154 lines
9.3 KiB
Plaintext
154 lines
9.3 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 3394148 queued and waiting for resources
|
||
|
srun: job 3394148 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, 583, 584, ..., 65459, 65460, 65460]),
|
||
|
col_indices=tensor([ 2, 23, 27, ..., 3324, 958, 841]),
|
||
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(11806, 11806),
|
||
|
nnz=65460, layout=torch.sparse_csr)
|
||
|
tensor([0.3190, 0.2829, 0.6210, ..., 0.9278, 0.7514, 0.5737])
|
||
|
Shape: torch.Size([11806, 11806])
|
||
|
NNZ: 65460
|
||
|
Density: 0.0004696458003979807
|
||
|
Time: 0.22389841079711914 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/Oregon-2.mtx 100':
|
||
|
|
||
|
42.01 msec task-clock:u # 0.012 CPUs utilized
|
||
|
0 context-switches:u # 0.000 /sec
|
||
|
0 cpu-migrations:u # 0.000 /sec
|
||
|
3,263 page-faults:u # 77.672 K/sec
|
||
|
47,084,933 cycles:u # 1.121 GHz (65.90%)
|
||
|
77,895,119 instructions:u # 1.65 insn per cycle (85.49%)
|
||
|
<not supported> branches:u
|
||
|
352,740 branch-misses:u
|
||
|
30,958,922 L1-dcache-loads:u # 736.946 M/sec
|
||
|
442,351 L1-dcache-load-misses:u # 1.43% of all L1-dcache accesses
|
||
|
<not supported> LLC-loads:u
|
||
|
<not supported> LLC-load-misses:u
|
||
|
29,506,648 L1-icache-loads:u # 702.376 M/sec
|
||
|
272,063 L1-icache-load-misses:u # 0.92% of all L1-icache accesses
|
||
|
51,646,382 dTLB-loads:u # 1.229 G/sec (15.87%)
|
||
|
<not counted> dTLB-load-misses:u (0.00%)
|
||
|
<not counted> iTLB-loads:u (0.00%)
|
||
|
<not counted> iTLB-load-misses:u (0.00%)
|
||
|
|
||
|
3.513156571 seconds time elapsed
|
||
|
|
||
|
15.150380000 seconds user
|
||
|
32.922923000 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, 583, 584, ..., 65459, 65460, 65460]),
|
||
|
col_indices=tensor([ 2, 23, 27, ..., 3324, 958, 841]),
|
||
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(11806, 11806),
|
||
|
nnz=65460, layout=torch.sparse_csr)
|
||
|
tensor([0.0741, 0.5476, 0.1060, ..., 0.8459, 0.8270, 0.8313])
|
||
|
Shape: torch.Size([11806, 11806])
|
||
|
NNZ: 65460
|
||
|
Density: 0.0004696458003979807
|
||
|
Time: 0.20610284805297852 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/Oregon-2.mtx 100':
|
||
|
|
||
|
330,923 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio
|
||
|
19,740,519 BR_RETIRED:u
|
||
|
|
||
|
3.639725976 seconds time elapsed
|
||
|
|
||
|
15.493122000 seconds user
|
||
|
27.617441000 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, 583, 584, ..., 65459, 65460, 65460]),
|
||
|
col_indices=tensor([ 2, 23, 27, ..., 3324, 958, 841]),
|
||
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(11806, 11806),
|
||
|
nnz=65460, layout=torch.sparse_csr)
|
||
|
tensor([0.9699, 0.9368, 0.7284, ..., 0.7182, 0.5308, 0.9833])
|
||
|
Shape: torch.Size([11806, 11806])
|
||
|
NNZ: 65460
|
||
|
Density: 0.0004696458003979807
|
||
|
Time: 0.15960955619812012 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/Oregon-2.mtx 100':
|
||
|
|
||
|
27,761,239 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio
|
||
|
6,471 ITLB_WALK:u
|
||
|
17,268 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio
|
||
|
36,993,265 L1D_TLB:u
|
||
|
|
||
|
3.455602215 seconds time elapsed
|
||
|
|
||
|
15.015027000 seconds user
|
||
|
27.930709000 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, 583, 584, ..., 65459, 65460, 65460]),
|
||
|
col_indices=tensor([ 2, 23, 27, ..., 3324, 958, 841]),
|
||
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(11806, 11806),
|
||
|
nnz=65460, layout=torch.sparse_csr)
|
||
|
tensor([0.5851, 0.3425, 0.8120, ..., 0.0829, 0.5823, 0.2256])
|
||
|
Shape: torch.Size([11806, 11806])
|
||
|
NNZ: 65460
|
||
|
Density: 0.0004696458003979807
|
||
|
Time: 0.15697884559631348 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/Oregon-2.mtx 100':
|
||
|
|
||
|
31,834,980 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio
|
||
|
298,333 L1I_CACHE_REFILL:u
|
||
|
466,901 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio
|
||
|
33,528,976 L1D_CACHE:u
|
||
|
|
||
|
3.452279902 seconds time elapsed
|
||
|
|
||
|
14.635240000 seconds user
|
||
|
28.262858000 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, 583, 584, ..., 65459, 65460, 65460]),
|
||
|
col_indices=tensor([ 2, 23, 27, ..., 3324, 958, 841]),
|
||
|
values=tensor([1., 1., 1., ..., 1., 1., 1.]), size=(11806, 11806),
|
||
|
nnz=65460, layout=torch.sparse_csr)
|
||
|
tensor([0.0772, 0.9112, 0.0293, ..., 0.4016, 0.4357, 0.5368])
|
||
|
Shape: torch.Size([11806, 11806])
|
||
|
NNZ: 65460
|
||
|
Density: 0.0004696458003979807
|
||
|
Time: 0.20962285995483398 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/Oregon-2.mtx 100':
|
||
|
|
||
|
525,505 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio
|
||
|
546,521 LL_CACHE_RD:u
|
||
|
184,884 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio
|
||
|
22,933 L2D_TLB_REFILL:u
|
||
|
292,367 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio
|
||
|
1,706,226 L2D_CACHE:u
|
||
|
|
||
|
3.566096255 seconds time elapsed
|
||
|
|
||
|
15.763579000 seconds user
|
||
|
28.620423000 seconds sys
|
||
|
|
||
|
|
||
|
|