164 lines
9.7 KiB
Plaintext
164 lines
9.7 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 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%)
|
|
<not supported> 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
|
|
<not supported> LLC-loads:u
|
|
<not supported> 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%)
|
|
<not counted> dTLB-load-misses:u (0.00%)
|
|
<not counted> iTLB-loads:u (0.00%)
|
|
<not counted> 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
|
|
|
|
|
|
|