169 lines
10 KiB
Plaintext
169 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 3394146 queued and waiting for resources
|
||
|
srun: job 3394146 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, 3, 9, ..., 572056, 572061,
|
||
|
572066]),
|
||
|
col_indices=tensor([ 453, 1291, 1979, ..., 113521, 114509,
|
||
|
114602]),
|
||
|
values=tensor([160642., 31335., 282373., ..., 88393., 99485.,
|
||
|
18651.]), size=(115406, 115406), nnz=572066,
|
||
|
layout=torch.sparse_csr)
|
||
|
tensor([0.4608, 0.1516, 0.8492, ..., 0.8920, 0.4275, 0.8070])
|
||
|
Shape: torch.Size([115406, 115406])
|
||
|
NNZ: 572066
|
||
|
Density: 4.295259032005559e-05
|
||
|
Time: 1.3751039505004883 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/ut2010.mtx 100':
|
||
|
|
||
|
60.55 msec task-clock:u # 0.012 CPUs utilized
|
||
|
0 context-switches:u # 0.000 /sec
|
||
|
0 cpu-migrations:u # 0.000 /sec
|
||
|
3,490 page-faults:u # 57.638 K/sec
|
||
|
49,977,496 cycles:u # 0.825 GHz (40.93%)
|
||
|
78,622,993 instructions:u # 1.57 insn per cycle (85.37%)
|
||
|
<not supported> branches:u
|
||
|
358,029 branch-misses:u
|
||
|
31,478,500 L1-dcache-loads:u # 519.877 M/sec
|
||
|
479,449 L1-dcache-load-misses:u # 1.52% of all L1-dcache accesses
|
||
|
<not supported> LLC-loads:u
|
||
|
<not supported> LLC-load-misses:u
|
||
|
29,991,824 L1-icache-loads:u # 495.324 M/sec
|
||
|
294,864 L1-icache-load-misses:u # 0.98% of all L1-icache accesses
|
||
|
35,154,647 dTLB-loads:u # 580.589 M/sec (23.19%)
|
||
|
<not counted> dTLB-load-misses:u (0.00%)
|
||
|
<not counted> iTLB-loads:u (0.00%)
|
||
|
<not counted> iTLB-load-misses:u (0.00%)
|
||
|
|
||
|
4.986156121 seconds time elapsed
|
||
|
|
||
|
23.724703000 seconds user
|
||
|
145.034521000 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, 3, 9, ..., 572056, 572061,
|
||
|
572066]),
|
||
|
col_indices=tensor([ 453, 1291, 1979, ..., 113521, 114509,
|
||
|
114602]),
|
||
|
values=tensor([160642., 31335., 282373., ..., 88393., 99485.,
|
||
|
18651.]), size=(115406, 115406), nnz=572066,
|
||
|
layout=torch.sparse_csr)
|
||
|
tensor([0.4697, 0.7121, 0.5987, ..., 0.2619, 0.7308, 0.3129])
|
||
|
Shape: torch.Size([115406, 115406])
|
||
|
NNZ: 572066
|
||
|
Density: 4.295259032005559e-05
|
||
|
Time: 1.6881086826324463 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/ut2010.mtx 100':
|
||
|
|
||
|
327,078 BR_MIS_PRED_RETIRED:u # 0.0 per branch branch_misprediction_ratio
|
||
|
20,135,808 BR_RETIRED:u
|
||
|
|
||
|
5.374156677 seconds time elapsed
|
||
|
|
||
|
25.609168000 seconds user
|
||
|
167.278028000 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, 3, 9, ..., 572056, 572061,
|
||
|
572066]),
|
||
|
col_indices=tensor([ 453, 1291, 1979, ..., 113521, 114509,
|
||
|
114602]),
|
||
|
values=tensor([160642., 31335., 282373., ..., 88393., 99485.,
|
||
|
18651.]), size=(115406, 115406), nnz=572066,
|
||
|
layout=torch.sparse_csr)
|
||
|
tensor([0.9215, 0.6706, 0.8015, ..., 0.8507, 0.8546, 0.4441])
|
||
|
Shape: torch.Size([115406, 115406])
|
||
|
NNZ: 572066
|
||
|
Density: 4.295259032005559e-05
|
||
|
Time: 1.2785694599151611 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/ut2010.mtx 100':
|
||
|
|
||
|
27,608,093 L1I_TLB:u # 0.0 per TLB access itlb_walk_ratio
|
||
|
6,616 ITLB_WALK:u
|
||
|
17,185 DTLB_WALK:u # 0.0 per TLB access dtlb_walk_ratio
|
||
|
36,866,957 L1D_TLB:u
|
||
|
|
||
|
4.861513311 seconds time elapsed
|
||
|
|
||
|
23.339077000 seconds user
|
||
|
141.584760000 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, 3, 9, ..., 572056, 572061,
|
||
|
572066]),
|
||
|
col_indices=tensor([ 453, 1291, 1979, ..., 113521, 114509,
|
||
|
114602]),
|
||
|
values=tensor([160642., 31335., 282373., ..., 88393., 99485.,
|
||
|
18651.]), size=(115406, 115406), nnz=572066,
|
||
|
layout=torch.sparse_csr)
|
||
|
tensor([0.8973, 0.5228, 0.4492, ..., 0.7677, 0.7722, 0.1700])
|
||
|
Shape: torch.Size([115406, 115406])
|
||
|
NNZ: 572066
|
||
|
Density: 4.295259032005559e-05
|
||
|
Time: 1.1654376983642578 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/ut2010.mtx 100':
|
||
|
|
||
|
32,639,204 L1I_CACHE:u # 0.0 per cache access l1i_cache_miss_ratio
|
||
|
309,643 L1I_CACHE_REFILL:u
|
||
|
478,856 L1D_CACHE_REFILL:u # 0.0 per cache access l1d_cache_miss_ratio
|
||
|
34,280,618 L1D_CACHE:u
|
||
|
|
||
|
4.677973310 seconds time elapsed
|
||
|
|
||
|
22.972655000 seconds user
|
||
|
125.062401000 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, 3, 9, ..., 572056, 572061,
|
||
|
572066]),
|
||
|
col_indices=tensor([ 453, 1291, 1979, ..., 113521, 114509,
|
||
|
114602]),
|
||
|
values=tensor([160642., 31335., 282373., ..., 88393., 99485.,
|
||
|
18651.]), size=(115406, 115406), nnz=572066,
|
||
|
layout=torch.sparse_csr)
|
||
|
tensor([0.4542, 0.7095, 0.5701, ..., 0.2172, 0.8829, 0.7757])
|
||
|
Shape: torch.Size([115406, 115406])
|
||
|
NNZ: 572066
|
||
|
Density: 4.295259032005559e-05
|
||
|
Time: 1.1153452396392822 seconds
|
||
|
|
||
|
Performance counter stats for 'apptainer run pytorch-altra.sif -c numactl --cpunodebind=0 --membind=0 python spmv.py matrices/ut2010.mtx 100':
|
||
|
|
||
|
555,275 LL_CACHE_MISS_RD:u # 1.0 per cache access ll_cache_read_miss_ratio
|
||
|
578,455 LL_CACHE_RD:u
|
||
|
188,723 L2D_TLB:u # 0.1 per TLB access l2_tlb_miss_ratio
|
||
|
24,635 L2D_TLB_REFILL:u
|
||
|
319,663 L2D_CACHE_REFILL:u # 0.2 per cache access l2_cache_miss_ratio
|
||
|
1,799,940 L2D_CACHE:u
|
||
|
|
||
|
4.655024760 seconds time elapsed
|
||
|
|
||
|
23.104641000 seconds user
|
||
|
122.294597000 seconds sys
|
||
|
|
||
|
|
||
|
|