174 lines
10 KiB
Plaintext
174 lines
10 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 3394982 queued and waiting for resources
|
|
srun: job 3394982 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, ..., 766390, 766394,
|
|
766396]),
|
|
col_indices=tensor([ 0, 1, 2, ..., 116833, 89,
|
|
116834]),
|
|
values=tensor([-1.0000e+00, -1.0000e+00, -1.0000e+00, ...,
|
|
1.0331e+01, -1.0000e-03, 1.0000e-03]),
|
|
size=(116835, 116835), nnz=766396, layout=torch.sparse_csr)
|
|
tensor([0.0986, 0.6504, 0.0132, ..., 0.6525, 0.3337, 0.7557])
|
|
Matrix: dc2
|
|
Shape: torch.Size([116835, 116835])
|
|
NNZ: 766396
|
|
Density: 5.614451099680581e-05
|
|
Time: 18.46260714530945 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/dc2.mtx 1000':
|
|
|
|
58.45 msec task-clock:u # 0.003 CPUs utilized
|
|
0 context-switches:u # 0.000 /sec
|
|
0 cpu-migrations:u # 0.000 /sec
|
|
3,471 page-faults:u # 59.382 K/sec
|
|
76,691,414 cycles:u # 1.312 GHz (41.20%)
|
|
89,547,095 instructions:u # 1.17 insn per cycle (73.16%)
|
|
<not supported> branches:u
|
|
382,362 branch-misses:u (96.21%)
|
|
33,271,433 L1-dcache-loads:u # 569.211 M/sec
|
|
488,730 L1-dcache-load-misses:u # 1.47% of all L1-dcache accesses
|
|
<not supported> LLC-loads:u
|
|
<not supported> LLC-load-misses:u
|
|
31,926,596 L1-icache-loads:u # 546.204 M/sec
|
|
304,792 L1-icache-load-misses:u # 0.95% of all L1-icache accesses
|
|
36,392,791 dTLB-loads:u # 622.612 M/sec (31.21%)
|
|
0 dTLB-load-misses:u (5.35%)
|
|
<not counted> iTLB-loads:u (0.00%)
|
|
<not counted> iTLB-load-misses:u (0.00%)
|
|
|
|
22.126601025 seconds time elapsed
|
|
|
|
103.642372000 seconds user
|
|
1434.131491000 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, ..., 766390, 766394,
|
|
766396]),
|
|
col_indices=tensor([ 0, 1, 2, ..., 116833, 89,
|
|
116834]),
|
|
values=tensor([-1.0000e+00, -1.0000e+00, -1.0000e+00, ...,
|
|
1.0331e+01, -1.0000e-03, 1.0000e-03]),
|
|
size=(116835, 116835), nnz=766396, layout=torch.sparse_csr)
|
|
tensor([0.5605, 0.9374, 0.4444, ..., 0.5937, 0.3099, 0.2252])
|
|
Matrix: dc2
|
|
Shape: torch.Size([116835, 116835])
|
|
NNZ: 766396
|
|
Density: 5.614451099680581e-05
|
|
Time: 13.607120752334595 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/dc2.mtx 1000':
|
|
|
|
329,725 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio
|
|
19,946,857 BR_RETIRED:u
|
|
|
|
17.131143957 seconds time elapsed
|
|
|
|
96.945305000 seconds user
|
|
1045.242697000 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, ..., 766390, 766394,
|
|
766396]),
|
|
col_indices=tensor([ 0, 1, 2, ..., 116833, 89,
|
|
116834]),
|
|
values=tensor([-1.0000e+00, -1.0000e+00, -1.0000e+00, ...,
|
|
1.0331e+01, -1.0000e-03, 1.0000e-03]),
|
|
size=(116835, 116835), nnz=766396, layout=torch.sparse_csr)
|
|
tensor([0.8954, 0.9777, 0.8042, ..., 0.2069, 0.7063, 0.8479])
|
|
Matrix: dc2
|
|
Shape: torch.Size([116835, 116835])
|
|
NNZ: 766396
|
|
Density: 5.614451099680581e-05
|
|
Time: 17.22396969795227 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/dc2.mtx 1000':
|
|
|
|
27,648,951 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio
|
|
6,857 ITLB_WALK:u
|
|
18,047 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio
|
|
37,225,736 L1D_TLB:u
|
|
|
|
20.911480243 seconds time elapsed
|
|
|
|
107.392462000 seconds user
|
|
1329.272154000 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, ..., 766390, 766394,
|
|
766396]),
|
|
col_indices=tensor([ 0, 1, 2, ..., 116833, 89,
|
|
116834]),
|
|
values=tensor([-1.0000e+00, -1.0000e+00, -1.0000e+00, ...,
|
|
1.0331e+01, -1.0000e-03, 1.0000e-03]),
|
|
size=(116835, 116835), nnz=766396, layout=torch.sparse_csr)
|
|
tensor([0.9293, 0.9606, 0.8914, ..., 0.2407, 0.2843, 0.5174])
|
|
Matrix: dc2
|
|
Shape: torch.Size([116835, 116835])
|
|
NNZ: 766396
|
|
Density: 5.614451099680581e-05
|
|
Time: 13.233965873718262 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/dc2.mtx 1000':
|
|
|
|
32,434,686 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio
|
|
293,072 L1I_CACHE_REFILL:u
|
|
483,557 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio
|
|
34,059,722 L1D_CACHE:u
|
|
|
|
16.956477005 seconds time elapsed
|
|
|
|
88.393687000 seconds user
|
|
1037.101858000 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, ..., 766390, 766394,
|
|
766396]),
|
|
col_indices=tensor([ 0, 1, 2, ..., 116833, 89,
|
|
116834]),
|
|
values=tensor([-1.0000e+00, -1.0000e+00, -1.0000e+00, ...,
|
|
1.0331e+01, -1.0000e-03, 1.0000e-03]),
|
|
size=(116835, 116835), nnz=766396, layout=torch.sparse_csr)
|
|
tensor([0.8850, 0.9552, 0.7029, ..., 0.3357, 0.0248, 0.5395])
|
|
Matrix: dc2
|
|
Shape: torch.Size([116835, 116835])
|
|
NNZ: 766396
|
|
Density: 5.614451099680581e-05
|
|
Time: 13.873224973678589 seconds
|
|
|
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/dc2.mtx 1000':
|
|
|
|
561,480 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio
|
|
578,369 LL_CACHE_RD:u
|
|
192,306 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio
|
|
25,364 L2D_TLB_REFILL:u
|
|
317,121 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio
|
|
1,812,330 L2D_CACHE:u
|
|
|
|
17.467787426 seconds time elapsed
|
|
|
|
92.463054000 seconds user
|
|
1072.584062000 seconds sys
|
|
|
|
|
|
|