Cyclops Tensor Framework
parallel arithmetic on multidimensional arrays

▼Examples  
algebraic_multigrid  Benchmark for smoothed algebraic multgrid 
Ao_mo_transf  Transformation between atomic and molecular orbitals 
apsp  Allpairs shortestpaths via path doubling and Tiskin's augmented path doubling 
bitonic_sort  Bitonic_sort sort iterative method using gemv and spmv 
block_sparse  Allpairs shortestpaths via path doubling and Tiskin's augmented path doubling 
betweenness centrality  Betweenness centrality computation 
CCSD  A Coupled Cluster Singles and Doubles contraction code extracted from Aquarius 
checkpoint  Tests read and write dense data to file functionality 
sparse_checkpoint  Tests read and write dense data to file functionality 
DFT_3D  3D Discrete Fourier Transform by tensor contractions 
fft  FFT iterative method using gemv and spmv 
force_integration  Tests custom elementwise transform by doing force integration 
force_integration_sparse  Tests custom elementwise transform on sparse tensors by doing force integration 
jacobi  Jacobi iterative method using gemv and spmv 
Matrix multiplication  Multiplication of two matrices with userdefined attributes of symmetry and sparsity 
mis  Code for maximal independent set 
mis2  Code for maximal 2independent set 
neural  Neural Network 
particle_interaction  Tests custom elementwise functions by computing interactions between particles and integrating 
recursive_matmul  Performs recursive parallel matrix multiplication using the slice interface to extract blocks 
scan  Scan iterative method using gemv and spmv 
sparse_mp3  Thirdorder MollerPlesset petrubation theory (MP3) with sparse integrals. Equations adapted from those in Aquarius (credit to Devin Matthews) 
sparse_permuted_slice  Randomly permuted block write of symmetric matrices from matrix on COMM_SELF to symmetric matrix on COMM_WORLD 
spectral  Spectral element methods test/benchmark 
spmv  Multiplication of a random square sparse matrix by a vector 
sssp  Singlesource shortestpaths via the BellmanFord algorithm 
Strassen's algorithm  Strassen's algorithm using the slice interface to extract blocks 
trace  Tests trace over diagonal of Matrices 
informatics  Highorder nonsymmetric contractions 
▼Tests  Matrix multiplication 
qr  QR factorization of CTF matrices 
svd  SVD factorization of CTF matrices 
bivar_function  Tests custom elementwise functions by implementing division elementwise on 4D tensors 
bivar_transform  Tests custom elementwise transforms by implementing division elementwise on 4D tensors 
DFT  Discrete Fourier Transform by matrix multiplication 
diag_ctr  Summation along tensor diagonals 
diag_sym  Summation along tensor diagonals 
endomorphism  Tests custom elementwise functions by implementing division elementwise on 4D tensors 
endomorphism_cust  Tests custom elementwise functions by implementing division elementwise on 4D tensors 
endomorphism_cust_sp  Tests cust_spom elementwise functions by implementing division elementwise on 4D tensors 
GEMM_4D  Folded matrix multiplication on 4D tensors 
permute_multiworld  Tests permute function between different worlds 
readall_test  Summation along tensor diagonals 
readwrite_test  Tests how writes to diagonals are handled for various tensors 
reduce_bcast  Summation along tensor diagonals 
repack  Tests contraction of a symmetric index group with a nonsymmetric one 
scalar  Basic functionality test for CTF::Scalar<> type and tensors with a zero edge length 
speye  Sparse identity matrix test 
sptensor_sum  Summation of sparse tensors 
subworld_gemm  Performs recursive parallel matrix multiplication using the slice interface to extract blocks 
sy_times_ns  Tests contraction of a symmetric index group with a nonsymmetric one 
univar_function  Tests custom elementwise functions by implementing division elementwise on 4D tensors 
weigh_4D  Tests custom elementwise functions by implementing division elementwise on 4D tensors 
CCSDT_T3_to_T2  A symmetric contraction from CCSDT compared with the explicitly permuted nonsymmetric form 
Dynamic scheduler  
▼Studies  
Symmetry preserving algorithm for AS<SYAS  A clever way to multiply symmetric tensors 
Symmetry preserving algorithm for SY<ASAS  A clever way to multiply symmetric tensors 
fast_sym  A clever way to multiply symmetric matrices 
fast_sym_4D  A clever way to multiply symmetric matrices of nonsymmetric matricers 
fast_tensor_ctr  A clever way to multiply symmetric tensors 
▼Benchmarks  
Bench_contractions  Benchmarks arbitrary NS contraction 
Bench_nosym_transp  Benchmarks the nonsymemtric transpose kernel 
Bench_redistributions  Benchmarks arbitrary NS redistribution 
Model_trainer  Executes a set of different contractions on different processor counts to train model parameters 
Nested distributed contraction and summation routines  
CTF Tensor  
CTF functions  Userdefined function interface 
Algebraic Structures  
Tensor expression compiler  
Partition/Decomposition interface  
Timing and cost measurement  
CTF World interface 