A test of the espeak speech synthesizer. Single-threaded and running quickly.

Topdown profile shows a high retirement rate with some backend stalls.

AMD metrics confirm the high retirement rate. There is no floating point and little L2 access. The opcache is also effective.
elapsed 112.946
on_cpu 0.052 # 0.83 / 16 cores
utime 87.090
stime 7.197
nvcsw 21350 # 96.97%
nivcsw 666 # 3.03%
inblock 48 # 0.42/sec
onblock 12702104 # 112461.35/sec
cpu-clock 94310785834 # 94.311 seconds
task-clock 94318017988 # 94.318 seconds
page faults 149818 # 1588.435/sec
context switches 22403 # 237.526/sec
cpu migrations 289 # 3.064/sec
major page faults 2 # 0.021/sec
minor page faults 149816 # 1588.413/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 193163296246 # 115.658 branches per 1000 inst
branch misses 1744326831 # 0.90% branch miss
conditional 182676341543 # 109.379 conditional branches per 1000 inst
indirect 604072931 # 0.362 indirect branches per 1000 inst
cpu-cycles 434557730024 # 0.24 GHz
instructions 1668407686867 # 3.84 IPC high
slots 870993417672 #
retiring 580446120951 # 66.6% (66.7%) high
-- ucode 427024719 # 0.0%
-- fastpath 580019096232 # 66.6%
frontend 92391692352 # 10.6% (10.6%)
-- latency 68703756942 # 7.9%
-- bandwidth 23687935410 # 2.7%
backend 179965270808 # 20.7% (20.7%)
-- cpu 101990866904 # 11.7%
-- memory 77974403904 # 9.0%
speculation 18042803552 # 2.1% ( 2.1%)
-- branch mispredict 18003487509 # 2.1%
-- pipeline restart 39316043 # 0.0%
smt-contention 147206319 # 0.0% ( 0.0%)
cpu-cycles 432787935090 # 0.24 GHz
instructions 1668205003308 # 3.85 IPC high
instructions 556647980697 # 2.582 l2 access per 1000 inst
l2 hit from l1 1362700789 # 6.20% l2 miss
l2 miss from l1 47715752 #
l2 hit from l2 pf 33010019 #
l3 hit from l2 pf 13918066 #
l3 miss from l2 pf 27479269 #
instructions 556976761227 # 2.003 float per 1000 inst
float 512 63 # 0.000 AVX-512 per 1000 inst
float 256 516 # 0.000 AVX-256 per 1000 inst
float 128 1115368825 # 2.003 AVX-128 per 1000 inst
float MMX 0 # 0.000 MMX per 1000 inst
float scalar 0 # 0.000 scalar per 1000 inst
instructions 1669554498304 #
opcache 184696141102 # 110.626 opcache per 1000 inst
opcache miss 8848476154 # 4.8% opcache miss rate
l1 dTLB miss 166790988 # 0.100 L1 dTLB per 1000 inst
l2 dTLB miss 7621946 # 0.005 L2 dTLB per 1000 inst
instructions 1671940200498 #
icache 19248358842 # 11.513 icache per 1000 inst
icache miss 2671413379 # 13.9% icache miss rate
l1 iTLB miss 12686920 # 0.008 L1 iTLB per 1000 inst
l2 iTLB miss 0 # 0.000 L2 iTLB per 1000 inst
tlb flush 16898 # 0.000 TLB flush per 1000 inst
Intel metrics
elapsed 519.760
on_cpu 0.050 # 0.80 / 16 cores
utime 397.642
stime 18.654
nvcsw 4112 # 65.54%
nivcsw 2162 # 34.46%
inblock 552 # 1.06/sec
onblock 50758896 # 97658.37/sec
cpu-clock 416348151355 # 416.348 seconds
task-clock 416359883778 # 416.360 seconds
page faults 150554 # 361.596/sec
context switches 8673 # 20.831/sec
cpu migrations 434 # 1.042/sec
major page faults 0 # 0.000/sec
minor page faults 150554 # 361.596/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 762305289947 # 114.664 branches per 1000 inst
branch misses 7354769854 # 0.96% branch miss
conditional 762305303131 # 114.664 conditional branches per 1000 inst
indirect 2461514797 # 0.370 indirect branches per 1000 inst
slots 2355213170534 #
retiring 1554402648687 # 66.0% (66.0%) high
-- ucode 78497933168 # 3.3%
-- fastpath 1475904715519 # 62.7%
frontend 262631941365 # 11.2% (11.2%)
-- latency 87865535157 # 3.7%
-- bandwidth 174766406208 # 7.4%
backend 311417454416 # 13.2% (13.2%) low
-- cpu 269763128222 # 11.5%
-- memory 41654326194 # 1.8%
speculation 229071059789 # 9.7% ( 9.7%)
-- branch mispredict 224352216417 # 9.5%
-- pipeline restart 4718843372 # 0.2%
smt-contention 0 # 0.0% ( 0.0%)
cpu-cycles 393405541781 # 0.18 GHz
instructions 1669050370516 # 4.24 IPC high
l2 access 3117802373 # 1.869 l2 access per 1000 inst
l2 miss 291667593 # 9.35% l2 miss
cpu-cycles 392641925148 # 4.0% memory latency
load stalls 14797751781 # 2.9% l1 bound
l1 miss 3541223751 # 0.7% l2 bound
l2 miss 687864109 # 0.1% l3 bound
l3 miss 373883226 # 0.1% dram bound
store_stalls 937830913 # 0.2% store bound
Process overview shows espeak-ng as the driver process
360 processes
8 espeak-ng 171.86 13.74
68 clinfo 16.53 5.99
38 vulkaninfo 1.11 1.52
4 vulkani:disk$0 0.11 0.16
6 glxinfo:gdrv0 0.06 0.10
6 glxinfo:gl0 0.06 0.10
2 llvmpipe-0 0.06 0.08
2 llvmpipe-1 0.06 0.08
2 llvmpipe-10 0.06 0.08
2 llvmpipe-11 0.06 0.08
2 llvmpipe-12 0.06 0.08
2 llvmpipe-13 0.06 0.08
2 llvmpipe-14 0.06 0.08
2 llvmpipe-15 0.06 0.08
2 llvmpipe-2 0.06 0.08
2 llvmpipe-3 0.06 0.08
2 llvmpipe-4 0.06 0.08
2 llvmpipe-5 0.06 0.08
2 llvmpipe-6 0.06 0.08
2 llvmpipe-7 0.06 0.08
2 llvmpipe-8 0.06 0.08
2 llvmpipe-9 0.06 0.08
6 php 0.06 0.07
6 clang 0.04 0.08
2 glxinfo 0.04 0.05
2 glxinfo:cs0 0.04 0.05
2 glxinfo:disk$0 0.04 0.05
2 glxinfo:sh0 0.04 0.05
2 glxinfo:shlo0 0.04 0.05
3 rocminfo 0.03 0.00
1 lspci 0.00 0.02
82 sh 0.00 0.00
13 gcc 0.00 0.00
9 gsettings 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 phoronix-test-s 0.00 0.00
4 espeak 0.00 0.00
4 gmain 0.00 0.00
3 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 date 0.00 0.00
1 dirname 0.00 0.00
1 dmesg 0.00 0.00
1 dmidecode 0.00 0.00
1 grep 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 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
Computation blocks
971105) espeak cpu=4 start=5.63 finish=28.69
971106) espeak-ng cpu=6 start=5.63 finish=28.69
971107) espeak-ng cpu=13 start=5.64 finish=28.69
971108) espeak cpu=15 start=32.69 finish=56.04
971109) espeak-ng cpu=0 start=32.70 finish=56.04
971110) espeak-ng cpu=2 start=32.70 finish=56.04
971111) espeak cpu=15 start=60.05 finish=83.45
971112) espeak-ng cpu=0 start=60.05 finish=83.45
971113) espeak-ng cpu=11 start=60.05 finish=83.45
971114) espeak cpu=15 start=87.46 finish=110.82
971115) espeak-ng cpu=0 start=87.46 finish=110.82
971116) espeak-ng cpu=10 start=87.46 finish=110.82
