Another build test, this time for the mplayer media player. A fairly quick build taking less than a minute.
Topdown overview shows a similar overview to other build processes. Generally heavier on front-end stalls and not as much backend stalls. Slight differences towards end at link stage.
AMD metrics show ~12 cores kept busy and 1/5th of the instructions are branches.
elapsed 131.083
on_cpu 0.749 # 11.98 / 16 cores
utime 1434.909
stime 136.095
nvcsw 184881 # 54.88%
nivcsw 151998 # 45.12%
inblock 4840 # 36.92/sec
onblock 815992 # 6225.02/sec
cpu-clock 1569995918518 # 1569.996 seconds
task-clock 1570022200562 # 1570.022 seconds
page faults 33042137 # 21045.650/sec
context switches 311123 # 198.165/sec
cpu migrations 32456 # 20.672/sec
major page faults 704 # 0.448/sec
minor page faults 33041433 # 21045.201/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 1588505172838 # 207.892 branches per 1000 inst
branch misses 43921596872 # 2.76% branch miss
conditional 1230296354350 # 161.012 conditional branches per 1000 inst
indirect 34954151096 # 4.575 indirect branches per 1000 inst
cpu-cycles 5992955401481 # 2.86 GHz
instructions 7521843661027 # 1.26 IPC
slots 12295701158958 #
retiring 2473184787261 # 20.1% (25.0%)
-- ucode 3277908923 # 0.0%
-- fastpath 2469906878338 # 20.1%
frontend 4267191925642 # 34.7% (43.1%)
-- latency 3145065275880 # 25.6%
-- bandwidth 1122126649762 # 9.1%
backend 2704586566512 # 22.0% (27.3%)
-- cpu 373789605992 # 3.0%
-- memory 2330796960520 # 19.0%
speculation 458055998059 # 3.7% ( 4.6%)
-- branch mispredict 453301995104 # 3.7%
-- pipeline restart 4754002955 # 0.0%
smt-contention 2392662345903 # 19.5% ( 0.0%)
cpu-cycles 5999256771224 # 2.86 GHz
instructions 7518589349203 # 1.25 IPC
instructions 2545551521414 # 39.154 l2 access per 1000 inst
l2 hit from l1 86386798530 # 17.25% l2 miss
l2 miss from l1 10772079364 #
l2 hit from l2 pf 6864784791 #
l3 hit from l2 pf 3645118667 #
l3 miss from l2 pf 2771144343 #
instructions 2542523986390 # 24.173 float per 1000 inst
float 512 8375 # 0.000 AVX-512 per 1000 inst
float 256 567122 # 0.000 AVX-256 per 1000 inst
float 128 61459757300 # 24.173 AVX-128 per 1000 inst
float MMX 0 # 0.000 MMX per 1000 inst
float scalar 1 # 0.000 scalar per 1000 inst
Intel metrics show a larger overall elapsed time, perhaps because of additional variability depending on what cores are used.
elapsed 702.937
on_cpu 0.830 # 13.27 / 16 cores
utime 8850.134
stime 480.073
nvcsw 805769 # 51.24%
nivcsw 766621 # 48.76%
inblock 37360 # 53.15/sec
onblock 2924240 # 4160.03/sec
cpu-clock 9327209381783 # 9327.209 seconds
task-clock 9327273727003 # 9327.274 seconds
page faults 150700356 # 16156.957/sec
context switches 1466331 # 157.209/sec
cpu migrations 144812 # 15.526/sec
major page faults 2783 # 0.298/sec
minor page faults 150697573 # 16156.658/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 7741484482358 # 207.389 branches per 1000 inst
branch misses 191113104298 # 2.47% branch miss
conditional 7741488432022 # 207.389 conditional branches per 1000 inst
indirect 1540448949106 # 41.268 indirect branches per 1000 inst
slots 9270230760800 #
retiring 3740816186972 # 40.4% (40.4%)
-- ucode 254059658497 # 2.7%
-- fastpath 3486756528475 # 37.6%
frontend 3249083635174 # 35.0% (35.0%)
-- latency 1538385778881 # 16.6%
-- bandwidth 1710697856293 # 18.5%
backend 700103408302 # 7.6% ( 7.6%)
-- cpu 352231579537 # 3.8%
-- memory 347871828765 # 3.8%
speculation 1600749496422 # 17.3% (17.3%)
-- branch mispredict 1561048913198 # 16.8%
-- pipeline restart 39700583224 # 0.4%
smt-contention 0 # 0.0% ( 0.0%)
cpu-cycles 3783910784078 # 1.61 GHz
instructions 5236575955741 # 1.38 IPC
l2 access 158201882092 # 39.489 l2 access per 1000 inst
l2 miss 35363291724 # 22.35% l2 miss
Process summary shows more compilation than I expected with ~5900 C complier front end (cc1) dominating the time.
28756 processes
5918 cc1 1292.43 69.61
331 yasm 56.10 0.40
68 clinfo 16.53 5.99
30 make 6.38 2.36
5917 as 3.86 0.09
157 ld 1.67 1.16
1 xz 0.80 0.05
38 vulkaninfo 0.76 1.34
137 awk 0.61 0.01
22 ar 0.33 0.58
6 glxinfo:gdrv0 0.14 0.07
6 php 0.09 0.21
3 codec-cfg 0.09 0.00
4 vulkani:disk$0 0.08 0.14
6 clang 0.07 0.05
2 glxinfo 0.07 0.03
2 glxinfo:cs0 0.07 0.03
2 glxinfo:disk$0 0.07 0.03
2 glxinfo:shlo0 0.07 0.03
2 glxinfo:sh0 0.06 0.03
2351 configure 0.04 0.32
2 llvmpipe-0 0.04 0.07
2 llvmpipe-1 0.04 0.07
2 llvmpipe-10 0.04 0.07
2 llvmpipe-11 0.04 0.07
2 llvmpipe-12 0.04 0.07
2 llvmpipe-13 0.04 0.07
2 llvmpipe-14 0.04 0.07
2 llvmpipe-15 0.04 0.07
2 llvmpipe-2 0.04 0.07
2 llvmpipe-3 0.04 0.07
2 llvmpipe-4 0.04 0.07
2 llvmpipe-5 0.04 0.07
2 llvmpipe-6 0.04 0.07
2 llvmpipe-7 0.04 0.07
2 llvmpipe-8 0.04 0.07
2 llvmpipe-9 0.04 0.07
3 rocminfo 0.03 0.00
1 tar 0.02 0.41
1 lspci 0.01 0.01
431 rm 0.00 0.33
5643 sh 0.00 0.07
1 ps 0.00 0.01
5934 cc 0.00 0.00
536 cat 0.00 0.00
526 tr 0.00 0.00
157 collect2 0.00 0.00
46 sed 0.00 0.00
24 pkg-config 0.00 0.00
21 true 0.00 0.00
14 cut 0.00 0.00
14 tmp 0.00 0.00
13 gcc 0.00 0.00
13 grep 0.00 0.00
12 cmp 0.00 0.00
12 gsettings 0.00 0.00
10 cp 0.00 0.00
10 head 0.00 0.00
8 stat 0.00 0.00
8 systemd-detect- 0.00 0.00
8 version.sh 0.00 0.00
6 llvm-link 0.00 0.00
5 phoronix-test-s 0.00 0.00
4 bash 0.00 0.00
4 help_create.sh 0.00 0.00
4 uname 0.00 0.00
3 basename 0.00 0.00
3 mv 0.00 0.00
3 time-compile-mp 0.00 0.00
3 touch 0.00 0.00
2 dconf worker 0.00 0.00
2 git 0.00 0.00
2 gmain 0.00 0.00
2 lscpu 0.00 0.00
2 tail 0.00 0.00
2 which 0.00 0.00
2 xset 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 ifconfig 0.00 0.00
1 ip 0.00 0.00
1 lsmod 0.00 0.00
1 mkdir 0.00 0.00
1 mktemp 0.00 0.00
1 nm 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 strings 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
77 processes running
158 maximum processes