Stockfish is a chess simulator. It has pattern that differs on a second basis with occasional waiting for backend memory and a moderate amount of branch misprediction.
AMD metrics confirm branch misprediction and L2 misses both occur. There is some floating point but not much.
elapsed 1384.118
on_cpu 0.952 # 15.23 / 16 cores
utime 21076.319
stime 6.667
nvcsw 18847 # 5.55%
nivcsw 320971 # 94.45%
inblock 92656 # 66.94/sec
onblock 24016 # 17.35/sec
cpu-clock 21086578525058 # 21086.579 seconds
task-clock 21086871739374 # 21086.872 seconds
page faults 1522050 # 72.180/sec
context switches 346514 # 16.433/sec
cpu migrations 359 # 0.017/sec
major page faults 367 # 0.017/sec
minor page faults 1521683 # 72.163/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 9684555930271 # 98.355 branches per 1000 inst
branch misses 573154236984 # 5.92% branch miss
conditional 8296142807057 # 84.254 conditional branches per 1000 inst
indirect 101382653603 # 1.030 indirect branches per 1000 inst
cpu-cycles 16866386094273 # 3.73 GHz
instructions 19983394101588 # 1.18 IPC
slots 33720258649008 #
retiring 6744916097790 # 20.0% (27.2%)
-- ucode 6891013174 # 0.0%
-- fastpath 6738025084616 # 20.0%
frontend 6617800247940 # 19.6% (26.6%)
-- latency 4767554687280 # 14.1%
-- bandwidth 1850245560660 # 5.5%
backend 9932644504225 # 29.5% (40.0%)
-- cpu 1893238505762 # 5.6%
-- memory 8039405998463 # 23.8%
speculation 1542532995220 # 4.6% ( 6.2%)
-- branch mispredict 1530609982806 # 4.5%
-- pipeline restart 11923012414 # 0.0%
smt-contention 8882340075342 # 26.3% ( 0.0%)
cpu-cycles 16740842864574 # 3.73 GHz
instructions 19931947861899 # 1.19 IPC
instructions 6645376767345 # 99.428 l2 access per 1000 inst
l2 hit from l1 446181719701 # 11.87% l2 miss
l2 miss from l1 26985632445 #
l2 hit from l2 pf 163101649579 #
l3 hit from l2 pf 45361494017 #
l3 miss from l2 pf 6088573564 #
instructions 6644088416780 # 34.037 float per 1000 inst
float 512 80 # 0.000 AVX-512 per 1000 inst
float 256 16 # 0.000 AVX-256 per 1000 inst
float 128 226147813954 # 34.037 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 also show a high branch misprediction
elapsed 1640.895
on_cpu 0.965 # 15.44 / 16 cores
utime 25329.305
stime 3.520
nvcsw 16253 # 7.98%
nivcsw 187395 # 92.02%
inblock 93480 # 56.97/sec
onblock 21472 # 13.09/sec
cpu-clock 25333794283551 # 25333.794 seconds
task-clock 25333963779703 # 25333.964 seconds
page faults 1237282 # 48.839/sec
context switches 211663 # 8.355/sec
cpu migrations 1506 # 0.059/sec
major page faults 366 # 0.014/sec
minor page faults 1236915 # 48.824/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 7994058687634 # 95.904 branches per 1000 inst
branch misses 519871858414 # 6.50% branch miss
conditional 7994058723858 # 95.904 conditional branches per 1000 inst
indirect 1527383862423 # 18.324 indirect branches per 1000 inst
slots 94369743796502 #
retiring 38302277643659 # 40.6% (40.6%)
-- ucode 1150130197139 # 1.2%
-- fastpath 37152147446520 # 39.4%
frontend 28816472204386 # 30.5% (30.5%)
-- latency 14730504927444 # 15.6%
-- bandwidth 14085967276942 # 14.9%
backend 10793915769259 # 11.4% (11.4%)
-- cpu 6233594044595 # 6.6%
-- memory 4560321724664 # 4.8%
speculation 17570676295568 # 18.6% (18.6%)
-- branch mispredict 17420985834181 # 18.5%
-- pipeline restart 149690461387 # 0.2%
smt-contention 0 # 0.0% ( 0.0%)
cpu-cycles 39480962644128 # 1.61 GHz
instructions 49309411201069 # 1.25 IPC
l2 access 2896293695870 # 76.281 l2 access per 1000 inst
l2 miss 469759342148 # 16.22% l2 miss
Process summary shows almost all time is spent in stockfish processes.
624 processes
337 stockfish 115727.47 51.96
38 vulkaninfo 0.90 0.95
4 vulkani:disk$0 0.08 0.10
6 php 0.07 0.09
6 clang 0.06 0.01
2 llvmpipe-0 0.05 0.05
2 llvmpipe-1 0.05 0.05
2 llvmpipe-10 0.05 0.05
2 llvmpipe-11 0.05 0.05
2 llvmpipe-12 0.05 0.05
2 llvmpipe-13 0.05 0.05
2 llvmpipe-14 0.05 0.05
2 llvmpipe-15 0.05 0.05
2 llvmpipe-2 0.05 0.05
2 llvmpipe-3 0.05 0.05
2 llvmpipe-4 0.05 0.05
2 llvmpipe-5 0.05 0.05
2 llvmpipe-6 0.05 0.05
2 llvmpipe-7 0.05 0.05
2 llvmpipe-8 0.05 0.05
2 llvmpipe-9 0.05 0.05
1 lspci 0.00 0.03
91 sh 0.00 0.00
13 gcc 0.00 0.00
11 gsettings 0.00 0.00
9 stty 0.00 0.00
8 stat 0.00 0.00
8 systemd-detect- 0.00 0.00
6 llvm-link 0.00 0.00
5 glxinfo 0.00 0.00
5 phoronix-test-s 0.00 0.00
3 gmain 0.00 0.00
2 cc 0.00 0.00
2 clinfo 0.00 0.00
2 dconf worker 0.00 0.00
2 grep 0.00 0.00
2 lscpu 0.00 0.00
2 setterm 0.00 0.00
2 uname 0.00 0.00
2 which 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 mktemp 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 sed 0.00 0.00
1 sort 0.00 0.00
1 systemctl 0.00 0.00
1 template.sh 0.00 0.00
1 wc 0.00 0.00
8 processes running
55 maximum processes