164 lines
9.8 KiB
Plaintext
164 lines
9.8 KiB
Plaintext
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 3394981 queued and waiting for resources
|
|
srun: job 3394981 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, 29, 124, ..., 545669, 545669,
|
|
545671]),
|
|
col_indices=tensor([ 1, 2, 3, ..., 81869, 81699, 81863]),
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(81871, 81871),
|
|
nnz=545671, layout=torch.sparse_csr)
|
|
tensor([0.6780, 0.5234, 0.1205, ..., 0.2995, 0.6275, 0.1399])
|
|
Matrix: soc-sign-Slashdot090216
|
|
Shape: torch.Size([81871, 81871])
|
|
NNZ: 545671
|
|
Density: 8.140867447881048e-05
|
|
Time: 30.653191089630127 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-Slashdot090216.mtx 1000':
|
|
|
|
67.66 msec task-clock:u # 0.002 CPUs utilized
|
|
0 context-switches:u # 0.000 /sec
|
|
0 cpu-migrations:u # 0.000 /sec
|
|
3,317 page-faults:u # 49.022 K/sec
|
|
41,915,850 cycles:u # 0.619 GHz (57.88%)
|
|
84,471,787 instructions:u # 2.02 insn per cycle (88.19%)
|
|
<not supported> branches:u
|
|
375,016 branch-misses:u
|
|
32,438,527 L1-dcache-loads:u # 479.407 M/sec
|
|
499,618 L1-dcache-load-misses:u # 1.54% of all L1-dcache accesses
|
|
<not supported> LLC-loads:u
|
|
<not supported> LLC-load-misses:u
|
|
30,998,693 L1-icache-loads:u # 458.127 M/sec
|
|
306,445 L1-icache-load-misses:u # 0.99% of all L1-icache accesses
|
|
34,294,934 dTLB-loads:u # 506.842 M/sec (18.86%)
|
|
<not counted> dTLB-load-misses:u (0.00%)
|
|
<not counted> iTLB-loads:u (0.00%)
|
|
<not counted> iTLB-load-misses:u (0.00%)
|
|
|
|
34.340632995 seconds time elapsed
|
|
|
|
149.743244000 seconds user
|
|
2355.852109000 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, 29, 124, ..., 545669, 545669,
|
|
545671]),
|
|
col_indices=tensor([ 1, 2, 3, ..., 81869, 81699, 81863]),
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(81871, 81871),
|
|
nnz=545671, layout=torch.sparse_csr)
|
|
tensor([0.9875, 0.2031, 0.7260, ..., 0.5908, 0.1575, 0.7971])
|
|
Matrix: soc-sign-Slashdot090216
|
|
Shape: torch.Size([81871, 81871])
|
|
NNZ: 545671
|
|
Density: 8.140867447881048e-05
|
|
Time: 13.671181440353394 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-Slashdot090216.mtx 1000':
|
|
|
|
344,452 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio
|
|
20,610,765 BR_RETIRED:u
|
|
|
|
17.331425967 seconds time elapsed
|
|
|
|
83.136180000 seconds user
|
|
1069.027469000 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, 29, 124, ..., 545669, 545669,
|
|
545671]),
|
|
col_indices=tensor([ 1, 2, 3, ..., 81869, 81699, 81863]),
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(81871, 81871),
|
|
nnz=545671, layout=torch.sparse_csr)
|
|
tensor([0.2046, 0.3645, 0.7960, ..., 0.6490, 0.4098, 0.5342])
|
|
Matrix: soc-sign-Slashdot090216
|
|
Shape: torch.Size([81871, 81871])
|
|
NNZ: 545671
|
|
Density: 8.140867447881048e-05
|
|
Time: 19.569235801696777 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-Slashdot090216.mtx 1000':
|
|
|
|
27,276,117 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio
|
|
6,358 ITLB_WALK:u
|
|
17,361 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio
|
|
36,565,837 L1D_TLB:u
|
|
|
|
23.323243037 seconds time elapsed
|
|
|
|
108.830923000 seconds user
|
|
1521.834565000 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, 29, 124, ..., 545669, 545669,
|
|
545671]),
|
|
col_indices=tensor([ 1, 2, 3, ..., 81869, 81699, 81863]),
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(81871, 81871),
|
|
nnz=545671, layout=torch.sparse_csr)
|
|
tensor([0.4164, 0.2188, 0.5460, ..., 0.1057, 0.5277, 0.0624])
|
|
Matrix: soc-sign-Slashdot090216
|
|
Shape: torch.Size([81871, 81871])
|
|
NNZ: 545671
|
|
Density: 8.140867447881048e-05
|
|
Time: 26.337355375289917 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-Slashdot090216.mtx 1000':
|
|
|
|
32,022,662 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio
|
|
293,044 L1I_CACHE_REFILL:u
|
|
458,939 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio
|
|
33,505,164 L1D_CACHE:u
|
|
|
|
30.017812847 seconds time elapsed
|
|
|
|
131.976276000 seconds user
|
|
2029.636174000 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, 29, 124, ..., 545669, 545669,
|
|
545671]),
|
|
col_indices=tensor([ 1, 2, 3, ..., 81869, 81699, 81863]),
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(81871, 81871),
|
|
nnz=545671, layout=torch.sparse_csr)
|
|
tensor([0.7679, 0.9196, 0.3474, ..., 0.5624, 0.0163, 0.8596])
|
|
Matrix: soc-sign-Slashdot090216
|
|
Shape: torch.Size([81871, 81871])
|
|
NNZ: 545671
|
|
Density: 8.140867447881048e-05
|
|
Time: 29.926054000854492 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/soc-sign-Slashdot090216.mtx 1000':
|
|
|
|
553,814 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio
|
|
567,372 LL_CACHE_RD:u
|
|
199,301 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio
|
|
25,193 L2D_TLB_REFILL:u
|
|
313,278 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio
|
|
1,796,299 L2D_CACHE:u
|
|
|
|
33.553779692 seconds time elapsed
|
|
|
|
154.498461000 seconds user
|
|
2293.574463000 seconds sys
|
|
|
|
|
|
|