{"id":1242,"date":"2024-02-01T23:23:19","date_gmt":"2024-02-01T23:23:19","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=1242"},"modified":"2024-02-01T23:47:25","modified_gmt":"2024-02-01T23:47:25","slug":"qe","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/qe\/","title":{"rendered":"qe"},"content":{"rendered":"\n<p>Code for modeling electronic structures and materials. One benchmark and result is reported. The code is multi-threaded with a mix of one thread per hyperthreaded core and one per actual cor.e<\/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\/02\/systemtime-5.png\" alt=\"\" class=\"wp-image-1243\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/systemtime-5.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/systemtime-5-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/systemtime-5-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile shows a blur between being backend stalls and occasional higher retirement rates. Frontend stalls are low.<\/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\/02\/amdtopdown-5.png\" alt=\"\" class=\"wp-image-1244\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/amdtopdown-5.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/amdtopdown-5-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/02\/amdtopdown-5-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics confirm backend stalls split between memory and CPU. The code doesn&#8217;t have much floating point or branches.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              2009.644\non_cpu               0.892          # 14.27 \/ 16 cores\nutime                27794.710\nstime                888.971\nnvcsw                66275          # 16.07%\nnivcsw               346047         # 83.93%\ninblock              0              # 0.00\/sec\nonblock              705448         # 351.03\/sec\ncpu-clock            28689747750498 # 28689.748 seconds\ntask-clock           28690022795733 # 28690.023 seconds\npage faults          81383819       # 2836.659\/sec\ncontext switches     422153         # 14.714\/sec\ncpu migrations       16702          # 0.582\/sec\nmajor page faults    458            # 0.016\/sec\nminor page faults    81383361       # 2836.643\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             11096495451105 # 63.130 branches per 1000 inst\nbranch misses        81279292087    # 0.73% branch miss\nconditional          8071827699704  # 45.922 conditional branches per 1000 inst\nindirect             385031131344   # 2.191 indirect branches per 1000 inst\ncpu-cycles           108628710804268 # 3.38 GHz\ninstructions         175396936466455 # 1.61 IPC\nslots                217224690829842 #\nretiring             58560058869307 # 27.0% (36.9%)\n-- ucode             59432676601    #     0.0%\n-- fastpath          58500626192706 #    26.9%\nfrontend             11170785657522 #  5.1% ( 7.0%)\n-- latency           6588015021012  #     3.0%\n-- bandwidth         4582770636510  #     2.1%\nbackend              88710120335677 # 40.8% (55.9%)\n-- cpu               45427624864433 #    20.9%\n-- memory            43282495471244 #    19.9%\nspeculation          253387692929   #  0.1% ( 0.2%) low\n-- branch mispredict 240323593293   #     0.1%\n-- pipeline restart  13064099636    #     0.0%\nsmt-contention       58530240425718 # 26.9% ( 0.0%)\ncpu-cycles           108712417550875 # 3.37 GHz\ninstructions         175866105021602 # 1.62 IPC\ninstructions         58623162544056 # 66.044 l2 access per 1000 inst\nl2 hit from l1       2318656460357  # 17.18% l2 miss\nl2 miss from l1      74091602930    #\nl2 hit from l2 pf    961995367095   #\nl3 hit from l2 pf    499044508637   #\nl3 miss from l2 pf   92004877695    #\ninstructions         58611513941603 # 43.639 float per 1000 inst\nfloat 512            73             # 0.000 AVX-512 per 1000 inst\nfloat 256            666            # 0.000 AVX-256 per 1000 inst\nfloat 128            2557768514987  # 43.639 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<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              6333.440\non_cpu               0.742          # 11.88 \/ 16 cores\nutime                74750.330\nstime                473.297\nnvcsw                1313743        # 89.74%\nnivcsw               150279         # 10.26%\ninblock              30890000       # 4877.29\/sec\nonblock              694880         # 109.72\/sec\ncpu-clock            75222931189368 # 75222.931 seconds\ntask-clock           75223322994820 # 75223.323 seconds\npage faults          85985637       # 1143.072\/sec\ncontext switches     1495425        # 19.880\/sec\ncpu migrations       54829          # 0.729\/sec\nmajor page faults    1233961        # 16.404\/sec\nminor page faults    84751671       # 1126.667\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             45503197495161 # 71.793 branches per 1000 inst\nbranch misses        90982505997    # 0.20% branch miss\nconditional          45503197511129 # 71.793 conditional branches per 1000 inst\nindirect             11993405533405 # 18.923 indirect branches per 1000 inst\nslots                433838595012596 #\nretiring             283286737116435 # 65.3% (65.3%) high\n-- ucode             13222986405835 #     3.0%\n-- fastpath          270063750710600 #    62.2%\nfrontend             19439778785847 #  4.5% ( 4.5%) low\n-- latency           9361508360355  #     2.2%\n-- bandwidth         10078270425492 #     2.3%\nbackend              112743375337721 # 26.0% (26.0%)\n-- cpu               63018362871765 #    14.5%\n-- memory            49725012465956 #    11.5%\nspeculation          12881927224817 #  3.0% ( 3.0%)\n-- branch mispredict 12368006069230 #     2.9%\n-- pipeline restart  513921155587   #     0.1%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           216187026514697 # 2.16 GHz\ninstructions         883987677201512 # 4.09 IPC high\nl2 access            3937606297777  # 13.285 l2 access per 1000 inst\nl2 miss              358227811293   # 9.10% l2 miss\n<\/code><\/pre>\n\n\n\n<p>Process overview shows pw.x as the primary process.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>498 processes\n\t120 pw.x                 138331.72  4422.93\n\t 68 clinfo                  16.54     5.99\n\t 18 mpirun                   1.04     2.27\n\t 38 vulkaninfo               0.95     1.33\n\t  6 php                      0.22     0.38\n\t  4 vulkani:disk$0           0.10     0.14\n\t  6 glxinfo:gdrv0            0.10     0.08\n\t  6 glxinfo:gl0              0.10     0.08\n\t  6 clang                    0.05     0.07\n\t  2 llvmpipe-0               0.05     0.07\n\t  2 llvmpipe-1               0.05     0.07\n\t  2 llvmpipe-10              0.05     0.07\n\t  2 llvmpipe-11              0.05     0.07\n\t  2 llvmpipe-12              0.05     0.07\n\t  2 llvmpipe-13              0.05     0.07\n\t  2 llvmpipe-14              0.05     0.07\n\t  2 llvmpipe-15              0.05     0.07\n\t  2 llvmpipe-2               0.05     0.07\n\t  2 llvmpipe-3               0.05     0.07\n\t  2 llvmpipe-4               0.05     0.07\n\t  2 llvmpipe-5               0.05     0.07\n\t  2 llvmpipe-6               0.05     0.07\n\t  2 llvmpipe-7               0.05     0.07\n\t  2 llvmpipe-8               0.05     0.07\n\t  2 llvmpipe-9               0.05     0.07\n\t  2 glxinfo                  0.04     0.04\n\t  2 glxinfo:cs0              0.04     0.04\n\t  2 glxinfo:disk$0           0.04     0.04\n\t  2 glxinfo:sh0              0.04     0.04\n\t  2 glxinfo:shlo0            0.04     0.04\n\t  3 rocminfo                 0.03     0.00\n\t  1 lspci                    0.00     0.02\n\t  1 ps                       0.00     0.01\n\t 82 sh                       0.00     0.00\n\t 14 gsettings                0.00     0.00\n\t 13 gcc                      0.00     0.00\n\t 10 sed                      0.00     0.00\n\t  8 stat                     0.00     0.00\n\t  8 systemd-detect-          0.00     0.00\n\t  6 llvm-link                0.00     0.00\n\t  5 phoronix-test-s          0.00     0.00\n\t  3 qe                       0.00     0.00\n\t  2 cc                       0.00     0.00\n\t  2 lscpu                    0.00     0.00\n\t  2 uname                    0.00     0.00\n\t  2 which                    0.00     0.00\n\t  2 xset                     0.00     0.00\n\t  1 date                     0.00     0.00\n\t  1 dconf worker             0.00     0.00\n\t  1 dirname                  0.00     0.00\n\t  1 dmesg                    0.00     0.00\n\t  1 dmidecode                0.00     0.00\n\t  1 gmain                    0.00     0.00\n\t  1 grep                     0.00     0.00\n\t  1 ifconfig                 0.00     0.00\n\t  1 ip                       0.00     0.00\n\t  1 lsmod                    0.00     0.00\n\t  1 mktemp                   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 sort                     0.00     0.00\n\t  1 stty                     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\n\t  1 xrandr                   0.00     0.00\n0 processes running\n55 maximum processes\n<\/code><\/pre>\n\n\n\n<p>Sample computation shows MPI being used<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      44262) qe               cpu=15 start=5.68  finish=665.97\n        44263) mpirun           cpu=0 start=5.69  finish=665.94\n          44268) mpirun           cpu=10 start=6.27  finish=665.94\n          44269) mpirun           cpu=3 start=6.27  finish=6.27 \n          44270) mpirun           cpu=2 start=6.29  finish=665.93\n          44271) mpirun           cpu=15 start=6.77  finish=665.93\n          44272) mpirun           cpu=13 start=6.77  finish=665.94\n          44273) pw.x             cpu=9 start=6.80  finish=665.92\n            44275) pw.x             cpu=4 start=6.81  finish=665.92\n            44277) pw.x             cpu=0 start=6.81  finish=665.92\n            44282) pw.x             cpu=6 start=6.82  finish=665.92\n            44307) pw.x             cpu=8 start=8.44  finish=665.92\n          44274) pw.x             cpu=6 start=6.81  finish=665.92\n            44278) pw.x             cpu=12 start=6.81  finish=665.92\n            44280) pw.x             cpu=10 start=6.82  finish=665.92\n            44286) pw.x             cpu=15 start=6.82  finish=665.92\n            44308) pw.x             cpu=15 start=8.45  finish=665.92\n          44276) pw.x             cpu=11 start=6.81  finish=665.92\n            44281) pw.x             cpu=5 start=6.82  finish=665.92\n            44284) pw.x             cpu=15 start=6.82  finish=665.92\n            44290) pw.x             cpu=5 start=6.83  finish=665.92\n            44310) pw.x             cpu=5 start=8.47  finish=665.92\n          44279) pw.x             cpu=13 start=6.82  finish=665.92\n            44285) pw.x             cpu=2 start=6.82  finish=665.92\n            44288) pw.x             cpu=10 start=6.83  finish=665.92\n            44294) pw.x             cpu=0 start=6.83  finish=665.92\n            44305) pw.x             cpu=5 start=8.41  finish=665.92\n          44283) pw.x             cpu=1 start=6.82  finish=665.92\n            44289) pw.x             cpu=15 start=6.83  finish=665.92\n            44292) pw.x             cpu=4 start=6.83  finish=665.92\n            44298) pw.x             cpu=3 start=6.84  finish=665.92\n            44312) pw.x             cpu=11 start=8.59  finish=665.92\n          44287) pw.x             cpu=10 start=6.83  finish=665.92\n            44293) pw.x             cpu=2 start=6.83  finish=665.92\n            44297) pw.x             cpu=10 start=6.84  finish=665.92\n            44301) pw.x             cpu=10 start=6.84  finish=665.92\n            44309) pw.x             cpu=8 start=8.46  finish=665.92\n          44291) pw.x             cpu=14 start=6.83  finish=665.92\n            44296) pw.x             cpu=8 start=6.84  finish=665.92\n            44299) pw.x             cpu=5 start=6.84  finish=665.92\n            44303) pw.x             cpu=13 start=6.85  finish=665.92\n            44306) pw.x             cpu=7 start=8.42  finish=665.92\n          44295) pw.x             cpu=7 start=6.83  finish=665.92\n            44300) pw.x             cpu=10 start=6.84  finish=665.92\n            44302) pw.x             cpu=5 start=6.85  finish=665.92\n            44304) pw.x             cpu=4 start=6.85  finish=665.92\n            44311) pw.x             cpu=1 start=8.48  finish=665.92\n        44359) sed              cpu=6 start=665.97 finish=665.97\n        44360) sed              cpu=12 start=665.97 finish=665.97\n        44361) sed              cpu=9 start=665.97 finish=665.97\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Code for modeling electronic structures and materials. One benchmark and result is reported. The code is multi-threaded with a mix of one thread per hyperthreaded core and one per actual cor.e Topdown profile shows a blur between being backend stalls <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/qe\/\"><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-1242","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/1242","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=1242"}],"version-history":[{"count":1,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/1242\/revisions"}],"predecessor-version":[{"id":1246,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/1242\/revisions\/1246"}],"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=1242"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}