Google Git
Sign in
opensecura / sw / vec_iree / d7a78573ecabea3f1fc069d5b967abf71cee7e65
commitd7a78573ecabea3f1fc069d5b967abf71cee7e65[log] [tgz]
authorLun Dong <lundong@google.com>Tue Nov 15 15:45:39 2022 -0800
committerLun Dong <lundong@google.com>Thu Nov 17 11:01:35 2022 -0800
treebb2120613e8c1371cc14e895879b549d5e0ffea9
parent2e3cd2fa5021a824463daae7bd2111064cf6ba55 [diff]
vec_iree: create sample custom microkernel library

We build infrastructure needed for future custom microkernel library in vec_iree/vmvx_ukernel and build targets based on it.

Currently we simply use iree generic ukernel library inside the custom
library, so the end performance is exactly the same as before. It will
be replaced with Kelvin in future.

Change-Id: I06f875adfaa965c76af5b58f95aa665089392e1c
6 files changed
tree: bb2120613e8c1371cc14e895879b549d5e0ffea9
  1. audio_prep/
  2. build_tools/
  3. cmake/
  4. device/
  5. model_util/
  6. native_log/
  7. risp4ml/
  8. samples/
  9. ssd_postprocess/
  10. vmvx_ukernel/
  11. CMakeLists.txt
  12. README.md
  13. 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)
  • vmvx_ukernel: Custom microkernel library for VMVX

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.