% lstopo -v Machine (P#0 total=333921024KB PlatformName=PowerNV PlatformModel="PowerNV 8335-GTW" Backend=Linux LinuxCgroup=/ OSName=Linux OSRelease=4.11.0-44.2.1.el7a.ppc64le OSVersion="#1 SMP Thu Nov 9 02:48:01 EST 2017" HostName=sierra400 Architecture=ppc64le hwlocVersion=1.11.7 ProcessName=lstopo) Group0 L#0 (total=267860736KB) NUMANode L#0 (P#0 local=133909504KB total=133909504KB) Package L#0 (P#0 CPUModel="POWER9 (raw), altivec supported" CPURevision="2.1 (pvr 004e 1201)") L3Cache L#0 (size=10240KB linesize=0) L2Cache L#0 (size=512KB linesize=0) L1dCache L#0 (size=32KB linesize=128 ways=32) L1iCache L#0 (size=32KB linesize=128 ways=32) Core L#0 (P#4) PU L#0 (P#0) PU L#1 (P#1) PU L#2 (P#2) PU L#3 (P#3) L3Cache L#1 (size=10240KB linesize=0) L2Cache L#1 (size=512KB linesize=0) L1dCache L#1 (size=32KB linesize=128 ways=32) L1iCache L#1 (size=32KB linesize=128 ways=32) Core L#1 (P#8) PU L#4 (P#4) PU L#5 (P#5) PU L#6 (P#6) PU L#7 (P#7) L1dCache L#2 (size=32KB linesize=128 ways=32) L1iCache L#2 (size=32KB linesize=128 ways=32) Core L#2 (P#12) PU L#8 (P#8) PU L#9 (P#9) PU L#10 (P#10) PU L#11 (P#11) L3Cache L#2 (size=10240KB linesize=0) L2Cache L#2 (size=512KB linesize=0) L1dCache L#3 (size=32KB linesize=128 ways=32) L1iCache L#3 (size=32KB linesize=128 ways=32) Core L#3 (P#16) PU L#12 (P#12) PU L#13 (P#13) PU L#14 (P#14) PU L#15 (P#15) L1dCache L#4 (size=32KB linesize=128 ways=32) L1iCache L#4 (size=32KB linesize=128 ways=32) Core L#4 (P#20) PU L#16 (P#16) PU L#17 (P#17) PU L#18 (P#18) PU L#19 (P#19) L3Cache L#3 (size=10240KB linesize=0) L2Cache L#3 (size=512KB linesize=0) L1dCache L#5 (size=32KB linesize=128 ways=32) L1iCache L#5 (size=32KB linesize=128 ways=32) Core L#5 (P#24) PU L#20 (P#20) PU L#21 (P#21) PU L#22 (P#22) PU L#23 (P#23) L1dCache L#6 (size=32KB linesize=128 ways=32) L1iCache L#6 (size=32KB linesize=128 ways=32) Core L#6 (P#28) PU L#24 (P#24) PU L#25 (P#25) PU L#26 (P#26) PU L#27 (P#27) L3Cache L#4 (size=10240KB linesize=0) L2Cache L#4 (size=512KB linesize=0) L1dCache L#7 (size=32KB linesize=128 ways=32) L1iCache L#7 (size=32KB linesize=128 ways=32) Core L#7 (P#32) PU L#28 (P#28) PU L#29 (P#29) PU L#30 (P#30) PU L#31 (P#31) L1dCache L#8 (size=32KB linesize=128 ways=32) L1iCache L#8 (size=32KB linesize=128 ways=32) Core L#8 (P#36) PU L#32 (P#32) PU L#33 (P#33) PU L#34 (P#34) PU L#35 (P#35) L3Cache L#5 (size=10240KB linesize=0) L2Cache L#5 (size=512KB linesize=0) L1dCache L#9 (size=32KB linesize=128 ways=32) L1iCache L#9 (size=32KB linesize=128 ways=32) Core L#9 (P#40) PU L#36 (P#36) PU L#37 (P#37) PU L#38 (P#38) PU L#39 (P#39) L1dCache L#10 (size=32KB linesize=128 ways=32) L1iCache L#10 (size=32KB linesize=128 ways=32) Core L#10 (P#44) PU L#40 (P#40) PU L#41 (P#41) PU L#42 (P#42) PU L#43 (P#43) L3Cache L#6 (size=10240KB linesize=0) L2Cache L#6 (size=512KB linesize=0) L1dCache L#11 (size=32KB linesize=128 ways=32) L1iCache L#11 (size=32KB linesize=128 ways=32) Core L#11 (P#52) PU L#44 (P#44) PU L#45 (P#45) PU L#46 (P#46) PU L#47 (P#47) L3Cache L#7 (size=10240KB linesize=0) L2Cache L#7 (size=512KB linesize=0) L1dCache L#12 (size=32KB linesize=128 ways=32) L1iCache L#12 (size=32KB linesize=128 ways=32) Core L#12 (P#56) PU L#48 (P#48) PU L#49 (P#49) PU L#50 (P#50) PU L#51 (P#51) L1dCache L#13 (size=32KB linesize=128 ways=32) L1iCache L#13 (size=32KB linesize=128 ways=32) Core L#13 (P#60) PU L#52 (P#52) PU L#53 (P#53) PU L#54 (P#54) PU L#55 (P#55) L3Cache L#8 (size=10240KB linesize=0) L2Cache L#8 (size=512KB linesize=0) L1dCache L#14 (size=32KB linesize=128 ways=32) L1iCache L#14 (size=32KB linesize=128 ways=32) Core L#14 (P#64) PU L#56 (P#56) PU L#57 (P#57) PU L#58 (P#58) PU L#59 (P#59) L1dCache L#15 (size=32KB linesize=128 ways=32) L1iCache L#15 (size=32KB linesize=128 ways=32) Core L#15 (P#68) PU L#60 (P#60) PU L#61 (P#61) PU L#62 (P#62) PU L#63 (P#63) L3Cache L#9 (size=10240KB linesize=0) L2Cache L#9 (size=512KB linesize=0) L1dCache L#16 (size=32KB linesize=128 ways=32) L1iCache L#16 (size=32KB linesize=128 ways=32) Core L#16 (P#72) PU L#64 (P#64) PU L#65 (P#65) PU L#66 (P#66) PU L#67 (P#67) L1dCache L#17 (size=32KB linesize=128 ways=32) L1iCache L#17 (size=32KB linesize=128 ways=32) Core L#17 (P#76) PU L#68 (P#68) PU L#69 (P#69) PU L#70 (P#70) PU L#71 (P#71) L3Cache L#10 (size=10240KB linesize=0) L2Cache L#10 (size=512KB linesize=0) L1dCache L#18 (size=32KB linesize=128 ways=32) L1iCache L#18 (size=32KB linesize=128 ways=32) Core L#18 (P#80) PU L#72 (P#72) PU L#73 (P#73) PU L#74 (P#74) PU L#75 (P#75) L1dCache L#19 (size=32KB linesize=128 ways=32) L1iCache L#19 (size=32KB linesize=128 ways=32) Core L#19 (P#84) PU L#76 (P#76) PU L#77 (P#77) PU L#78 (P#78) PU L#79 (P#79) L3Cache L#11 (size=10240KB linesize=0) L2Cache L#11 (size=512KB linesize=0) L1dCache L#20 (size=32KB linesize=128 ways=32) L1iCache L#20 (size=32KB linesize=128 ways=32) Core L#20 (P#88) PU L#80 (P#80) PU L#81 (P#81) PU L#82 (P#82) PU L#83 (P#83) L1dCache L#21 (size=32KB linesize=128 ways=32) L1iCache L#21 (size=32KB linesize=128 ways=32) Core L#21 (P#92) PU L#84 (P#84) PU L#85 (P#85) PU L#86 (P#86) PU L#87 (P#87) Bridge Host->PCI L#0 (P#0 buses=0000:[00-01]) Bridge PCI->PCI (P#0 busid=0000:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0000:[01-01]) PCI 144d:a822 (P#4096 busid=0000:01:00.0 class=0108(NVMExp)) Bridge Host->PCI L#2 (P#2 buses=0002:[00-02]) Bridge PCI->PCI (P#2097152 busid=0002:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0002:[01-02]) Bridge PCI->PCI (P#2101248 busid=0002:01:00.0 id=1a03:1150 class=0604(PCI_B) buses=0002:[02-02]) PCI 1a03:2000 (P#2105344 busid=0002:02:00.0 class=0300(VGA)) GPU L#0 "card4" GPU L#1 "controlD68" Bridge Host->PCI L#5 (P#3 buses=0003:[00-01]) Bridge PCI->PCI (P#3145728 busid=0003:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0003:[01-01]) PCI 15b3:1019 (P#3149824 busid=0003:01:00.0 class=0207(IB)) Network L#2 (Address=00:00:00:86:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:6d:98:dc Port=1) "hsi0" OpenFabrics L#3 (NodeGUID=ec0d:9a03:006d:98dc SysImageGUID=ec0d:9a03:006d:98dc Port1State=4 Port1LID=0xe33 Port1LMC=0 Port1GID0=fe80:0000:0000:0000:ec0d:9a03:006d:98dc) "mlx5_0" PCI 15b3:1019 (P#3149825 busid=0003:01:00.1 class=0207(IB)) Network L#4 (Address=00:00:08:86:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:6d:98:dd Port=1) "hsi1" OpenFabrics L#5 (NodeGUID=ec0d:9a03:006d:98dd SysImageGUID=ec0d:9a03:006d:98dc Port1State=4 Port1LID=0xe41 Port1LMC=0 Port1GID0=fe80:0000:0000:0000:ec0d:9a03:006d:98dd) "mlx5_1" Bridge Host->PCI L#7 (P#4 buses=0004:[00-0a]) Bridge PCI->PCI (P#4194304 busid=0004:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0004:[01-0a]) Bridge PCI->PCI (P#4198400 busid=0004:01:00.0 id=10b5:8725 class=0604(PCI_B) buses=0004:[02-0a]) Bridge PCI->PCI (P#4202528 busid=0004:02:02.0 id=10b5:8725 class=0604(PCI_B) buses=0004:[03-03]) PCI 1b4b:9235 (P#4206592 busid=0004:03:00.0 class=0106(SATA)) Bridge PCI->PCI (P#4202656 busid=0004:02:0a.0 id=10b5:8725 class=0604(PCI_B) buses=0004:[04-04]) PCI 10de:1db1 (P#4210688 busid=0004:04:00.0 class=0302(3D)) GPU L#6 "renderD128" GPU L#7 "card0" Bridge PCI->PCI (P#4202672 busid=0004:02:0b.0 id=10b5:8725 class=0604(PCI_B) buses=0004:[05-05]) PCI 10de:1db1 (P#4214784 busid=0004:05:00.0 class=0302(3D)) GPU L#8 "card1" GPU L#9 "renderD129" Bridge Host->PCI L#13 (P#5 buses=0005:[00-01]) Bridge PCI->PCI (P#5242880 busid=0005:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0005:[01-01]) PCI 14e4:1657 (P#5246976 busid=0005:01:00.0 class=0200(Ether)) Network L#10 (Address=70:e2:84:14:54:8b) "enP5p1s0f0" PCI 14e4:1657 (P#5246977 busid=0005:01:00.1 class=0200(Ether)) Network L#11 (Address=70:e2:84:14:54:8c) "enP5p1s0f1" NUMANode L#1 (P#8 local=133951232KB total=133951232KB) Package L#1 (P#8 CPUModel="POWER9 (raw), altivec supported" CPURevision="2.1 (pvr 004e 1201)") L3Cache L#12 (size=10240KB linesize=0) L2Cache L#12 (size=512KB linesize=0) L1dCache L#22 (size=32KB linesize=128 ways=32) L1iCache L#22 (size=32KB linesize=128 ways=32) Core L#22 (P#2048) PU L#88 (P#88) PU L#89 (P#89) PU L#90 (P#90) PU L#91 (P#91) L1dCache L#23 (size=32KB linesize=128 ways=32) L1iCache L#23 (size=32KB linesize=128 ways=32) Core L#23 (P#2052) PU L#92 (P#92) PU L#93 (P#93) PU L#94 (P#94) PU L#95 (P#95) L3Cache L#13 (size=10240KB linesize=0) L2Cache L#13 (size=512KB linesize=0) L1dCache L#24 (size=32KB linesize=128 ways=32) L1iCache L#24 (size=32KB linesize=128 ways=32) Core L#24 (P#2056) PU L#96 (P#96) PU L#97 (P#97) PU L#98 (P#98) PU L#99 (P#99) L1dCache L#25 (size=32KB linesize=128 ways=32) L1iCache L#25 (size=32KB linesize=128 ways=32) Core L#25 (P#2060) PU L#100 (P#100) PU L#101 (P#101) PU L#102 (P#102) PU L#103 (P#103) L3Cache L#14 (size=10240KB linesize=0) L2Cache L#14 (size=512KB linesize=0) L1dCache L#26 (size=32KB linesize=128 ways=32) L1iCache L#26 (size=32KB linesize=128 ways=32) Core L#26 (P#2064) PU L#104 (P#104) PU L#105 (P#105) PU L#106 (P#106) PU L#107 (P#107) L1dCache L#27 (size=32KB linesize=128 ways=32) L1iCache L#27 (size=32KB linesize=128 ways=32) Core L#27 (P#2068) PU L#108 (P#108) PU L#109 (P#109) PU L#110 (P#110) PU L#111 (P#111) L3Cache L#15 (size=10240KB linesize=0) L2Cache L#15 (size=512KB linesize=0) L1dCache L#28 (size=32KB linesize=128 ways=32) L1iCache L#28 (size=32KB linesize=128 ways=32) Core L#28 (P#2072) PU L#112 (P#112) PU L#113 (P#113) PU L#114 (P#114) PU L#115 (P#115) L1dCache L#29 (size=32KB linesize=128 ways=32) L1iCache L#29 (size=32KB linesize=128 ways=32) Core L#29 (P#2076) PU L#116 (P#116) PU L#117 (P#117) PU L#118 (P#118) PU L#119 (P#119) L3Cache L#16 (size=10240KB linesize=0) L2Cache L#16 (size=512KB linesize=0) L1dCache L#30 (size=32KB linesize=128 ways=32) L1iCache L#30 (size=32KB linesize=128 ways=32) Core L#30 (P#2080) PU L#120 (P#120) PU L#121 (P#121) PU L#122 (P#122) PU L#123 (P#123) L1dCache L#31 (size=32KB linesize=128 ways=32) L1iCache L#31 (size=32KB linesize=128 ways=32) Core L#31 (P#2084) PU L#124 (P#124) PU L#125 (P#125) PU L#126 (P#126) PU L#127 (P#127) L3Cache L#17 (size=10240KB linesize=0) L2Cache L#17 (size=512KB linesize=0) L1dCache L#32 (size=32KB linesize=128 ways=32) L1iCache L#32 (size=32KB linesize=128 ways=32) Core L#32 (P#2088) PU L#128 (P#128) PU L#129 (P#129) PU L#130 (P#130) PU L#131 (P#131) L1dCache L#33 (size=32KB linesize=128 ways=32) L1iCache L#33 (size=32KB linesize=128 ways=32) Core L#33 (P#2092) PU L#132 (P#132) PU L#133 (P#133) PU L#134 (P#134) PU L#135 (P#135) L3Cache L#18 (size=10240KB linesize=0) L2Cache L#18 (size=512KB linesize=0) L1dCache L#34 (size=32KB linesize=128 ways=32) L1iCache L#34 (size=32KB linesize=128 ways=32) Core L#34 (P#2096) PU L#136 (P#136) PU L#137 (P#137) PU L#138 (P#138) PU L#139 (P#139) L1dCache L#35 (size=32KB linesize=128 ways=32) L1iCache L#35 (size=32KB linesize=128 ways=32) Core L#35 (P#2100) PU L#140 (P#140) PU L#141 (P#141) PU L#142 (P#142) PU L#143 (P#143) L3Cache L#19 (size=10240KB linesize=0) L2Cache L#19 (size=512KB linesize=0) L1dCache L#36 (size=32KB linesize=128 ways=32) L1iCache L#36 (size=32KB linesize=128 ways=32) Core L#36 (P#2104) PU L#144 (P#144) PU L#145 (P#145) PU L#146 (P#146) PU L#147 (P#147) L1dCache L#37 (size=32KB linesize=128 ways=32) L1iCache L#37 (size=32KB linesize=128 ways=32) Core L#37 (P#2108) PU L#148 (P#148) PU L#149 (P#149) PU L#150 (P#150) PU L#151 (P#151) L3Cache L#20 (size=10240KB linesize=0) L2Cache L#20 (size=512KB linesize=0) L1dCache L#38 (size=32KB linesize=128 ways=32) L1iCache L#38 (size=32KB linesize=128 ways=32) Core L#38 (P#2112) PU L#152 (P#152) PU L#153 (P#153) PU L#154 (P#154) PU L#155 (P#155) L1dCache L#39 (size=32KB linesize=128 ways=32) L1iCache L#39 (size=32KB linesize=128 ways=32) Core L#39 (P#2116) PU L#156 (P#156) PU L#157 (P#157) PU L#158 (P#158) PU L#159 (P#159) L3Cache L#21 (size=10240KB linesize=0) L2Cache L#21 (size=512KB linesize=0) L1dCache L#40 (size=32KB linesize=128 ways=32) L1iCache L#40 (size=32KB linesize=128 ways=32) Core L#40 (P#2124) PU L#160 (P#160) PU L#161 (P#161) PU L#162 (P#162) PU L#163 (P#163) L3Cache L#22 (size=10240KB linesize=0) L2Cache L#22 (size=512KB linesize=0) L1dCache L#41 (size=32KB linesize=128 ways=32) L1iCache L#41 (size=32KB linesize=128 ways=32) Core L#41 (P#2128) PU L#164 (P#164) PU L#165 (P#165) PU L#166 (P#166) PU L#167 (P#167) L1dCache L#42 (size=32KB linesize=128 ways=32) L1iCache L#42 (size=32KB linesize=128 ways=32) Core L#42 (P#2132) PU L#168 (P#168) PU L#169 (P#169) PU L#170 (P#170) PU L#171 (P#171) L3Cache L#23 (size=10240KB linesize=0) L2Cache L#23 (size=512KB linesize=0) L1dCache L#43 (size=32KB linesize=128 ways=32) L1iCache L#43 (size=32KB linesize=128 ways=32) Core L#43 (P#2136) PU L#172 (P#172) PU L#173 (P#173) PU L#174 (P#174) PU L#175 (P#175) Bridge Host->PCI L#15 (P#9 buses=0033:[00-01]) Bridge PCI->PCI (P#53477376 busid=0033:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0033:[01-01]) PCI 15b3:1019 (P#53481472 busid=0033:01:00.0 class=0207(IB)) Network L#12 (Address=00:00:04:86:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:6d:98:de Port=1) "hsi2" OpenFabrics L#13 (NodeGUID=ec0d:9a03:006d:98de SysImageGUID=ec0d:9a03:006d:98dc Port1State=4 Port1LID=0xe4e Port1LMC=0 Port1GID0=fe80:0000:0000:0000:ec0d:9a03:006d:98de) "mlx5_2" PCI 15b3:1019 (P#53481473 busid=0033:01:00.1 class=0207(IB)) Network L#14 (Address=00:00:0c:86:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:6d:98:df Port=1) "hsi3" OpenFabrics L#15 (NodeGUID=ec0d:9a03:006d:98df SysImageGUID=ec0d:9a03:006d:98dc Port1State=4 Port1LID=0xe51 Port1LMC=0 Port1GID0=fe80:0000:0000:0000:ec0d:9a03:006d:98df) "mlx5_3" Bridge Host->PCI L#17 (P#11 buses=0035:[00-09]) Bridge PCI->PCI (P#55574528 busid=0035:00:00.0 id=1014:04c1 class=0604(PCI_B) buses=0035:[01-09]) Bridge PCI->PCI (P#55578624 busid=0035:01:00.0 id=10b5:8725 class=0604(PCI_B) buses=0035:[02-09]) Bridge PCI->PCI (P#55582784 busid=0035:02:04.0 id=10b5:8725 class=0604(PCI_B) buses=0035:[03-03]) PCI 10de:1db1 (P#55586816 busid=0035:03:00.0 class=0302(3D)) GPU L#16 "card2" GPU L#17 "renderD130" Bridge PCI->PCI (P#55582800 busid=0035:02:05.0 id=10b5:8725 class=0604(PCI_B) buses=0035:[04-04]) PCI 10de:1db1 (P#55590912 busid=0035:04:00.0 class=0302(3D)) GPU L#18 "card3" GPU L#19 "renderD131" NUMANode L#2 (P#252 local=16515072KB total=16515072KB) NUMANode L#3 (P#253 local=16515072KB total=16515072KB) NUMANode L#4 (P#254 local=16515072KB total=16515072KB) NUMANode L#5 (P#255 local=16515072KB total=16515072KB) depth 0: 1 Machine (type #1) depth 1: 1 Group0 (type #7) depth 2: 6 NUMANode (type #2) depth 3: 2 Package (type #3) depth 4: 24 L3Cache (type #4) depth 5: 24 L2Cache (type #4) depth 6: 44 L1dCache (type #4) depth 7: 44 L1iCache (type #4) depth 8: 44 Core (type #5) depth 9: 176 PU (type #6) Special depth -3: 22 Bridge (type #9) Special depth -4: 13 PCI Device (type #10) Special depth -5: 20 OS Device (type #11) relative latency matrix between NUMANodes (depth 2) by logical indexes: index 0 1 2 3 4 5 0 1.000 4.000 8.000 8.000 8.000 8.000 1 4.000 1.000 8.000 8.000 8.000 8.000 2 8.000 8.000 1.000 8.000 8.000 8.000 3 8.000 8.000 8.000 1.000 8.000 8.000 4 8.000 8.000 8.000 8.000 1.000 8.000 5 8.000 8.000 8.000 8.000 8.000 1.000