Google Git
Sign in
opensecura / sw / vec_iree / 41c0b8638a81f68426748a2a4ff8ae3cb80e7104
commit41c0b8638a81f68426748a2a4ff8ae3cb80e7104[log] [tgz]
authorLun Dong <lundong@google.com>Sun Mar 06 19:00:08 2022 +0000
committerLun Dong <lundong@google.com>Mon Mar 07 23:42:06 2022 +0000
tree942e9d40ca43f352ce32c63487486fc55f1d6916
parent150783ad8482ff192922c1421ebc5267ff28a58d [diff]
RISP4ML: further optimize memory allocation and usage

This change further optimizes memory allocation/usage for RISP4ML.

It enables in-place operations in RISP4ML stages whenever possible and minimizes use of "malloc". Unit tests are also updated accordingly.

The change has been verified by comparing output@plain-C risp4ml against output@google3. All unit tests are passed.

Change-Id: I93ec0c97f75c36be764bc65e4a886f725e0b2a9a
13 files changed
tree: 942e9d40ca43f352ce32c63487486fc55f1d6916
  1. build_tools/
  2. cmake/
  3. native_log/
  4. samples/
  5. CMakeLists.txt
  6. README.md
  7. 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

  • build_tools: Utility scripts for the project
  • cmake: CMake Macros for the project
  • native_log: BSP support for the Linux userspace emulation
  • samples: Codegen and execution of ML models based on IREE
    • device: Device HAL driver library
    • float_model: float model examples
    • quant_model: quantized model examples
    • simple_vec_mul: Point-wise vector multiplication examples
    • util: Runtime utility library for model execution

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.txt files under samples. To run the test, at the Shodan top level directory

lit --path <Filecheck dir> -a sw/vec_iree/samples

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

Add -D FEATURES=internal to enable the internal model tests. Add -D RUNNER=qemu to enable the qemu tests.