blender is a SPEC CPU(R) benchmark described here and written in C and C++. The workload runs on all logical cores.
Topdown profile shows moderate retirement rate with backend stalls. Also a somewhat higher branch mis-prediction ratio.
AMD metrics show a large number of conditional branches, a lot of floating point. L2 access in contrast is lower.
elapsed 1003.543
on_cpu 0.976 # 15.62 / 16 cores
utime 15577.792
stime 93.492
nvcsw 25699 # 14.13%
nivcsw 156210 # 85.87%
inblock 0 # 0.00/sec
onblock 657472 # 655.15/sec
cpu-clock 15672524593811 # 15672.525 seconds
task-clock 15672677832025 # 15672.678 seconds
page faults 31056598 # 1981.576/sec
context switches 181238 # 11.564/sec
cpu migrations 217 # 0.014/sec
major page faults 3799 # 0.242/sec
minor page faults 31052799 # 1981.333/sec
alignment faults 0 # 0.000/sec
emulation faults 0 # 0.000/sec
branches 9162902970976 # 134.627 branches per 1000 inst
branch misses 191136129020 # 2.09% branch miss
conditional 8195526125542 # 120.414 conditional branches per 1000 inst
indirect 85457359205 # 1.256 indirect branches per 1000 inst
cpu-cycles 62796772217200 # 3.88 GHz
instructions 68050948821278 # 1.08 IPC
slots 125582309615328 #
retiring 22462534406699 # 17.9% (24.9%)
-- ucode 4511747160 # 0.0%
-- fastpath 22458022659539 # 17.9%
frontend 5992219329471 # 4.8% ( 6.6%)
-- latency 4651956387924 # 3.7%
-- bandwidth 1340262941547 # 1.1%
backend 56277781669765 # 44.8% (62.3%)
-- cpu 17120809186613 # 13.6%
-- memory 39156972483152 # 31.2%
speculation 5623383914045 # 4.5% ( 6.2%)
-- branch mispredict 5590516227249 # 4.5%
-- pipeline restart 32867686796 # 0.0%
smt-contention 35226327822583 # 28.1% ( 0.0%)
cpu-cycles 62413646220576 # 3.88 GHz
instructions 68057299082957 # 1.09 IPC
instructions 22689634557097 # 31.225 l2 access per 1000 inst
l2 hit from l1 625483301949 # 15.56% l2 miss
l2 miss from l1 61732557357 #
l2 hit from l2 pf 34508483022 #
l3 hit from l2 pf 15862924695 #
l3 miss from l2 pf 32620726863 #
instructions 22676887930929 # 397.608 float per 1000 inst
float 512 236 # 0.000 AVX-512 per 1000 inst
float 256 194075558 # 0.009 AVX-256 per 1000 inst
float 128 9016321382594 # 397.600 AVX-128 per 1000 inst
float MMX 0 # 0.000 MMX per 1000 inst
float scalar 0 # 0.000 scalar per 1000 inst
instructions 68048780839108 #
opcache 11281642777070 # 165.788 opcache per 1000 inst
opcache miss 110863695024 # 1.0% opcache miss rate
l1 dTLB miss 795057958815 # 11.684 L1 dTLB per 1000 inst
l2 dTLB miss 20403293260 # 0.300 L2 dTLB per 1000 inst
instructions 68048507612293 #
icache 177196855525 # 2.604 icache per 1000 inst
icache miss 50061354268 # 28.3% icache miss rate
l1 iTLB miss 4181404456 # 0.061 L1 iTLB per 1000 inst
l2 iTLB miss 0 # 0.000 L2 iTLB per 1000 inst
tlb flush 10990627 # 0.000 TLB flush per 1000 inst
Process overview shows blender_r_base. as the primary process.
691 processes
48 blender_r_base. 15538.72 89.32
71 specperl 17.90 1.95
48 imagevalidate_5 1.20 0.10
2 clang 0.02 0.00
10 ps 0.01 0.01
2 clang++ 0.01 0.01
1 lsb_release 0.01 0.00
225 sh 0.00 0.00
54 specrxp 0.00 0.00
48 bash 0.00 0.00
41 specinvoke 0.00 0.00
22 cat 0.00 0.00
21 grep 0.00 0.00
12 uniq 0.00 0.00
11 sort 0.00 0.00
10 expand 0.00 0.00
7 specmake 0.00 0.00
6 pwd 0.00 0.00
5 basename 0.00 0.00
5 systemctl 0.00 0.00
4 rm 0.00 0.00
4 specpp 0.00 0.00
4 uname 0.00 0.00
3 dirname 0.00 0.00
3 dmidecode 0.00 0.00
3 lscpu 0.00 0.00
2 df 0.00 0.00
2 dpkg 0.00 0.00
2 runcpu 0.00 0.00
2 specsha512sum 0.00 0.00
2 specxz 0.00 0.00
2 who 0.00 0.00
1 cpupower 0.00 0.00
1 head 0.00 0.00
1 logname 0.00 0.00
1 ls 0.00 0.00
1 numactl 0.00 0.00
1 sysctl 0.00 0.00
1 w 0.00 0.00
1 wc 0.00 0.00
1 which 0.00 0.00
0 processes running
53 maximum processes
specinvoke fires up the blender processes in parallel
430775) specinvoke cpu=5 start=333.05 finish=660.87
430777) sh cpu=0 start=333.05 finish=656.15
430785) bash cpu=0 start=333.06 finish=656.15
430809) blender_r_base. cpu=0 start=333.06 finish=656.10
430778) sh cpu=5 start=333.05 finish=659.52
430786) bash cpu=1 start=333.06 finish=659.52
430810) blender_r_base. cpu=1 start=333.06 finish=659.47
430779) sh cpu=0 start=333.05 finish=659.91
430787) bash cpu=2 start=333.06 finish=659.91
430811) blender_r_base. cpu=2 start=333.06 finish=659.87
430780) sh cpu=5 start=333.05 finish=659.62
430788) bash cpu=3 start=333.06 finish=659.62
430813) blender_r_base. cpu=3 start=333.06 finish=659.57
430781) sh cpu=10 start=333.05 finish=660.86
430796) bash cpu=4 start=333.06 finish=660.86
430816) blender_r_base. cpu=4 start=333.06 finish=660.81
430782) sh cpu=5 start=333.05 finish=658.54
430794) bash cpu=5 start=333.06 finish=658.54
430815) blender_r_base. cpu=5 start=333.06 finish=658.50
430783) sh cpu=13 start=333.05 finish=659.24
430791) bash cpu=6 start=333.06 finish=659.24
430812) blender_r_base. cpu=6 start=333.06 finish=659.19
430784) sh cpu=6 start=333.06 finish=659.63
430797) bash cpu=7 start=333.06 finish=659.63
430818) blender_r_base. cpu=7 start=333.06 finish=659.57
430789) sh cpu=8 start=333.06 finish=655.29
430799) bash cpu=8 start=333.06 finish=655.29
430814) blender_r_base. cpu=8 start=333.06 finish=655.23
430790) sh cpu=7 start=333.06 finish=660.06
430800) bash cpu=9 start=333.06 finish=660.06
430817) blender_r_base. cpu=9 start=333.06 finish=660.02
430792) sh cpu=3 start=333.06 finish=659.83
430802) bash cpu=10 start=333.06 finish=659.83
430819) blender_r_base. cpu=10 start=333.06 finish=659.77
430793) sh cpu=13 start=333.06 finish=660.11
430804) bash cpu=11 start=333.06 finish=660.11
430820) blender_r_base. cpu=11 start=333.06 finish=660.08
430795) sh cpu=11 start=333.06 finish=660.87
430805) bash cpu=12 start=333.06 finish=660.87
430821) blender_r_base. cpu=12 start=333.06 finish=660.82
430798) sh cpu=8 start=333.06 finish=657.84
430806) bash cpu=13 start=333.06 finish=657.84
430822) blender_r_base. cpu=13 start=333.06 finish=657.78
430801) sh cpu=14 start=333.06 finish=658.27
430807) bash cpu=14 start=333.06 finish=658.27
430823) blender_r_base. cpu=14 start=333.06 finish=658.21
430803) sh cpu=14 start=333.06 finish=659.98
430808) bash cpu=15 start=333.06 finish=659.98
430824) blender_r_base. cpu=15 start=333.06 finish=659.94