154 lines
9.4 KiB
Plaintext
154 lines
9.4 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 3394142 queued and waiting for resources
|
||
|
|
srun: job 3394142 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, 10, 10, ..., 88328, 88328, 88328]),
|
||
|
|
col_indices=tensor([ 1, 2, 3, ..., 36675, 36676, 36677]),
|
||
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36682, 36682),
|
||
|
|
nnz=88328, layout=torch.sparse_csr)
|
||
|
|
tensor([0.5867, 0.3729, 0.0718, ..., 0.5551, 0.6046, 0.6005])
|
||
|
|
Shape: torch.Size([36682, 36682])
|
||
|
|
NNZ: 88328
|
||
|
|
Density: 6.564359899804003e-05
|
||
|
|
Time: 0.3765556812286377 seconds
|
||
|
|
|
||
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/p2p-Gnutella30.mtx 100':
|
||
|
|
|
||
|
|
65.91 msec task-clock:u # 0.017 CPUs utilized
|
||
|
|
0 context-switches:u # 0.000 /sec
|
||
|
|
0 cpu-migrations:u # 0.000 /sec
|
||
|
|
3,247 page-faults:u # 49.267 K/sec
|
||
|
|
92,293,071 cycles:u # 1.400 GHz (58.72%)
|
||
|
|
76,208,632 instructions:u # 0.83 insn per cycle (75.47%)
|
||
|
|
<not supported> branches:u
|
||
|
|
336,620 branch-misses:u (89.96%)
|
||
|
|
33,256,017 L1-dcache-loads:u # 504.599 M/sec
|
||
|
|
479,188 L1-dcache-load-misses:u # 1.44% of all L1-dcache accesses
|
||
|
|
<not supported> LLC-loads:u
|
||
|
|
<not supported> LLC-load-misses:u
|
||
|
|
31,686,331 L1-icache-loads:u # 480.782 M/sec
|
||
|
|
297,521 L1-icache-load-misses:u # 0.94% of all L1-icache accesses
|
||
|
|
55,295,804 dTLB-loads:u # 839.012 M/sec (27.47%)
|
||
|
|
103,616 dTLB-load-misses:u # 0.19% of all dTLB cache accesses (20.17%)
|
||
|
|
<not counted> iTLB-loads:u (0.00%)
|
||
|
|
<not counted> iTLB-load-misses:u (0.00%)
|
||
|
|
|
||
|
|
3.803094533 seconds time elapsed
|
||
|
|
|
||
|
|
16.585763000 seconds user
|
||
|
|
62.703127000 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, 10, 10, ..., 88328, 88328, 88328]),
|
||
|
|
col_indices=tensor([ 1, 2, 3, ..., 36675, 36676, 36677]),
|
||
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36682, 36682),
|
||
|
|
nnz=88328, layout=torch.sparse_csr)
|
||
|
|
tensor([0.2027, 0.2128, 0.5093, ..., 0.8069, 0.6413, 0.1136])
|
||
|
|
Shape: torch.Size([36682, 36682])
|
||
|
|
NNZ: 88328
|
||
|
|
Density: 6.564359899804003e-05
|
||
|
|
Time: 0.2942969799041748 seconds
|
||
|
|
|
||
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/p2p-Gnutella30.mtx 100':
|
||
|
|
|
||
|
|
320,083 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio
|
||
|
|
19,285,106 BR_RETIRED:u
|
||
|
|
|
||
|
|
3.763535833 seconds time elapsed
|
||
|
|
|
||
|
|
16.476022000 seconds user
|
||
|
|
55.208213000 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, 10, 10, ..., 88328, 88328, 88328]),
|
||
|
|
col_indices=tensor([ 1, 2, 3, ..., 36675, 36676, 36677]),
|
||
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36682, 36682),
|
||
|
|
nnz=88328, layout=torch.sparse_csr)
|
||
|
|
tensor([0.5930, 0.8044, 0.8115, ..., 0.6366, 0.1026, 0.6914])
|
||
|
|
Shape: torch.Size([36682, 36682])
|
||
|
|
NNZ: 88328
|
||
|
|
Density: 6.564359899804003e-05
|
||
|
|
Time: 0.2431955337524414 seconds
|
||
|
|
|
||
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/p2p-Gnutella30.mtx 100':
|
||
|
|
|
||
|
|
26,853,940 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio
|
||
|
|
6,728 ITLB_WALK:u
|
||
|
|
13,955 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio
|
||
|
|
37,111,059 L1D_TLB:u
|
||
|
|
|
||
|
|
3.752433570 seconds time elapsed
|
||
|
|
|
||
|
|
16.433982000 seconds user
|
||
|
|
53.207908000 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, 10, 10, ..., 88328, 88328, 88328]),
|
||
|
|
col_indices=tensor([ 1, 2, 3, ..., 36675, 36676, 36677]),
|
||
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36682, 36682),
|
||
|
|
nnz=88328, layout=torch.sparse_csr)
|
||
|
|
tensor([0.9666, 0.8206, 0.6252, ..., 0.5180, 0.8170, 0.7406])
|
||
|
|
Shape: torch.Size([36682, 36682])
|
||
|
|
NNZ: 88328
|
||
|
|
Density: 6.564359899804003e-05
|
||
|
|
Time: 0.15313339233398438 seconds
|
||
|
|
|
||
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/p2p-Gnutella30.mtx 100':
|
||
|
|
|
||
|
|
32,554,796 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio
|
||
|
|
298,729 L1I_CACHE_REFILL:u
|
||
|
|
473,779 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio
|
||
|
|
34,117,102 L1D_CACHE:u
|
||
|
|
|
||
|
|
3.595579651 seconds time elapsed
|
||
|
|
|
||
|
|
15.817851000 seconds user
|
||
|
|
44.491315000 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, 10, 10, ..., 88328, 88328, 88328]),
|
||
|
|
col_indices=tensor([ 1, 2, 3, ..., 36675, 36676, 36677]),
|
||
|
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(36682, 36682),
|
||
|
|
nnz=88328, layout=torch.sparse_csr)
|
||
|
|
tensor([0.9800, 0.9021, 0.5677, ..., 0.3869, 0.2468, 0.3286])
|
||
|
|
Shape: torch.Size([36682, 36682])
|
||
|
|
NNZ: 88328
|
||
|
|
Density: 6.564359899804003e-05
|
||
|
|
Time: 0.2539215087890625 seconds
|
||
|
|
|
||
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/p2p-Gnutella30.mtx 100':
|
||
|
|
|
||
|
|
535,040 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio
|
||
|
|
547,502 LL_CACHE_RD:u
|
||
|
|
179,876 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio
|
||
|
|
21,809 L2D_TLB_REFILL:u
|
||
|
|
298,620 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio
|
||
|
|
1,722,959 L2D_CACHE:u
|
||
|
|
|
||
|
|
3.549060962 seconds time elapsed
|
||
|
|
|
||
|
|
16.570077000 seconds user
|
||
|
|
52.238012000 seconds sys
|
||
|
|
|
||
|
|
|
||
|
|
|