{"id":220,"date":"2024-01-05T09:55:51","date_gmt":"2024-01-05T09:55:51","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=220"},"modified":"2024-01-05T11:00:19","modified_gmt":"2024-01-05T11:00:19","slug":"lammps","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/lammps\/","title":{"rendered":"lammps"},"content":{"rendered":"\n<p>Lammps is molecular dynamics code. A steady profile with a very high amount of branch mis-prediction.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1280\" height=\"960\" src=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/01\/amdtopdown-16.png\" alt=\"\" class=\"wp-image-221\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/01\/amdtopdown-16.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/01\/amdtopdown-16-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/01\/amdtopdown-16-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics show a lot of floating point and a moderate number of branches with a high misprediction ratio and a relatively higher IPC<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>mev@augusta:~\/source\/wspy\/workload\/phoronix\/lammps-perf$ more amdtopdown.txt \nelapsed              3607.385\non_cpu               0.497          # 7.95 \/ 16 cores\nutime                28422.382\nstime                266.904\nnvcsw                34931          # 31.82%\nnivcsw               74834          # 68.18%\ninblock              808            # 0.22\/sec\nonblock              149424         # 41.42\/sec\ncpu-clock            28689723667470 # 28689.724 seconds\ntask-clock           28689830702354 # 28689.831 seconds\npage faults          320132         # 11.158\/sec\ncontext switches     127549         # 4.446\/sec\ncpu migrations       42780          # 1.491\/sec\nmajor page faults    318            # 0.011\/sec\nminor page faults    319814         # 11.147\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             23793575093943 # 98.234 branches per 1000 inst\nbranch misses        851710978452   # 3.58% branch miss\nconditional          21073569115948 # 87.004 conditional branches per 1000 inst\nindirect             230267785218   # 0.951 indirect branches per 1000 inst\ncpu-cycles           121063342816018 # 2.09 GHz\ninstructions         243280310806043 # 2.01 IPC\nslots                242118479094498 #\nretiring             81755137984811 # 33.8% (33.8%)\n-- ucode             12236037330    #     0.0%\n-- fastpath          81742901947481 #    33.8%\nfrontend             23418316746824 #  9.7% ( 9.7%)\n-- latency           12051836963268 #     5.0%\n-- bandwidth         11366479783556 #     4.7%\nbackend              85433362902042 # 35.3% (35.3%)\n-- cpu               51382962662189 #    21.2%\n-- memory            34050400239853 #    14.1%\nspeculation          51385443415715 # 21.2% (21.2%)\n-- branch mispredict 51082009983348 #    21.1%\n-- pipeline restart  303433432367   #     0.1%\nsmt-contention       126136389092   #  0.1% ( 0.0%)\ncpu-cycles           120737853365517 # 2.09 GHz\ninstructions         241988029059643 # 2.00 IPC\ninstructions         80671577903670 # 63.872 l2 access per 1000 inst\nl2 hit from l1       3637543520009  # 3.39% l2 miss\nl2 miss from l1      58163463293    #\nl2 hit from l2 pf    1398780866072  #\nl3 hit from l2 pf    61743676247    #\nl3 miss from l2 pf   54570665759    #\ninstructions         80620315692299 # 332.278 float per 1000 inst\nfloat 512            34             # 0.000 AVX-512 per 1000 inst\nfloat 256            1002           # 0.000 AVX-256 per 1000 inst\nfloat 128            26788381930153 # 332.278 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         0              # 0.000 scalar per 1000 inst\n<\/code><\/pre>\n\n\n\n<p>Intel metrics show a particularly high IPC and more time overall in cores.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              5234.464\non_cpu               0.747          # 11.96 \/ 16 cores\nutime                61938.747\nstime                643.461\nnvcsw                55070          # 27.73%\nnivcsw               143501         # 72.27%\ninblock              296264         # 56.60\/sec\nonblock              149624         # 28.58\/sec\ncpu-clock            62583082310865 # 62583.082 seconds\ntask-clock           62583209388366 # 62583.209 seconds\npage faults          340254         # 5.437\/sec\ncontext switches     224519         # 3.588\/sec\ncpu migrations       45949          # 0.734\/sec\nmajor page faults    2768           # 0.044\/sec\nminor page faults    337486         # 5.393\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             48031836251892 # 124.988 branches per 1000 inst\nbranch misses        875770490567   # 1.82% branch miss\nconditional          48031836267444 # 124.988 conditional branches per 1000 inst\nindirect             10260173632800 # 26.699 indirect branches per 1000 inst\nslots                359968213625054 #\nretiring             207191541248343 # 57.6% (57.6%)\n-- ucode             10580047628562 #     2.9%\n-- fastpath          196611493619781 #    54.6%\nfrontend             24396382454844 #  6.8% ( 6.8%)\n-- latency           9601924139766  #     2.7%\n-- bandwidth         14794458315078 #     4.1%\nbackend              52986590450881 # 14.7% (14.7%)\n-- cpu               45057192033341 #    12.5%\n-- memory            7929398417540  #     2.2%\nspeculation          76099342557612 # 21.1% (21.1%)\n-- branch mispredict 74687668037222 #    20.7%\n-- pipeline restart  1411674520390  #     0.4%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           166960049481381 # 1.99 GHz\ninstructions         597991842690222 # 3.58 IPC\nl2 access            4182134029230  # 19.354 l2 access per 1000 inst\nl2 miss              218708314722   # 5.23% l2 miss<\/code><\/pre>\n\n\n\n<p>Most time spent in the lmp process; we do abort prematurely at end of the run<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>237 processes\n\t 24 lmp                  28521.62   274.58\n\t 19 vulkaninfo               0.46     0.38\n\t  2 vulkani:disk$0           0.05     0.04\n\t  6 clang                    0.05     0.01\n\t  1 llvmpipe-0               0.03     0.02\n\t  1 llvmpipe-1               0.03     0.02\n\t  1 llvmpipe-10              0.03     0.02\n\t  1 llvmpipe-11              0.03     0.02\n\t  1 llvmpipe-12              0.03     0.02\n\t  1 llvmpipe-13              0.03     0.02\n\t  1 llvmpipe-14              0.03     0.02\n\t  1 llvmpipe-15              0.03     0.02\n\t  1 llvmpipe-2               0.03     0.02\n\t  1 llvmpipe-3               0.03     0.02\n\t  1 llvmpipe-4               0.03     0.02\n\t  1 llvmpipe-5               0.03     0.02\n\t  1 llvmpipe-6               0.03     0.02\n\t  1 llvmpipe-7               0.03     0.02\n\t  1 llvmpipe-8               0.03     0.02\n\t  1 llvmpipe-9               0.03     0.02\n\t 68 sh                       0.00     0.00\n\t 13 gcc                      0.00     0.00\n\t  9 stty                     0.00     0.00\n\t  8 systemd-detect-          0.00     0.00\n\t  7 gsettings                0.00     0.00\n\t  7 stat                     0.00     0.00\n\t  6 llvm-link                0.00     0.00\n\t  5 gmain                    0.00     0.00\n\t  4 glxinfo                  0.00     0.00\n\t  4 phoronix-test-s          0.00     0.00\n\t  3 dconf worker             0.00     0.00\n\t  2 grep                     0.00     0.00\n\t  2 which                    0.00     0.00\n\t  1 cc                       0.00     0.00\n\t  1 clinfo                   0.00     0.00\n\t  1 date                     0.00     0.00\n\t  1 dirname                  0.00     0.00\n\t  1 ifconfig                 0.00     0.00\n\t  1 ip                       0.00     0.00\n\t  1 lscpu                    0.00     0.00\n\t  1 mktemp                   0.00     0.00\n\t  1 ps                       0.00     0.00\n\t  1 qdbus                    0.00     0.00\n\t  1 readlink                 0.00     0.00\n\t  1 realpath                 0.00     0.00\n\t  1 sed                      0.00     0.00\n\t  1 setterm                  0.00     0.00\n\t  1 sort                     0.00     0.00\n\t  1 systemctl                0.00     0.00\n\t  1 template.sh              0.00     0.00\n\t  1 wc                       0.00     0.00\n14 processes running\n47 maximum processes\n<\/code><\/pre>\n\n\n\n<p>Following is the profile until the end.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      7702) ?? start=4.82  finish=0.00 \n        7703) ?? start=4.82  finish=0.00 \n          7707) ?? start=5.53  finish=0.00 \n          7708) ?? start=6.18  finish=0.00 \n          7709) ?? start=6.18  finish=0.00 \n          7710) lmp start=6.21  finish=1206.38\n            7712) lmp start=6.22  finish=1206.38\n            7716) lmp start=6.22  finish=1206.38\n          7711) lmp start=6.21  finish=1206.38\n            7714) lmp start=6.22  finish=1206.38\n            7719) lmp start=6.23  finish=1206.38\n          7713) lmp start=6.22  finish=1206.38\n            7717) lmp start=6.22  finish=1206.38\n            7721) lmp start=6.23  finish=1206.38\n          7715) lmp start=6.22  finish=1206.38\n            7722) lmp start=6.23  finish=1206.38\n            7725) lmp start=6.23  finish=1206.38\n          7718) lmp start=6.22  finish=1206.38\n            7724) lmp start=6.23  finish=1206.38\n            7728) lmp start=6.23  finish=1206.38\n          7720) lmp start=6.23  finish=1206.38\n            7727) lmp start=6.23  finish=1206.38\n            7730) lmp start=6.24  finish=1206.38\n          7723) lmp start=6.23  finish=1206.38\n            7729) lmp start=6.24  finish=1206.38\n            7732) lmp start=6.24  finish=1206.38\n          7726) lmp start=6.23  finish=1206.38\n            7731) lmp start=6.24  finish=1206.38\n            7733) lmp start=6.24  finish=1206.38\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Lammps is molecular dynamics code. A steady profile with a very high amount of branch mis-prediction. AMD metrics show a lot of floating point and a moderate number of branches with a high misprediction ratio and a relatively higher IPC <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/lammps\/\"><span class=\"more-msg\">Continue reading &rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":58,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-220","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/220","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/comments?post=220"}],"version-history":[{"count":2,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/220\/revisions"}],"predecessor-version":[{"id":259,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/220\/revisions\/259"}],"up":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/58"}],"wp:attachment":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/media?parent=220"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}