srun: Job time limit was unset; set to partition default of 60 minutes srun: ################################################################################ srun: # Please note that the oasis compute nodes have aarch64 architecture CPUs. # srun: # All submission nodes and all other compute nodes have x86_64 architecture # srun: # CPUs. Programs, environments, or other software that was built on x86_64 # srun: # nodes may need to be rebuilt to properly execute on these nodes. # srun: ################################################################################ srun: job 3394986 queued and waiting for resources srun: job 3394986 has been allocated resources /nfshomes/vut/ampere_research/pytorch/spmv.py:20: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.) ).to_sparse_csr().type(torch.float) tensor(crow_indices=tensor([ 0, 1, 71, ..., 367660, 367661, 367662]), col_indices=tensor([ 1, 0, 2, ..., 36690, 36689, 8203]), values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36692, 36692), nnz=367662, layout=torch.sparse_csr) tensor([0.9906, 0.9401, 0.5661, ..., 0.4491, 0.7550, 0.2452]) Matrix: email-Enron Shape: torch.Size([36692, 36692]) NNZ: 367662 Density: 0.0002730901120626302 Time: 12.80848503112793 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/email-Enron.mtx 1000': 48.76 msec task-clock:u # 0.003 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 3,281 page-faults:u # 67.289 K/sec 45,495,589 cycles:u # 0.933 GHz (57.79%) 79,104,832 instructions:u # 1.74 insn per cycle (81.70%) branches:u 372,161 branch-misses:u 32,089,348 L1-dcache-loads:u # 658.113 M/sec 467,576 L1-dcache-load-misses:u # 1.46% of all L1-dcache accesses LLC-loads:u LLC-load-misses:u 30,688,995 L1-icache-loads:u # 629.393 M/sec 289,698 L1-icache-load-misses:u # 0.94% of all L1-icache accesses 47,006,355 dTLB-loads:u # 964.042 M/sec (22.12%) dTLB-load-misses:u (0.00%) iTLB-loads:u (0.00%) iTLB-load-misses:u (0.00%) 16.331438990 seconds time elapsed 76.869141000 seconds user 999.179638000 seconds sys /nfshomes/vut/ampere_research/pytorch/spmv.py:20: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.) ).to_sparse_csr().type(torch.float) tensor(crow_indices=tensor([ 0, 1, 71, ..., 367660, 367661, 367662]), col_indices=tensor([ 1, 0, 2, ..., 36690, 36689, 8203]), values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36692, 36692), nnz=367662, layout=torch.sparse_csr) tensor([0.7565, 0.5273, 0.1038, ..., 0.9432, 0.1309, 0.5542]) Matrix: email-Enron Shape: torch.Size([36692, 36692]) NNZ: 367662 Density: 0.0002730901120626302 Time: 26.91536283493042 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/email-Enron.mtx 1000': 335,574 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio 20,121,415 BR_RETIRED:u 30.559245388 seconds time elapsed 126.799314000 seconds user 2081.777635000 seconds sys /nfshomes/vut/ampere_research/pytorch/spmv.py:20: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.) ).to_sparse_csr().type(torch.float) tensor(crow_indices=tensor([ 0, 1, 71, ..., 367660, 367661, 367662]), col_indices=tensor([ 1, 0, 2, ..., 36690, 36689, 8203]), values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36692, 36692), nnz=367662, layout=torch.sparse_csr) tensor([0.2321, 0.0702, 0.2538, ..., 0.6254, 0.6308, 0.5317]) Matrix: email-Enron Shape: torch.Size([36692, 36692]) NNZ: 367662 Density: 0.0002730901120626302 Time: 14.841739892959595 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/email-Enron.mtx 1000': 26,011,880 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio 5,842 ITLB_WALK:u 16,448 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio 35,000,292 L1D_TLB:u 18.443612527 seconds time elapsed 80.694133000 seconds user 1159.740575000 seconds sys /nfshomes/vut/ampere_research/pytorch/spmv.py:20: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.) ).to_sparse_csr().type(torch.float) tensor(crow_indices=tensor([ 0, 1, 71, ..., 367660, 367661, 367662]), col_indices=tensor([ 1, 0, 2, ..., 36690, 36689, 8203]), values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36692, 36692), nnz=367662, layout=torch.sparse_csr) tensor([0.7091, 0.9447, 0.0959, ..., 0.0090, 0.7012, 0.6025]) Matrix: email-Enron Shape: torch.Size([36692, 36692]) NNZ: 367662 Density: 0.0002730901120626302 Time: 10.863199234008789 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/email-Enron.mtx 1000': 32,193,112 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio 310,304 L1I_CACHE_REFILL:u 495,806 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio 33,829,187 L1D_CACHE:u 14.426841778 seconds time elapsed 70.728541000 seconds user 853.184507000 seconds sys /nfshomes/vut/ampere_research/pytorch/spmv.py:20: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.) ).to_sparse_csr().type(torch.float) tensor(crow_indices=tensor([ 0, 1, 71, ..., 367660, 367661, 367662]), col_indices=tensor([ 1, 0, 2, ..., 36690, 36689, 8203]), values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36692, 36692), nnz=367662, layout=torch.sparse_csr) tensor([0.8267, 0.6185, 0.8015, ..., 0.8593, 0.4881, 0.8599]) Matrix: email-Enron Shape: torch.Size([36692, 36692]) NNZ: 367662 Density: 0.0002730901120626302 Time: 12.076026678085327 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/email-Enron.mtx 1000': 546,628 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio 570,044 LL_CACHE_RD:u 196,794 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio 24,071 L2D_TLB_REFILL:u 316,028 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio 1,836,018 L2D_CACHE:u 15.581045199 seconds time elapsed 77.345591000 seconds user 942.987439000 seconds sys