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 3394154 queued and waiting for resources srun: job 3394154 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, 2, ..., 841371, 841371, 841372]), col_indices=tensor([ 1, 128552, 3, ..., 131824, 131826, 7714]), values=tensor([-1., -1., 1., ..., 1., 1., 1.]), size=(131828, 131828), nnz=841372, layout=torch.sparse_csr) tensor([0.5842, 0.3042, 0.7358, ..., 0.7882, 0.7596, 0.5895]) Shape: torch.Size([131828, 131828]) NNZ: 841372 Density: 4.841419648464106e-05 Time: 2.4407293796539307 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-epinions.mtx 100': 49.87 msec task-clock:u # 0.008 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 3,300 page-faults:u # 66.174 K/sec 51,935,476 cycles:u # 1.041 GHz (65.00%) 83,731,856 instructions:u # 1.61 insn per cycle (84.25%) branches:u 375,900 branch-misses:u 34,169,837 L1-dcache-loads:u # 685.197 M/sec 474,410 L1-dcache-load-misses:u # 1.39% of all L1-dcache accesses LLC-loads:u LLC-load-misses:u 32,443,215 L1-icache-loads:u # 650.574 M/sec 294,146 L1-icache-load-misses:u # 0.91% of all L1-icache accesses 63,709,518 dTLB-loads:u # 1.278 G/sec (16.44%) dTLB-load-misses:u (0.00%) iTLB-loads:u (0.00%) iTLB-load-misses:u (0.00%) 6.058862056 seconds time elapsed 29.101578000 seconds user 224.790489000 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, 2, ..., 841371, 841371, 841372]), col_indices=tensor([ 1, 128552, 3, ..., 131824, 131826, 7714]), values=tensor([-1., -1., 1., ..., 1., 1., 1.]), size=(131828, 131828), nnz=841372, layout=torch.sparse_csr) tensor([0.9696, 0.8139, 0.4858, ..., 0.2374, 0.1716, 0.9756]) Shape: torch.Size([131828, 131828]) NNZ: 841372 Density: 4.841419648464106e-05 Time: 2.0945546627044678 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-epinions.mtx 100': 326,464 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio 20,341,367 BR_RETIRED:u 5.525378890 seconds time elapsed 28.841740000 seconds user 199.678982000 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, 2, ..., 841371, 841371, 841372]), col_indices=tensor([ 1, 128552, 3, ..., 131824, 131826, 7714]), values=tensor([-1., -1., 1., ..., 1., 1., 1.]), size=(131828, 131828), nnz=841372, layout=torch.sparse_csr) tensor([0.3478, 0.0057, 0.8574, ..., 0.6409, 0.1876, 0.8429]) Shape: torch.Size([131828, 131828]) NNZ: 841372 Density: 4.841419648464106e-05 Time: 2.8504912853240967 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-epinions.mtx 100': 27,590,154 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio 6,210 ITLB_WALK:u 17,536 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio 36,763,243 L1D_TLB:u 6.425887143 seconds time elapsed 33.069094000 seconds user 256.667850000 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, 2, ..., 841371, 841371, 841372]), col_indices=tensor([ 1, 128552, 3, ..., 131824, 131826, 7714]), values=tensor([-1., -1., 1., ..., 1., 1., 1.]), size=(131828, 131828), nnz=841372, layout=torch.sparse_csr) tensor([0.5381, 0.6651, 0.4689, ..., 0.7251, 0.3759, 0.8516]) Shape: torch.Size([131828, 131828]) NNZ: 841372 Density: 4.841419648464106e-05 Time: 1.6941111087799072 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-epinions.mtx 100': 31,663,300 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio 289,727 L1I_CACHE_REFILL:u 462,864 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio 33,262,254 L1D_CACHE:u 5.304170809 seconds time elapsed 25.992245000 seconds user 173.752913000 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, 2, ..., 841371, 841371, 841372]), col_indices=tensor([ 1, 128552, 3, ..., 131824, 131826, 7714]), values=tensor([-1., -1., 1., ..., 1., 1., 1.]), size=(131828, 131828), nnz=841372, layout=torch.sparse_csr) tensor([0.4145, 0.8515, 0.7222, ..., 0.1386, 0.6641, 0.6662]) Shape: torch.Size([131828, 131828]) NNZ: 841372 Density: 4.841419648464106e-05 Time: 3.0850296020507812 seconds Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-epinions.mtx 100': 530,272 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio 551,373 LL_CACHE_RD:u 196,152 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio 23,542 L2D_TLB_REFILL:u 301,998 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio 1,732,662 L2D_CACHE:u 6.733517838 seconds time elapsed 34.030476000 seconds user 271.397968000 seconds sys