structure

  • audio_prep: Audio preprocessing libarary
  • build_tools: Utility scripts for the project
  • cmake: CMake Macros for the project
  • device: Device HAL driver library
  • model_util: Runtime utility library for model execution
  • native_log: BSP support for the Linux userspace emulation
  • risp4ml: Vision preprocessing library (Reduced ISP for ML)
  • samples: Codegen and execution of ML models based on IREE
    • simple_vec_mul: Point-wise vector multiplication examples
  • ssd_postprocess: Vision postprocessing library for Single-Shot Detectors (SSD)

Build the project

If you are running from Project Shodan repo, you can build the artifacts with m iree. If you download this project alone, you need to download/build IREE's host compiler, then at the top level directory

  cmake -B <output dir> -G Ninja \
     -DCMAKE_TOOLCHAIN_FILE="$(realpath sw/vec_iree/cmake/riscv_iree.cmake)" \
     -DCMAKE_BUILD_TYPE=MinSizeRel \
     -DIREE_HOST_BINARY_ROOT="$(IREE_COMPILER_DIR)/install" \
     -DRISCV_TOOLCHAIN_ROOT=$(TOOLCHAINRV32_PATH) \
     <dir>/sw/vec_iree
  cmake --build <output dir> --target all

Run the executables

You can run QEMU or RENODE emulation with the built executables. In Shodan repo, qemu_sim_springbok for QEMU emulation, and sim_springbok for Renode simulation. Out-of-repo emulation is possible but require more steps.

Test the executables

In Shodan, this project utilizes LLVM lit and FileCheck to test the ML executable performance. The tests are defined in the *_test.run files under <output dir>. To run the test, at the Shodan top level directory

lit --path <Filecheck dir> -a <output dir>

Filecheck in Debian testing is under /usr/lib/llvm-11/bin

Add -D RUNNER=qemu to enable the qemu tests.