p95768021
/
InfiniTensor
forked from jiuyuan/InfiniTensor
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
142 Commits 70 Branches 0 Tags 141 MiB
C++ 76.3%
Cuda 18%
Python 4.3%
CMake 1.1%
Shell 0.1%
Go to file
zhengly123 a1974aabcd
NNET supports TVM backend and kernels (#78) 
* Add: mutator InfoGAN minimum test

* Add: cache and padding (bugs!!)

* Add: expression reader as a cmake target

* Fix: [Intermediate] NMutator::expressionToGraph

To be fix: matmul with implicit broadcast

* Add: matmul broadcast

* Fix: GraphObj ctor should use cloneTensor

* Fix: cuBLAS failure when codegen is enabled

* Add: Exception for checkCuError

* Fix: graph OpList ctor

* Add: expr simplication for TVM

* Add: TVM headers and CMake include paths

* Add: CMake config

* Add: PackedFunc (broken)

* Fix: remove cuCtxCreate which makes TVM fails

* Fix: membound_tvm

* Fix: test_memboundOp

* Add: PRelu Expr and AsTVMVisitor

* Add: Random generator

* Add: support TVM packed function

* Fix: specify runtime

* Add: CMake support of TVM

* Add: detailed output of Matmul

* Add: comments for Matmul

* Chore: format and comments

* Chore: GraphObj::selfCheck without assert control

* Fix: CMAKE_CXX_FLAGS in CMakeLists

* fix merge bug

* update api for mkl batchnorm test

* fix lotus env

* fig header bug

---------

Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
Co-authored-by: huangshuhong <huangsh19@mails.tsinghua.edu.cn>
Co-authored-by: whjthu <haojie0429@gmail.com>
 		2023-04-18 00:26:36 +08:00
.github/workflows fix code of bang conv (#76) 2023-03-29 15:47:32 +08:00
3rd-party test: enhance ci (#62) 2023-02-12 00:01:36 +08:00
cmake NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
include NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
proto Tensor serialization (#25) 2022-09-13 11:27:41 +08:00
pyinfinitensor Cpu backend2 (#77) 2023-04-17 12:15:23 +08:00
python NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
src NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
test NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
.clang-format Add: graph, tensor, and operator 2022-07-31 21:44:03 +08:00
.cmake-format.json Add: graph, tensor, and operator 2022-07-31 21:44:03 +08:00
.gitignore feat: 创建 pyinfinitensor 前端 2023-02-13 09:19:05 +08:00
.gitmodules add code for backtrace (#21) 2022-09-01 20:30:12 +08:00
CMakeLists.txt NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
LICENSE Initial commit 2022-07-27 22:40:23 +08:00
Makefile NNET supports TVM backend and kernels (#78) 2023-04-18 00:26:36 +08:00
README.md Cpu backend2 (#77) 2023-04-17 12:15:23 +08:00

README.md

InfiniTensor

Compilation on Lotus

Compilation for cuda

# Enter the root of InfiniTensor
source test/script/env_lotus.sh
make CUDA=ON

Compilation for intelcpu

# Enter the root of InfiniTensor
source test/script/env_lotus.sh intelcpu
mkdir build && cd build
cmake -DUSE_INTELCPU=ON -DCMAKE_CXX_COMPILER=dpcpp .. && make -j 12

Make Commands

  • make/make build: Builds the project;
  • make install-python: Builds the project then install the python frontend;
  • make test-cpp: Builds the project then run cpp unit tests;
  • make test-onnx: Run python unit tests;

Sets env: CUDA=ON to enable cuda.

CMake Options

There are several configurable CMake options, see the CMakeLists.txt file.

  • If USE_BACKTRACE is ON, libdw-dev have to be installed. See the README of backward-cpp for details.
  • If USE_PROTOBUF is ON, protobuf have to be installed. See the README of protobuf for details.
  • If USE_CUDA is ON, cuda have to be installed.

Contributor Guide

InfiniTensor development is based on the pull request on Github. Before requesting for merging, a PR should satisfy the following requirements

  1. Pass all tests.
    1. Now CI on Github will test everything that can be tested in the ci environment, including code format. So, script test/script/clang_format_inplace.sh is for formatting all code.
    2. Contributors should run ctest manually and copy its output to the PR. Use fenced code blocks (triple backquotes, i.e., ```) to avoid referencing in Github. Otherwise, # in the output is interpreted as a Github reference. Do not directly paste the ctest output in commit messages either for the same reason.
  2. Receive at least one approval from reviewers.
  3. PR title should be concise since it is going to be the commit message in the main branch after merging and squashing.

Dependencies