Testing the GNU multi-precision library. A single threaded program that reports a GMPbench score
Topdown profile suggests multiple sub-tests. Overall a high retirement rate low frontend stalls with backend stalls variable with the test case.
AMD metrics show little floating point and little l2 access. The CPU stalls are core-bound and not memory-bound.
elapsed 427.784
on_cpu 0.062 # 0.99 / 16 cores
utime 417.815
stime 4.074
nvcsw 3074 # 64.89%
nivcsw 1663 # 35.11%
inblock 0 # 0.00/sec
onblock 14296 # 33.42/sec
cpu-clock 421916906517 # 421.917 seconds
task-clock 421922454058 # 421.922 seconds
page faults 2756183 # 6532.440/sec
context switches 6298 # 14.927/sec
cpu migrations 444 # 1.052/sec
major page faults 3 # 0.007/sec
minor page faults 2756180 # 6532.433/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 501523528799 # 82.260 branches per 1000 inst
branch misses 3061059185 # 0.61% branch miss
conditional 382644488334 # 62.761 conditional branches per 1000 inst
indirect 14876152172 # 2.440 indirect branches per 1000 inst
cpu-cycles 1965040411588 # 0.29 GHz
instructions 6072094172754 # 3.09 IPC high
slots 3937816545756 #
retiring 2247636929437 # 57.1% (57.1%) high
-- ucode 776956035 # 0.0%
-- fastpath 2246859973402 # 57.1%
frontend 116276658154 # 3.0% ( 3.0%) low
-- latency 80906720016 # 2.1%
-- bandwidth 35369938138 # 0.9%
backend 1509881987155 # 38.3% (38.3%)
-- cpu 1262260815603 # 32.1%
-- memory 247621171552 # 6.3%
speculation 63519286739 # 1.6% ( 1.6%)
-- branch mispredict 60232902373 # 1.5%
-- pipeline restart 3286384366 # 0.1%
smt-contention 501252396 # 0.0% ( 0.0%)
cpu-cycles 1965474699019 # 0.29 GHz
instructions 6059932908034 # 3.08 IPC high
instructions 2023359162871 # 2.900 l2 access per 1000 inst
l2 hit from l1 3554993713 # 10.74% l2 miss
l2 miss from l1 138068096 #
l2 hit from l2 pf 1820413091 #
l3 hit from l2 pf 483630493 #
l3 miss from l2 pf 8709715 #
instructions 2021651448545 # 1.140 float per 1000 inst
float 512 213 # 0.000 AVX-512 per 1000 inst
float 256 638 # 0.000 AVX-256 per 1000 inst
float 128 2303804812 # 1.140 AVX-128 per 1000 inst
float MMX 0 # 0.000 MMX per 1000 inst
float scalar 0 # 0.000 scalar per 1000 inst
Intel metrics
elapsed 429.153
on_cpu 0.062 # 0.99 / 16 cores
utime 421.186
stime 2.284
nvcsw 2764 # 62.44%
nivcsw 1663 # 37.56%
inblock 248 # 0.58/sec
onblock 2720 # 6.34/sec
cpu-clock 423457398211 # 423.457 seconds
task-clock 423463418970 # 423.463 seconds
page faults 2434289 # 5748.523/sec
context switches 5991 # 14.148/sec
cpu migrations 466 # 1.100/sec
major page faults 1 # 0.002/sec
minor page faults 2434288 # 5748.520/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 444883853274 # 81.002 branches per 1000 inst
branch misses 2834417364 # 0.64% branch miss
conditional 444883878586 # 81.002 conditional branches per 1000 inst
indirect 14177570230 # 2.581 indirect branches per 1000 inst
slots 9621835222010 #
retiring 6303423323147 # 65.5% (65.5%) high
-- ucode 987932791689 # 10.3%
-- fastpath 5315490531458 # 55.2%
frontend 487924713905 # 5.1% ( 5.1%)
-- latency 108479845700 # 1.1%
-- bandwidth 379444868205 # 3.9%
backend 2464878156935 # 25.6% (25.6%)
-- cpu 2307296971385 # 24.0%
-- memory 157581185550 # 1.6%
speculation 366841291386 # 3.8% ( 3.8%)
-- branch mispredict 355601817820 # 3.7%
-- pipeline restart 11239473566 # 0.1%
smt-contention 0 # 0.0% ( 0.0%)
cpu-cycles 1602571643660 # 0.23 GHz
instructions 5493598362825 # 3.43 IPC high
l2 access 9495709247 # 1.729 l2 access per 1000 inst
l2 miss 1735896974 # 18.28% l2 miss
Process overview suggests different operations being tested in separate processes.
772 processes
15 multiply 157.50 1.91
8 divide 86.34 0.79
5 gcd 53.60 0.01
5 gcdext 53.39 0.00
3 rsa 33.69 0.00
3 pi 31.87 0.25
67 clinfo 15.59 7.19
38 vulkaninfo 0.58 1.71
6 glxinfo:gdrv0 0.14 0.03
6 glxinfo:gl0 0.14 0.03
4 vulkani:disk$0 0.07 0.18
6 php 0.07 0.10
6 clang 0.07 0.05
2 glxinfo 0.07 0.02
2 glxinfo:cs0 0.06 0.01
2 glxinfo:disk$0 0.06 0.01
2 glxinfo:sh0 0.06 0.01
2 glxinfo:shlo0 0.06 0.01
2 llvmpipe-0 0.04 0.09
2 llvmpipe-1 0.04 0.09
2 llvmpipe-10 0.04 0.09
2 llvmpipe-11 0.04 0.09
2 llvmpipe-12 0.04 0.09
2 llvmpipe-13 0.04 0.09
2 llvmpipe-14 0.04 0.09
2 llvmpipe-15 0.04 0.09
2 llvmpipe-2 0.04 0.09
2 llvmpipe-3 0.04 0.09
2 llvmpipe-4 0.04 0.09
2 llvmpipe-5 0.04 0.09
2 llvmpipe-6 0.04 0.09
2 llvmpipe-7 0.04 0.09
2 llvmpipe-8 0.04 0.09
2 llvmpipe-9 0.04 0.09
3 rocminfo 0.03 0.00
118 runbench 0.01 0.04
1 lspci 0.00 0.03
1 ps 0.00 0.01
150 gexpr 0.00 0.00
80 sh 0.00 0.00
79 sed 0.00 0.00
40 grep 0.00 0.00
13 gcc 0.00 0.00
8 stat 0.00 0.00
8 systemd-detect- 0.00 0.00
7 gsettings 0.00 0.00
6 llvm-link 0.00 0.00
5 gmain 0.00 0.00
5 phoronix-test-s 0.00 0.00
4 dconf worker 0.00 0.00
2 cc 0.00 0.00
2 lscpu 0.00 0.00
2 uname 0.00 0.00
2 which 0.00 0.00
2 xset 0.00 0.00
1 cat 0.00 0.00
1 date 0.00 0.00
1 dirname 0.00 0.00
1 dmesg 0.00 0.00
1 dmidecode 0.00 0.00
1 gmpbench 0.00 0.00
1 ifconfig 0.00 0.00
1 ip 0.00 0.00
1 lsmod 0.00 0.00
1 mktemp 0.00 0.00
1 qdbus 0.00 0.00
1 readlink 0.00 0.00
1 realpath 0.00 0.00
1 sort 0.00 0.00
1 stty 0.00 0.00
1 systemctl 0.00 0.00
1 template.sh 0.00 0.00
1 wc 0.00 0.00
1 xrandr 0.00 0.00
0 processes running
47 maximum processes
An example from the computation section
1170498) gmpbench cpu=0 start=5.47 finish=425.53
1170499) runbench cpu=0 start=5.47 finish=425.53
1170500) cat cpu=15 start=5.47 finish=5.47
1170501) runbench cpu=14 start=5.48 finish=5.48
1170502) runbench cpu=3 start=5.48 finish=5.48
1170503) sed cpu=2 start=5.48 finish=5.48
1170504) multiply cpu=1 start=5.48 finish=13.29
1170507) runbench cpu=14 start=13.29 finish=13.29
1170508) grep cpu=15 start=13.29 finish=13.29
1170509) sed cpu=3 start=13.29 finish=13.29
1170510) gexpr cpu=15 start=13.29 finish=13.29
1170511) gexpr cpu=3 start=13.29 finish=13.29
1170512) gexpr cpu=4 start=13.29 finish=13.29
1170513) runbench cpu=1 start=13.29 finish=13.29
1170514) runbench cpu=4 start=13.29 finish=13.29
1170515) sed cpu=15 start=13.29 finish=13.29
1170516) multiply cpu=14 start=13.29 finish=24.10
1170518) runbench cpu=7 start=24.10 finish=24.10
1170519) grep cpu=1 start=24.10 finish=24.10
1170520) sed cpu=3 start=24.10 finish=24.10
1170521) gexpr cpu=4 start=24.10 finish=24.10
1170522) gexpr cpu=1 start=24.10 finish=24.10
1170523) gexpr cpu=3 start=24.10 finish=24.10
1170524) runbench cpu=14 start=24.10 finish=24.11
1170525) runbench cpu=7 start=24.10 finish=24.10
1170526) sed cpu=2 start=24.10 finish=24.11
1170527) multiply cpu=4 start=24.11 finish=34.75
1170528) runbench cpu=6 start=34.75 finish=34.75
1170529) grep cpu=7 start=34.75 finish=34.75
1170530) sed cpu=1 start=34.75 finish=34.75
1170531) gexpr cpu=10 start=34.76 finish=34.76
1170532) gexpr cpu=6 start=34.76 finish=34.76
1170533) gexpr cpu=7 start=34.76 finish=34.76
1170534) runbench cpu=11 start=34.76 finish=34.76
1170535) runbench cpu=12 start=34.76 finish=34.76
1170536) sed cpu=10 start=34.76 finish=34.76
1170537) multiply cpu=6 start=34.76 finish=45.30
1170538) runbench cpu=6 start=45.30 finish=45.30
1170539) grep cpu=15 start=45.30 finish=45.30
1170540) sed cpu=1 start=45.30 finish=45.30
1170541) gexpr cpu=10 start=45.30 finish=45.30
1170542) gexpr cpu=15 start=45.30 finish=45.30
1170543) gexpr cpu=1 start=45.30 finish=45.30
1170544) runbench cpu=3 start=45.30 finish=45.30
1170545) runbench cpu=12 start=45.30 finish=45.30
1170546) sed cpu=6 start=45.30 finish=45.30
1170547) multiply cpu=1 start=45.31 finish=57.07
1170548) runbench cpu=6 start=57.07 finish=57.07
1170549) grep cpu=7 start=57.07 finish=57.07
1170550) sed cpu=10 start=57.07 finish=57.07
1170551) gexpr cpu=3 start=57.07 finish=57.08
1170552) gexpr cpu=4 start=57.08 finish=57.08
1170553) gexpr cpu=6 start=57.08 finish=57.08
1170554) runbench cpu=1 start=57.08 finish=57.08
1170555) runbench cpu=10 start=57.08 finish=57.08
1170556) sed cpu=3 start=57.08 finish=57.08
1170557) multiply cpu=6 start=57.08 finish=67.69
1170558) runbench cpu=7 start=67.69 finish=67.69
1170559) grep cpu=9 start=67.69 finish=67.69
1170560) sed cpu=10 start=67.69 finish=67.69
1170561) gexpr cpu=3 start=67.69 finish=67.69
1170562) gexpr cpu=6 start=67.69 finish=67.69
1170563) gexpr cpu=7 start=67.69 finish=67.69
1170564) runbench cpu=9 start=67.70 finish=67.70
1170565) runbench cpu=10 start=67.70 finish=67.70
1170566) sed cpu=11 start=67.70 finish=67.70
1170567) multiply cpu=4 start=67.70 finish=78.30
1170568) runbench cpu=14 start=78.30 finish=78.31
1170569) grep cpu=7 start=78.30 finish=78.31
1170570) sed cpu=9 start=78.30 finish=78.31
1170571) gexpr cpu=10 start=78.31 finish=78.31
1170572) gexpr cpu=3 start=78.31 finish=78.31
1170573) gexpr cpu=14 start=78.31 finish=78.31
1170574) runbench cpu=7 start=78.31 finish=78.31
1170575) runbench cpu=9 start=78.31 finish=78.31
1170576) sed cpu=10 start=78.31 finish=78.31
1170577) multiply cpu=1 start=78.31 finish=88.83
1170578) runbench cpu=14 start=88.83 finish=88.83
1170579) grep cpu=15 start=88.83 finish=88.83
1170580) sed cpu=10 start=88.83 finish=88.83
1170581) gexpr cpu=1 start=88.83 finish=88.83
1170582) gexpr cpu=3 start=88.83 finish=88.84
1170583) gexpr cpu=15 start=88.84 finish=88.84