p49270318
/
InfiniTensor
forked from jiuyuan/InfiniTensor
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
InfiniTensor/test/script/env_lotus.sh

27 lines
2.0 KiB
Bash
Raw Normal View History

Cpu backend2 (#77) 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
2023-04-17 12:15:23 +08:00
#!/bin/bash
cuDNN conv tuning (#16) * 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. * Chore: remove print and blank lines Co-authored-by: wcz112 <wcz19@mails.tsinghua.edu.cn> Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com>
2022-08-29 21:37:07 +08:00
. /home/spack/spack/share/spack/setup-env.sh
Cpu backend2 (#77) 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
2023-04-17 12:15:23 +08:00
if [ "$#" == 0 ] || [ "$1" == "cuda" ]
then
echo "Load CUDA environment."
spack load cuda@11.0.2 cudnn@8.0.3.33-11.0
export CUDAHOSTCXX=/home/spack/spack/opt/spack/linux-ubuntu22.04-broadwell/gcc-9.4.0/gcc-9.4.0-st36klijpsnquihiy463hmedsyhoc3g6/bin/gcc
elif [ "$1" == "intelcpu" ]
then
echo "Load INTELCPU environment."
spack load intel-oneapi-dnn@2022.1.0 intel-oneapi-mkl@2022.1.0 intel-oneapi-compilers@2022.1.0
# The default dnnl library is cpu_dpcpp_gpu_dpcpp which requires libsycl.so, after "spack load", and need to change to gomp explicitly.
export LD_LIBRARY_PATH=/home/spack/spack/opt/spack/linux-ubuntu22.04-broadwell/gcc-12.1.0/intel-oneapi-dnn-2022.1.0-7rs6ht57zozyxhxx6s2qlrqzmqknhgzx/dnnl/2022.1.0/cpu_gomp/lib/:$LD_LIBRARY_PATH
# flopen mkl libs will fail when used by python.
# Refering to "https://groups.google.com/g/kaldi-help/c/m3nyQke0HS0/m/4fj8gkSWAgAJ", it is recommended to use mkl_rt instead,
# but mkl_rt do not support dpc++ refered to https://www.intel.com/content/www/us/en/docs/onemkl/developer-guide-linux/2023-0/using-the-single-dynamic-library.html
# Preloading the missing libs will work, refered to https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/mkl-fails-to-load/m-p/1155538
export MKLLIB_PATH=/home/spack/spack/opt/spack/linux-ubuntu22.04-broadwell/gcc-12.1.0/intel-oneapi-mkl-2022.1.0-mf6te62fo6wxlo33jwwwgg5kljoagc6g/mkl/2022.1.0/
export LD_PRELOAD=$MKLLIB_PATH/lib/intel64/libmkl_def.so.2:$MKLLIB_PATH/lib/intel64/libmkl_avx2.so.2:$MKLLIB_PATH/lib/intel64/libmkl_core.so:$MKLLIB_PATH/lib/intel64/libmkl_intel_lp64.so:$MKLLIB_PATH/lib/intel64/libmkl_intel_thread.so:/home/spack/spack/opt/spack/linux-ubuntu22.04-broadwell/gcc-11.3.0/intel-oneapi-compilers-2022.1.0-qrq4a63scjip455bpxvl5ipgqbllwecj/compiler/2022.1.0/linux/compiler/lib/intel64_lin/libiomp5.so
else
echo "Bad option. Please enter 'cuda' or 'intelcpu'. CUDA will be loaded by default if nothing specified."
fi