Basic compilation task on how long it takes to build ffmpeg. Higher than average amount of branch misprediction and compilations seem to have some of the highest frontend times and many separate processes.

AMD metrics
elapsed 171.202
on_cpu 0.776 # 12.41 / 16 cores
utime 1947.351
stime 177.076
nvcsw 114968 # 32.43%
nivcsw 239595 # 67.57%
inblock 117920 # 688.78/sec
onblock 14100816 # 82363.59/sec
cpu-clock 2123980912392 # 2123.981 seconds
task-clock 2124121813103 # 2124.122 seconds
page faults 42358510 # 19941.658/sec
context switches 327492 # 154.178/sec
cpu migrations 21796 # 10.261/sec
major page faults 2396 # 1.128/sec
minor page faults 42356114 # 19940.530/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 2218874607784 # 211.000 branches per 1000 inst
branch misses 60796986990 # 2.74% branch miss
conditional 1702720659155 # 161.917 conditional branches per 1000 inst
indirect 52690269300 # 5.010 indirect branches per 1000 inst
cpu-cycles 8477488825007 # 3.11 GHz
instructions 10371093730733 # 1.22 IPC
slots 17364839747580 #
retiring 3403828778757 # 19.6% (24.3%)
-- ucode 3982965399 # 0.0%
-- fastpath 3399845813358 # 19.6%
frontend 5839913740178 # 33.6% (41.6%)
-- latency 4277633170788 # 24.6%
-- bandwidth 1562280569390 # 9.0%
backend 4131015233051 # 23.8% (29.5%)
-- cpu 540707338867 # 3.1%
-- memory 3590307894184 # 20.7%
speculation 648179004659 # 3.7% ( 4.6%)
-- branch mispredict 641559867721 # 3.7%
-- pipeline restart 6619136938 # 0.0%
smt-contention 3341842645550 # 19.2% ( 0.0%)
cpu-cycles 8450512615627 # 3.11 GHz
instructions 10367098166757 # 1.23 IPC
instructions 3502228303687 # 39.059 l2 access per 1000 inst
l2 hit from l1 116829178127 # 16.93% l2 miss
l2 miss from l1 13877145906 #
l2 hit from l2 pf 10677565181 #
l3 hit from l2 pf 5095309639 #
l3 miss from l2 pf 4192514345 #
instructions 3499360326307 # 24.617 float per 1000 inst
float 512 9551 # 0.000 AVX-512 per 1000 inst
float 256 199056 # 0.000 AVX-256 per 1000 inst
float 128 86143020332 # 24.617 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 674.715
on_cpu 0.827 # 13.23 / 16 cores
utime 8459.988
stime 465.057
nvcsw 328774 # 29.44%
nivcsw 787917 # 70.56%
inblock 115008 # 170.45/sec
onblock 46517320 # 68943.64/sec
cpu-clock 8924013570046 # 8924.014 seconds
task-clock 8924333278137 # 8924.333 seconds
page faults 139136217 # 15590.657/sec
context switches 1038677 # 116.387/sec
cpu migrations 90336 # 10.122/sec
major page faults 2335 # 0.262/sec
minor page faults 139133882 # 15590.395/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 7296503689664 # 209.124 branches per 1000 inst
branch misses 176386328060 # 2.42% branch miss
conditional 7296506700480 # 209.124 conditional branches per 1000 inst
indirect 1498814182689 # 42.957 indirect branches per 1000 inst
slots 12988285798586 #
retiring 5235931312872 # 40.3% (40.3%)
-- ucode 351433784840 # 2.7%
-- fastpath 4884497528032 # 37.6%
frontend 4421921591724 # 34.0% (34.0%)
-- latency 2094764988792 # 16.1%
-- bandwidth 2327156602932 # 17.9%
backend 1152804012150 # 8.9% ( 8.9%)
-- cpu 542205814746 # 4.2%
-- memory 610598197404 # 4.7%
speculation 2204644564571 # 17.0% (17.0%)
-- branch mispredict 2148498675712 # 16.5%
-- pipeline restart 56145888859 # 0.4%
smt-contention 0 # 0.0% ( 0.0%)
cpu-cycles 5063611872783 # 1.53 GHz
instructions 7035472426496 # 1.39 IPC
l2 access 220349292960 # 39.600 l2 access per 1000 inst
l2 miss 51775619931 # 23.50% l2 miss
Overall process table shows most time spent in the compiler front end.
30993 processes
6425 cc1 1600.03 75.82
413 nasm 185.92 2.50
6315 as 61.10 5.02
91 ld 4.53 1.92
6 make 3.31 1.14
38 vulkaninfo 0.57 0.96
1875 configure 0.46 0.29
23 ar 0.42 2.80
1 xz 0.39 0.01
22 ranlib 0.23 2.57
6 php 0.08 0.17
4 vulkani:disk$0 0.06 0.11
7 clang 0.06 0.03
2 llvmpipe-0 0.03 0.06
2 llvmpipe-1 0.03 0.06
2 llvmpipe-10 0.03 0.06
2 llvmpipe-11 0.03 0.06
2 llvmpipe-12 0.03 0.06
2 llvmpipe-13 0.03 0.06
2 llvmpipe-14 0.03 0.06
2 llvmpipe-15 0.03 0.06
2 llvmpipe-2 0.03 0.06
2 llvmpipe-3 0.03 0.06
2 llvmpipe-4 0.03 0.06
2 llvmpipe-5 0.03 0.06
2 llvmpipe-6 0.03 0.06
2 llvmpipe-7 0.03 0.06
2 llvmpipe-8 0.03 0.06
2 llvmpipe-9 0.03 0.06
1 pod2man 0.02 0.00
1 tar 0.01 0.22
1 lspci 0.01 0.03
138 rm 0.00 0.55
412 strip 0.00 0.12
7243 sh 0.00 0.09
6580 gcc 0.00 0.00
345 cat 0.00 0.00
241 pkgconfig_gener 0.00 0.00
179 sed 0.00 0.00
93 tr 0.00 0.00
91 collect2 0.00 0.00
63 awk 0.00 0.00
48 grep 0.00 0.00
40 mkdir 0.00 0.00
30 pkg-config 0.00 0.00
21 cut 0.00 0.00
16 sort 0.00 0.00
15 dirname 0.00 0.00
14 cmp 0.00 0.00
14 cp 0.00 0.00
12 expr 0.00 0.00
9 gsettings 0.00 0.00
9 stty 0.00 0.00
8 stat 0.00 0.00
8 systemd-detect- 0.00 0.00
7 head 0.00 0.00
6 llvm-link 0.00 0.00
5 glxinfo 0.00 0.00
5 gmain 0.00 0.00
5 mktemp 0.00 0.00
5 phoronix-test-s 0.00 0.00
5 version.sh 0.00 0.00
4 bash 0.00 0.00
4 uname 0.00 0.00
3 build-ffmpeg 0.00 0.00
3 touch 0.00 0.00
2 cc 0.00 0.00
2 chmod 0.00 0.00
2 clinfo 0.00 0.00
2 dconf worker 0.00 0.00
2 git 0.00 0.00
2 lscpu 0.00 0.00
2 setterm 0.00 0.00
2 test 0.00 0.00
2 which 0.00 0.00
1 cc1plus 0.00 0.00
1 date 0.00 0.00
1 dmesg 0.00 0.00
1 dmidecode 0.00 0.00
1 g++ 0.00 0.00
1 ifconfig 0.00 0.00
1 ip 0.00 0.00
1 ln 0.00 0.00
1 lsmod 0.00 0.00
1 nm 0.00 0.00
1 od 0.00 0.00
1 perl 0.00 0.00
1 ps 0.00 0.00
1 qdbus 0.00 0.00
1 readlink 0.00 0.00
1 realpath 0.00 0.00
1 rsync 0.00 0.00
1 systemctl 0.00 0.00
1 tail 0.00 0.00
1 template.sh 0.00 0.00
1 test.sh 0.00 0.00
1 wc 0.00 0.00
2 processes running
62 maximum processes
