* MLU CNCL base
* add FindCNCL.cmake, not find -lcncl
* bangPrintFloat not find
* docker:make sucessful, test error
* delete net file and onnxtest.py
* init
* fix cncl
* format
* fix
* format
* fix cncl
* run dist gpt2 on mlu
* format
* fix import error on mlu docker
* run llama single card
* run distributed llama2
* add test for slice/reduce on mlu
* fix cncl related test
* fix format
* format
* delete comments
* change GPU to MLU
* MLU CNCL base
* add FindCNCL.cmake, not find -lcncl
* bangPrintFloat not find
* docker:make sucessful, test error
* delete net file and onnxtest.py
* init
* fix cncl
* format
* fix
* format
* fix cncl
* run dist gpt2 on mlu
* format
* fix import error on mlu docker
* run llama single card
* run distributed llama2
* add test for slice/reduce on mlu
* fix cncl related test
* fix format
* format
* delete comments
* change GPU to MLU
* modify launch script
* fix name
* fix format
* fix gather
* format python script
---------
Co-authored-by: xgqdut2016 <kenan_gewei@163.com>
Co-authored-by: Bolun <chamberlain0w0@gmail.com>
Co-authored-by: Bolun Zhang <48948016+Chamberlain0w0@users.noreply.github.com>
* test: 支持编译 einnet 单元测试，但不是所有测试都能通过
Signed-off-by: YdrMaster <ydrml@hotmail.com>
* Fix: locating resource files and skip codegen
- Change the path parameters in `matchExprResult` and `checkExprLogSame` to paths relative to the project home
- Skip NNetMemboundOp tests as they require codegen
---------
Signed-off-by: YdrMaster <ydrml@hotmail.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
* support kunlun xpu and add an operator named Add
* add sub, mul, div, pow, maximum, minimum
* add code
* add xpu code
* add code
* add matmul
* add transpose
* add unary operator
* add unary operator
* add some operator
* add code
* support run resnet18 on xpu
* add code
* add max pool2d
* fix xpu code, let it can run.
* 添加XPU算子 (#120)
* add floordiv for xpu
* add batchnorm for xpu
* add more cast types for xpu
* add conv_trans for xpu
* add pad for xpu
* add logical ops for xpu
* fix format for xpu src and include
* fix format for xpu test
* fix format for xpu src
---------
Co-authored-by: Bolun <bolunz@u.nus.edu>
* Xpu abs (#121)
* add: unary kernel for xpu
* formatting
* format
* format
* format
* fix: pointer jump
* fix optype comments
* fix bug introduced while resolving conflict
* change cmake option for kunlunxin xpu from 'xpu' to 'kunlun'; fix bug after merging distributed infrastructure
* Add doc support for xpu (#141)
* fix
* fix
* fix pooling test
* format
* format
* fix
* fix
* set cmake version requirement
* fix cmakelists
* rename xpu to kunlun
* fix
* fix format
* fix format
* fix format
* fix change name to kunlun
* format
* fix format
* clang format
* fix format
---------
Co-authored-by: root <root@localhost.localdomain>
Co-authored-by: wanghailu <wanghailu@qiyuanlab.com>
Co-authored-by: wanghailu <wanghailu0717@163.com>
Co-authored-by: Bolun Zhang <48948016+Chamberlain0w0@users.noreply.github.com>
Co-authored-by: Bolun <bolunz@u.nus.edu>
Co-authored-by: zhangyue207 <138768300+zhangyue207@users.noreply.github.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
Co-authored-by: baominghelly <41820386+baominghelly@users.noreply.github.com>
Co-authored-by: Bolun <chamberlain0w0@gmail.com>
* add cmake bits about NCCL
* move example to examples/NNmodel
* impl NCCL communicator
* add comm related function to Runtime
* export runtime interface
* add launch.py
* use unique name to distingush the the NCCL ID file
* add timeout to communicator init
* expose communicator obj from runtime obj, add unit test for nccl communicator
* reformat files
* Add allReduce operator and cuda nccl allReduce kernel
* impl model parallel for resnet
* add allGather nccl kernel and operator
* Add allreduce allgather operator tests, change allgather kernel to output list of tensor, fix shape infer, handle nullptr output
* fix format of onnx.py
* use concat following AllGather
* get tensor parallel for resnet
* fix format of graph_handler.cc
* change BUILD_DIST default to OFF
* polish code of communicator
* update .gitignore
* Add broadcast operator and cuda kernel
* Add comments for operators
* remove const of class member
* move communicator to CudaRuntimeObj
* Add an empty line at EOF.
---------
Co-authored-by: panzezhong <panzezhong@qiyuanlab.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* - add LazyAllocator class
- calculate memory consumption at present
* - basic function of lazy_allocator, remaining test
* - modify LazyAllocator
* - modify InfiniTensor to fit LazyAllocator
* - add setDataBlob
- modify alignment
- fix GraphObj::dataMalloc
* - modified alignment value(64bytes -> 8bytes)
- fix LazyAllocator::getPtr()
- some dubug codes and commonts
- do alignment by chaning size instead of tailAddr
* - fix some problem
* - translate chinese comments to english
* - format codes
* - fix test
* - code format
* - modify codes as YdrMaser and bitzyz suggested
* - code format
* - modify codes as constroy suggested
* - codes format
* - modify alignment on cuda
* - code format
* - add test_lazy_allocator
- fix tests where not add input tensor into graph.tensors
- fix tests where init tensor's data before calling graph->dataMallocate()
* - code format
* - remove gpu runtime in test_lazy_allocator
* - fix test_lazy_allocator: remove cuda include
* - add test
* - code format
* - add ifdef for test of allocator
* - code format
* - fix test: remove unused ifdef
* - fix bang test
* - code format
* Merge branch 'master' into dcj/memory_allocator
* fix: fix cuda conv_fp16 run fail
* fix bang_runtime.cc and cuda_runtime.cc
* - update mkl code
* - fix codes for mkl
* - code format
* - remove unused commented codes
- add an empty line at the end of the blob.cc
---------
Co-authored-by: zhangyunze <z13785159769@163.com>
fix review
change Device::MKL to Device::INTELCPU
fix mkl linkage
fix errors according to merge from master
now can call mkl backend
fix softmax/flatten with axis from onnx.
modify README.md
fix memory refree
add env_lotus_intelcpu.sh
fix compile
merge from branch cpu_backend
fix something add gather
fix something
FIX: directory rename from "mkl" to "intelcpu"
ADD: use oneMKL dpcpp interface to implement matmul kernel.
ADD: add dpcpp as compiler for mkl, and fix warnings for clang compiling.
add dpcpp kernel for pow.
ADD: mkl kernel for pad.
ADD: slice mkl kernel.
ADD: reshape/flatten/identity mkl kernel.
ADD: split mkl kernel.
fix compile error
FIX: fix flattenObj with axis.
ADD reduce_mean mkl kernel.
Add concat mkl kernel.
bathNorm for mkl kernel.
sigmoid mkl kernel.
ADD：add mkl kernel for pooling
add more tests for softmax
Now softmax cuda kernel supports any axises.
mkl kernel for softmax
softmax
add axis to softmax operator
add mkl kernel for abs tanh
ADD: relu kernel for mkl
fix binary mkl primitives.
add mkl kernel for binary operators
fix compiler error
move stream to runtime
clang format
add MemoryFormat for tensorObj.
use post_ops for fused conv/deconv
Distinguish mkl op_timer from cuda op timer.
add act optype to conv and deconv
add operator timer
add mkl kernel for convTransposed
minor fix for group conv
do not use cblas_sgemm_batch
CpuRuntimeObj->NativeCpuRuntimeObj
add matmul op for mkl
* move memory format transformation to TensorObj
clang format
add MemoryFormat for tensorObj.
use post_ops for fused conv/deconv
Distinguish mkl op_timer from cuda op timer.
add act optype to conv and deconv
add operator timer
add mkl kernel for convTransposed
minor fix for group conv
do not use cblas_sgemm_batch
CpuRuntimeObj->NativeCpuRuntimeObj
add matmul op for mkl
* fix: fix bugs when rebasing from master
fix: fix bugs when rebasing from master
* fix: update api after rebasing
* fix: fix format; fix onnx import
* fix: fix clang-format
* [fix] fix conv_transpose test
* [fix] use stronger test case for transposed conv
* [fix] remove tensor memory format; fix mkl transpose conv
* [fix] add FIXME tag for op_timer python api
---------
Co-authored-by: whjthu <haojie0429@gmail.com>
* fix a little bug which found by new verison CMake
* add code for support BangC language kernel , just like Cuda kernel, not
library
* add bangc kernel
* support BangC kernel
* add code for support BangC kernel
* support bangc kernel
* fix some code from reviewer
* fix code of template fumction
* add code for support bangc kernel
* fix bangc format
Co-authored-by: wanghailu <wanghailu@qiyuanlab.com>
Co-authored-by: Haojie Wang <haojie0429@gmail.com>
* Add: interface for membound TVM kernel and test
* add getAnsorCode
* add evaluation, but link failed
* add evaluation of kernel, but link failed
* Fix: link libcuda and nvrtc
* add print
* Add: const for source of copy
* compile and evaluate the kernel
* add compute
* fix gen_ansor_op.py
* fix membound_TVM
* format and fix CMakeLists.txt
* fix memory leak
Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
Co-authored-by: huangshuhong <huangsh19@mails.tsinghua.edu.cn>
* add code for cambricon mlu, bang, cnnl
* add code for support cambricon mlu,cnnl,cnrt
* add code for support mlu
* add code for support cambricon cnnl
* add code for support mlu
* add code for mlu
* add code for mlu
`
* Update CMakeLists.txt
Co-authored-by: wanghailu <wanghailu@qiyuanlab.com>
Co-authored-by: zhengly123 <zhengly123@outlook.com>
* use protobuf for tensor data save,write,read, in chinese 序列化和反序列化
* add protobuf
* add code for tensor load & save from/to file
* add code for tensor laod & save
* add code for tensor load & save
* add code for tensor save & load
* add code for tensor save & load
* add code for save & load
* add code for load & save
* add code for tensor load & save
* add code for tensor save & load
Co-authored-by: wanghailu <wanghailu@qiyuanlab.com>
* Function tune and corresponding testcase.
*Add: Tune function in /src/kernel/cuda/conv.cc and corresponding testcase in test_conv.
*Fix: A little bug of perfRecord using in /src/core/runtime.cc.
* Tune part debug
*Add: recover the code, fixed the commit error.
*Add: some anotations in tune function
* clang formmat test
* Fix: mem leak in CUDA Runtime and Conv
* Fix: sync in conv and default sync in timeit
* Change the way to tune operator conv.
Timeit function cudNNUnfused -> Timeit function cudnnConvolutionForward.
* Change: merge the common part of cudnnunfused&tune into cudnndescriptoraccess
* clang test
* clang-format
* clang-format bash.
* Added operator G2BMM and corresponding testcase.
*Added files related to operator G2BMM creating&calling.
*Added custom_ops.cuh&custom_op.h.
* Add operator GBMML
* new version
* Fix: G2BMM and GBMM kernel bugs
* Added testcase of operator GBMML
* clang format
* Added cmake option REQUIRE_GCC9
* Delete redundent file
* Renamed class GBMML into GBMM
* clang format
* Reviewed.
* Added cudahostcompier option.
* Add: explicit CMAKE_CUDA_HOST_COMPILER
* Rename gbmm kernel
* Fix: nvcc warning in GBMM and G2BMM
Co-authored-by: wcz112 <wcz19@mails.tsinghua.edu.cn>
Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
Class "Cuda Runtime" fulfills function "tune" and adds corresponding testcase.
*Add: convCudnn::tune, convCudnn::cuDNNdescriptorAccess.
*Add: testcase tune.
*Fix: a brief bug in CPU Runtime.
* Fix: add warm-up and repetition in timing
* Add: CUDA runtime and float support
* Refactor: Cuda and Cpu runtimes inherit Runtime
* Add: environment script for Lotus
* Add: Lotus build instructions
* Update README.md
Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
Hardy
Derui Yang