28 Haziran 2020 Pazar

yorumsuz - işlemci-hafıza arasındaki hızları

Değişik işlemcilerin en basit şekilde hafızadan okuma hızlarını göstermek istedim.
Yorum sizlere aittir;

remzi@dell-7557:~$ dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
1042116771840 bytes (1.0 TB, 971 GiB) copied, 48 s, 21.7 GB/s   
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB, 977 GiB) copied, 48.2988 s, 21.7 GB/s
remzi@dell-7557:~$ lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                8
On-line CPU(s) list:   0-7
Thread(s) per core:    2
Core(s) per socket:    4
Socket(s):             1
NUMA node(s):          1
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 158
Model name:            Intel(R) Core(TM) i7-7700HQ CPU @ 2.80GHz
Stepping:              9
CPU MHz:               800.111
CPU max MHz:           3800.0000
CPU min MHz:           800.0000
BogoMIPS:              5616.00
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              6144K
NUMA node0 CPU(s):     0-7
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx rdseed adx smap clflushopt intel_pt xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp flush_l1d
remzi@dell-7557:~$

root@Z170-HD3P:~# dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
1047730847744 bytes (1,0 TB, 976 GiB) copied, 48 s, 21,8 GB/s   
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1,0 TB, 977 GiB) copied, 48,0387 s, 21,8 GB/s
root@Z170-HD3P:~# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                4
On-line CPU(s) list:   0-3
Thread(s) per core:    2
Core(s) per socket:    2
Socket(s):             1
NUMA node(s):          1
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 94
Model name:            Intel(R) Core(TM) i3-6100 CPU @ 3.70GHz
Stepping:              3
CPU MHz:               800.185
CPU max MHz:           3700,0000
CPU min MHz:           800,0000
BogoMIPS:              7392.00
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              3072K
NUMA node0 CPU(s):     0-3
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid mpx rdseed adx smap clflushopt intel_pt xsaveopt xsavec xgetbv1 xsaves dtherm arat pln pts hwp hwp_notify hwp_act_window hwp_epp flush_l1d
root@Z170-HD3P:~#



remzi@dell-7557:~$ ssh node13
Last login: Wed Jan  9 20:38:20 2019 from 176.43.21.110
root@node13 ~ # dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress1030936854528 bytes (1.0 TB, 960 GiB) copied, 46 s, 22.4 GB/s   
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB, 977 GiB) copied, 46.7969 s, 22.4 GB/s
root@node13 ~ # lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                8
On-line CPU(s) list:   0-7
Thread(s) per core:    2
Core(s) per socket:    4
Socket(s):             1
NUMA node(s):          1
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 58
Model name:            Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz
Stepping:              9
CPU MHz:               2189.533
CPU max MHz:           3900.0000
CPU min MHz:           1600.0000
BogoMIPS:              7004.06
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              8192K
NUMA node0 CPU(s):     0-7
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm cpuid_fault epb pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms xsaveopt dtherm ida arat pln pts flush_l1d
root@node13 ~ #



p8-800002-22c:~ #  dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
985714917376 bytes (986 GB, 918 GiB) copied, 12 s, 82.1 GB/s
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB, 977 GiB) copied, 12.7649 s, 82.1 GB/s
p8-800002-22c:~ # lscpu
Architecture:         ppc64le
Byte Order:           Little Endian
CPU(s):               160
On-line CPU(s) list:  0,8,16,24,32,40,48,56,64,72,80,88,96,104,112,120,128,136,144,152
Off-line CPU(s) list: 1-7,9-15,17-23,25-31,33-39,41-47,49-55,57-63,65-71,73-79,81-87,89-95,97-103,105-111,113-119,121-127,129-135,137-143,145-151,153-159
Thread(s) per core:   1
Core(s) per socket:   10
Socket(s):            2
NUMA node(s):         2
Model:                2.0 (pvr 004d 0200)
Model name:           POWER8 (raw), altivec supported
CPU max MHz:          3491.0000
CPU min MHz:          2061.0000
L1d cache:            64K
L1i cache:            32K
L2 cache:             512K
L3 cache:             8192K
NUMA node0 CPU(s):    0,8,16,24,32,40,48,56,64,72
NUMA node8 CPU(s):    80,88,96,104,112,120,128,136,144,152
p8-800002-22c:~ #  dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
985749520384 bytes (986 GB, 918 GiB) copied, 12 s, 82.1 GB/s
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB, 977 GiB) copied, 12.7648 s, 82.1 GB/s
p8-800002-22c:~ #


processor       : 152
cpu             : POWER8 (raw), altivec supported
clock           : 3491.000000MHz
revision        : 2.0 (pvr 004d 0200)

timebase        : 512000000
platform        : PowerNV
model           : 8001-22C
machine         : PowerNV 8001-22C
firmware        : OPAL
MMU             : Hash
p8-800002-22c:~ #


[root@cnode002 ~ ]# dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
1037066829824 bytes (1.0 TB) copied, 56.001647 s, 18.5 GB/s
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB) copied, 56.6216 s, 18.5 GB/s
[root@cnode002 ~ ]# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                28
On-line CPU(s) list:   0-27
Thread(s) per core:    1
Core(s) per socket:    14
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 79
Model name:            Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz
Stepping:              1
CPU MHz:               2400.000
CPU max MHz:           2400.0000
CPU min MHz:           1200.0000
BogoMIPS:              4788.87
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              35840K
NUMA node0 CPU(s):     0-6,14-20
NUMA node1 CPU(s):     7-13,21-27
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 intel_ppin intel_pt ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts spec_ctrl intel_stibp
[root@cnode002 ~ ]#


[root@headnode ~ ]# dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
1041830510592 bytes (1.0 TB) copied, 75.002684 s, 13.9 GB/s
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB) copied, 75.4883 s, 13.9 GB/s
[root@headnode ~ ]# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                40
On-line CPU(s) list:   0-39
Thread(s) per core:    2
Core(s) per socket:    10
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 79
Model name:            Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz
Stepping:              1
CPU MHz:               2200.000
CPU max MHz:           2200.0000
CPU min MHz:           1200.0000
BogoMIPS:              4395.00
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              25600K
NUMA node0 CPU(s):     0-9,20-29
NUMA node1 CPU(s):     10-19,30-39
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 invpcid_single intel_pt tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts
[root@headnode ~ ]#



root@node2:~# dd if=/dev/zero of=/dev/null bs=1M count=1000000 status=progress
1033986113536 bytes (1.0 TB, 963 GiB) copied, 58.0001 s, 17.8 GB/s
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB, 977 GiB) copied, 58.818 s, 17.8 GB/s
root@node2:~# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                24
On-line CPU(s) list:   0-23
Thread(s) per core:    1
Core(s) per socket:    12
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 63
Model name:            Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Stepping:              2
CPU MHz:               1200.485
CPU max MHz:           3300.0000
CPU min MHz:           1200.0000
BogoMIPS:              5000.75
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              30720K
NUMA node0 CPU(s):     0,2,4,6,8,10,12,14,16,18,20,22
NUMA node1 CPU(s):     1,3,5,7,9,11,13,15,17,19,21,23
Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm cpuid_fault epb invpcid_single pti tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc ibpb ibrs stibp dtherm ida arat pln pts
root@node2:~#


node1 deki dd status parametresini desteklemediğinden kullanamadım.

root@node1:~# time  dd if=/dev/zero of=/dev/null bs=1M count=1000000
1000000+0 records in
1000000+0 records out
1048576000000 bytes (1.0 TB) copied, 49.8366 s, 21.0 GB/s

real    0m49.838s
user    0m0.216s
sys     0m49.566s
root@node1:~# lscpu
Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                20
On-line CPU(s) list:   0-19
Thread(s) per core:    1
Core(s) per socket:    10
Socket(s):             2
NUMA node(s):          2
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 62
Stepping:              4
CPU MHz:               3000.023
BogoMIPS:              6001.40
Virtualization:        VT-x
L1d cache:             32K
L1i cache:             32K
L2 cache:              256K
L3 cache:              25600K
NUMA node0 CPU(s):     0,2,4,6,8,10,12,14,16,18
NUMA node1 CPU(s):     1,3,5,7,9,11,13,15,17,19
root@node1:~#

processor       : 19
vendor_id       : GenuineIntel
cpu family      : 6
model           : 62
model name      : Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz
stepping        : 4
microcode       : 0x42d
cpu MHz         : 3000.023
cache size      : 25600 KB
physical id     : 1
siblings        : 10
core id         : 12
cpu cores       : 10
apicid          : 56
initial apicid  : 56
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm ida arat xsaveopt pln pts dtherm rsb_ctxsw ssbd retpoline tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms flush_l1d
bogomips        : 6001.40
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual




Hiç yorum yok:

Yorum Gönder