search

SmileiPIC / Smilei

Particle-in-cell code for plasma simulation
https://smileipic.github.io/Smilei
344 stars 120 forks source link

GPU Quadro M5000 Installation Failed #744

Closed W-Wuxian closed 1 month ago

W-Wuxian commented 2 months ago

Hi, please review the attached makelog2.log as a result of the following configuration:

conda activate smilei_env
module load nvhpc-hpcx-cuda12/ phdf5/nvhpc/
export GPU_COMPILER=nvcc
export SMILEICXX=nvc++
export BUILD_DIR=/opt/apps/libsoft/smilei/nvhpc/5.1
export PYTHONEXE=/opt/apps/miniconda3/env/root/envs/smilei_gpu_env/bin/python
export HDF5_ROOT_DIR=/opt/apps/fileformat/phdf5/nvhpc/1.14.3

export CXXFLAGS="-O3 -march=cascadelake -mtune=cascadelake -noswitcherror -w -v -tp=cascadelake -gpu=cc50 -acc=gpu -std=c++14  -lcurand -cudalib=curand -Minfo=accel -D__GCC_ATOMIC_TEST_AND_SET_TRUEVAL=1"
export GPU_COMPILER_FLAGS="-O3 --std c++14 -arch=sm_50 -v --expt-relaxed-constexpr"
export LDFLAGS="-acc=gpu -gpu=cc50 -v -std=c++14 -cudalib=curand -lcudart -lcurand -lacccuda"
export SMILEICXX_DEPS=g++

make -j 12 config="verbose noopenmp gpu_nvidia" 2>&1 | tee makelog2.log

Originally posted by @W-Wuxian in https://github.com/SmileiPIC/Smilei/issues/742#issuecomment-2345641109

charlesprouveur commented 1 month ago

As said in https://forums.developer.nvidia.com/t/failed-installation-of-smilei-gpu-nvidia-quadro-m5000/306953 This problem is nvhpc 24.7 specific, 24.5 works fine.

W-Wuxian commented 1 month ago

As said in https://forums.developer.nvidia.com/t/failed-installation-of-smilei-gpu-nvidia-quadro-m5000/306953 This problem is nvhpc 24.7 specific, 24.5 works fine.

Hi it is actually my nvidia ticket that you point me out, but I still get errors, please review the following ticket:

the "-cuda" option actually fix previous errors msg, but i got new one related to constexpr see the attached MAKELOG.log file. MAKELOG.log|attachment (130.2 KB)

to reproduce the error, here is the step by step:

conda activate smilei_env
module load nvhpc-hpcx-cuda12/ phdf5/nvhpc/
source NVIDIA_SMILEI_ENV
make -j12 machine="machine_file" config="verbose gpu_nvidia" 2>&1 | tee MAKELOGlog

I created a NVIDIA_SMILEI_ENV.sh:

export BUILD_DIR=/opt/apps/libsoft/smilei/nvhpc/5.1

export GPU_COMPILER=nvcc
export SMILEICXX=nvc++

export PYTHONEXE=/opt/apps/miniconda3/env/root/envs/smilei_gpu_env/bin/python
export HDF5_ROOT_DIR=/opt/apps/fileformat/phdf5/nvhpc/1.14.3

and used this mahine_file:

SMILEICXX_DEPS = g++
# Options pour nvcxx (Compilateur C++ de NVHP)
CXXFLAGS += -w -v -cuda -noswitcherror
CXXFLAGS += -tp=cascadelake -gpu=cc50 -acc=gpu -std=c++14  -lcurand -cudalib=curand
CXXFLAGS += -Minfo=accel # what is offloaded/copied
CXXFLAGS += -D__GCC_ATOMIC_TEST_AND_SET_TRUEVAL=1

# Options pour NVCC (Compilateur CUDA)
GPU_COMPILER_FLAGS += -O3 --std c++14 -arch=sm_50 -v # --compiler-bindir="mpicc"
GPU_COMPILER_FLAGS += --expt-relaxed-constexpr

LDFLAGS += -acc=gpu -gpu=cc50 -v -std=c++14 -cudalib=curand -lcudart -lcurand -lacccuda
charlesprouveur commented 1 month ago

First things first:

-Sorry if there was a misunderstanding, I knew it was you since it was the exact same issue. I was being tongue in cheek. I found it by chance looking at the nvidia forum today.

Now if you would like, please open a conversation or we can continue this discussion on element

charlesprouveur commented 1 month ago

Your attachment is missing (MAKELOG.log)

W-Wuxian commented 1 month ago
  • but also internally to add on top of the support we provide through element. So we like to provide support and intend to continue doing so but consider this is a lot of work for a small team. Please understand that support might not be provided as fast as you would hope for as we all have a lot of work on our

I would like to apologize for my toxic behavior, and thank you and your team for your patience and teaching. I was only focused on myself without thinking about all your constraints. I repost the error log here issue745.