So trying to compile graphnn with oneTBB (ie using #include "oneapi/tbb.h" instead of "tbb/tbb.h") I get the error with the code as-is (since I didn't write the original:
src/tensor/cpu_row_sparse_tensor.cpp:298:8: error: « mutex » is not a member of « tbb »
tbb::mutex ll;
^~~~~
It will compile correctly if I both of these lines:
#define __TBB_PREVIEW_MUTEXES 1
[...]
#include <tbb/mutex.h>
but then when trying to compile the MNIST example, I get a very long list of errors for both cpu_row_dense_tensor and cpu_row_sparse_tensor:
../../build/lib/libgnn.a(cpu_dense_tensor.o) : In the function « tbb::detail::d1::task_arena_function<tbb::detail::d1::graph::wait_for_all()::{lambda()#1}::operator()() const::{lambda()#1}, void>::operator()() const » :
cpu_dense_tensor.cpp:(.text._ZNK3tbb6detail2d119task_arena_functionIZZNS1_5graph12wait_for_allEvENKUlvE_clEvEUlvE_vEclEv[_ZNK3tbb6detail2d119task_arena_functionIZZNS1_5graph12wait_for_allEvENKUlvE_clEvEUlvE_vEclEv]+0x14) : undefined reference to « tbb::detail::r1::wait(tbb::detail::d1::wait_context&, tbb::detail::d1::task_group_context&) »
../../build/lib/libgnn.a(cpu_dense_tensor.o) : In the function « tbb::detail::d1::graph::~graph() » :
cpu_dense_tensor.cpp:(.text._ZN3tbb6detail2d15graphD2Ev[_ZN3tbb6detail2d15graphD5Ev]+0x5b) : undefined reference to « tbb::detail::r1::initialize(tbb::detail::d1::task_arena_base&) »
cpu_dense_tensor.cpp:(.text._ZN3tbb6detail2d15graphD2Ev[_ZN3tbb6detail2d15graphD5Ev]+0x9a) : undefined reference to « tbb::detail::r1::execute(tbb::detail::d1::task_arena_base&, tbb::detail::d1::delegate_base&) »
cpu_dense_tensor.cpp:(.text._ZN3tbb6detail2d15graphD2Ev[_ZN3tbb6detail2d15graphD5Ev]+0xa3) : undefined reference to « tbb::detail::r1::is_group_execution_cancelled(tbb::detail::d1::task_group_context&) »
cpu_dense_tensor.cpp:(.text._ZN3tbb6detail2d15graphD2Ev[_ZN3tbb6detail2d15graphD5Ev]+0xb5) : undefined reference to « tbb::detail::r1::reset(tbb::detail::d1::task_group_context&) »
[...]
../../build/lib/libgnn.a(cpu_row_sparse_tensor.o) : In the function « gnn::TensorTemplate<gnn::CPU, gnn::ROW_SPARSE, float>::RowSparseCopy(gnn::TensorTemplate<gnn::CPU, gnn::DENSE, float>&) » :
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0xb9) : undefined reference to « tbb::detail::r1::initialize(tbb::detail::d1::task_group_context&) »
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0xd1) : undefined reference to « tbb::detail::r1::allocate(tbb::detail::d1::small_object_pool*&, unsigned long) »
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0x12b) : undefined reference to « tbb::detail::r1::max_concurrency(tbb::detail::d1::task_arena_base const*) »
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0x19d) : undefined reference to « tbb::detail::r1::execute_and_wait(tbb::detail::d1::task&, tbb::detail::d1::task_group_context&, tbb::detail::d1::wait_context&, tbb::detail::d1::task_group_context&) »
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0x1a5) : undefined reference to « tbb::detail::r1::destroy(tbb::detail::d1::task_group_context&) »
cpu_row_sparse_tensor.cpp:(.text._ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE[_ZN3gnn14TensorTemplateINS_3CPUENS_10ROW_SPARSEEfE13RowSparseCopyERNS0_IS1_NS_5DENSEEfEE]+0x1d8) : undefined reference to « tbb::detail::r1::destroy(tbb::detail::d1::task_group_context&) »
[...]
I can try using more defines and it seems to reduce the number of errors, but I don't think this is really the right way to be using oneTBB, since it's already odd all the features are disabeled.
If instead I replace oneTBB with regular TBB (from 2018) I recieve the same error unless I add the mutex.h file, but then I get the following error:
cpp
g++ -Wall -O3 -std=c++14 -I/local/java/cuda-11.2//include -I~/intel/oneapi/mkl/latest/include -I/usr/include/tbb -Iinclude -fPIC -DUSE_GPU -MMD -c -o build/objs/cxx/nn/relu.o src/nn/relu.cpp -lm -lmkl_rt -ltbb -L/local/java/cuda-11.2//lib64 -lcudart -lcublas -lcurand -lcusparse
In file included from /usr/include/tbb/mutex.h:32,
from src/tensor/cpu_row_sparse_tensor.cpp:12:
/usr/include/tbb/tbb_stddef.h: At the global level:
/usr/include/tbb/tbb_stddef.h:409:14: error: expected type-specifier before « split »
operator split() const { return split(); }
^~~~~
In file included from src/tensor/cpu_row_sparse_tensor.cpp:12:
/usr/include/tbb/mutex.h:231:1: error: expected constructor, destructor, or type conversion before « } » token
} // namespace tbb
^
I would prefer to use oneTBB, and I feel like I'm using it wrong, but if using regular TBB works better then I don't really care. Any hints as to what I'm doing wrong?
