{"id":2068,"date":"2024-03-08T10:56:39","date_gmt":"2024-03-08T10:56:39","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=2068"},"modified":"2024-03-08T10:56:40","modified_gmt":"2024-03-08T10:56:40","slug":"rays1bench","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/rays1bench\/","title":{"rendered":"rays1bench"},"content":{"rendered":"\n<p>A simple path-tracer\/ray-tracer with one workload. Looks like it runs in ~20 seconds per iteration.<\/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\/03\/systemtime-29.png\" alt=\"\" class=\"wp-image-2069\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-29.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-29-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-29-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile shows a fairly high retirement rate with some backend stalls.<\/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\/03\/amdtopdown-29.png\" alt=\"\" class=\"wp-image-2070\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-29.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-29-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-29-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics confirm a 53% retirement rate and low L2 access and low opcache miss.  Looks like small kernels overall.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              56.575\non_cpu               0.650          # 10.41 \/ 16 cores\nutime                587.145\nstime                1.550\nnvcsw                2224           # 26.55%\nnivcsw               6153           # 73.45%\ninblock              0              # 0.00\/sec\nonblock              38216          # 675.49\/sec\ncpu-clock            588988945689   # 588.989 seconds\ntask-clock           588994392600   # 588.994 seconds\npage faults          403434         # 684.954\/sec\ncontext switches     8442           # 14.333\/sec\ncpu migrations       285            # 0.484\/sec\nmajor page faults    3              # 0.005\/sec\nminor page faults    403431         # 684.949\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             422033102895   # 95.619 branches per 1000 inst\nbranch misses        8767528965     # 2.08% branch miss\nconditional          390398110502   # 88.452 conditional branches per 1000 inst\nindirect             2995398424     # 0.679 indirect branches per 1000 inst\ncpu-cycles           2193517209245  # 2.43 GHz\ninstructions         4412484677562  # 2.01 IPC\nslots                4390587834432  #\nretiring             1393458662508  # 31.7% (53.4%)\n-- ucode             958018754      #     0.0%\n-- fastpath          1392500643754  #    31.7%\nfrontend             351318571484   #  8.0% (13.5%)\n-- latency           217424991282   #     5.0%\n-- bandwidth         133893580202   #     3.0%\nbackend              653236524449   # 14.9% (25.0%)\n-- cpu               596466322859   #    13.6%\n-- memory            56770201590    #     1.3%\nspeculation          212678142692   #  4.8% ( 8.1%)\n-- branch mispredict 212394334311   #     4.8%\n-- pipeline restart  283808381      #     0.0%\nsmt-contention       1779890319064  # 40.5% ( 0.0%)\ncpu-cycles           2194363711223  # 2.43 GHz\ninstructions         4409314620701  # 2.01 IPC\ninstructions         1472643771017  # 9.090 l2 access per 1000 inst\nl2 hit from l1       9590644993     # 0.66% l2 miss\nl2 miss from l1      54619276       #\nl2 hit from l2 pf    3761503405     #\nl3 hit from l2 pf    24597536       #\nl3 miss from l2 pf   9534127        #\ninstructions         1470855146556  # 76.471 float per 1000 inst\nfloat 512            80             # 0.000 AVX-512 per 1000 inst\nfloat 256            610            # 0.000 AVX-256 per 1000 inst\nfloat 128            112477303101   # 76.471 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         0              # 0.000 scalar per 1000 inst\ninstructions         4413386672400  #\nopcache              621787364163   # 140.887 opcache per 1000 inst\nopcache miss         2223793132     #  0.4% opcache miss rate\nl1 dTLB miss         156568437      # 0.035 L1 dTLB per 1000 inst\nl2 dTLB miss         9987439        # 0.002 L2 dTLB per 1000 inst\ninstructions         4413463173734  #\nicache               4075752160     # 0.923 icache per 1000 inst\nicache miss          859116413      # 21.1% icache miss rate\nl1 iTLB miss         67570423       # 0.015 L1 iTLB per 1000 inst\nl2 iTLB miss         0              # 0.000 L2 iTLB per 1000 inst\ntlb flush            29434          # 0.000 TLB flush 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              361.295\non_cpu               0.771          # 12.34 \/ 16 cores\nutime                4456.398\nstime                2.584\nnvcsw                2851           # 6.15%\nnivcsw               43486          # 93.85%\ninblock              8              # 0.02\/sec\nonblock              133024         # 368.19\/sec\ncpu-clock            4460238106346  # 4460.238 seconds\ntask-clock           4460254922589  # 4460.255 seconds\npage faults          1500897        # 336.505\/sec\ncontext switches     47717          # 10.698\/sec\ncpu migrations       531            # 0.119\/sec\nmajor page faults    1              # 0.000\/sec\nminor page faults    1500896        # 336.505\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             2104213340106  # 95.285 branches per 1000 inst\nbranch misses        46948434651    # 2.23% branch miss\nconditional          2104213383082  # 95.285 conditional branches per 1000 inst\nindirect             674160895320   # 30.528 indirect branches per 1000 inst\nslots                8682095488862  #\nretiring             5295681969594  # 61.0% (61.0%) high\n-- ucode             276375704863   #     3.2%\n-- fastpath          5019306264731  #    57.8%\nfrontend             1145825338892  # 13.2% (13.2%)\n-- latency           767452449161   #     8.8%\n-- bandwidth         378372889731   #     4.4%\nbackend              762062648350   #  8.8% ( 8.8%) low\n-- cpu               262379951747   #     3.0%\n-- memory            499682696603   #     5.8%\nspeculation          1491692962110  # 17.2% (17.2%) high\n-- branch mispredict 1488388813726  #    17.1%\n-- pipeline restart  3304148384     #     0.0%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           5520830012827  # 1.76 GHz\ninstructions         10513725252527 # 1.90 IPC\nl2 access            4365224473     # 0.602 l2 access per 1000 inst\nl2 miss              764411421      # 17.51% l2 miss\ncpu-cycles           2855102875288  # 15.1% memory latency\nload stalls          431689352949   # 14.9% l1 bound\nl1 miss              6670996467     #  0.2% l2 bound\nl2 miss              1734383138     #  0.0% l3 bound\nl3 miss              729430767      #  0.0% dram bound\nstore_stalls         430419365      #  0.0% store bound\n<\/code><\/pre>\n\n\n\n<p>Process overview with a.out as the name of the benchmark process.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>547 processes\n\t147 a.out                12846.28     1.50\n\t 68 clinfo                  15.88     6.98\n\t  6 cc1plus                  2.05     0.40\n\t 38 vulkaninfo               1.34     1.15\n\t  3 lto1-ltrans              0.94     0.05\n\t  4 vulkani:disk$0           0.14     0.13\n\t  6 glxinfo:gdrv0            0.08     0.10\n\t  6 glxinfo:gl0              0.08     0.10\n\t  3 ld                       0.08     0.02\n\t  2 llvmpipe-0               0.07     0.07\n\t  2 llvmpipe-1               0.07     0.07\n\t  2 llvmpipe-10              0.07     0.07\n\t  2 llvmpipe-11              0.07     0.07\n\t  2 llvmpipe-12              0.07     0.07\n\t  2 llvmpipe-13              0.07     0.07\n\t  2 llvmpipe-14              0.07     0.07\n\t  2 llvmpipe-15              0.07     0.07\n\t  2 llvmpipe-2               0.07     0.07\n\t  2 llvmpipe-3               0.07     0.07\n\t  2 llvmpipe-4               0.07     0.07\n\t  2 llvmpipe-5               0.07     0.07\n\t  2 llvmpipe-6               0.07     0.07\n\t  2 llvmpipe-7               0.07     0.07\n\t  2 llvmpipe-8               0.07     0.07\n\t  2 llvmpipe-9               0.07     0.07\n\t  7 python3                  0.07     0.00\n\t  6 php                      0.06     0.06\n\t  9 as                       0.06     0.01\n\t  2 glxinfo                  0.05     0.04\n\t  6 clang                    0.04     0.08\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  3 lto1-wpa                 0.01     0.01\n\t  1 lspci                    0.01     0.01\n\t  1 ps                       0.00     0.01\n\t 84 sh                       0.00     0.00\n\t 13 gcc                      0.00     0.00\n\t 12 gsettings                0.00     0.00\n\t  9 g++                      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 collect2                 0.00     0.00\n\t  3 gmain                    0.00     0.00\n\t  3 lto-wrapper              0.00     0.00\n\t  3 rays1bench               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 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 python                   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 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\n47 maximum processes\n<\/code><\/pre>\n\n\n\n<p>Computation blocks<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      1052322) rays1bench       cpu=6 start=5.64  finish=19.07\n        1052323) python3          cpu=4 start=5.65  finish=19.07\n          1052324) python3          cpu=5 start=5.67  finish=5.68 \n          1052325) g++              cpu=7 start=5.68  finish=7.00 \n            1052326) cc1plus          cpu=5 start=5.69  finish=6.25 \n            1052327) as               cpu=8 start=6.26  finish=6.28 \n            1052328) cc1plus          cpu=2 start=6.28  finish=6.56 \n            1052329) as               cpu=8 start=6.57  finish=6.57 \n            1052330) collect2         cpu=13 start=6.57  finish=7.00 \n              1052331) ld               cpu=13 start=6.58  finish=7.00 \n                1052332) lto-wrapper      cpu=8 start=6.59  finish=6.97 \n                  1052333) g++              cpu=6 start=6.59  finish=6.61 \n                    1052334) lto1-wpa         cpu=9 start=6.59  finish=6.60 \n                  1052335) g++              cpu=4 start=6.61  finish=6.97 \n                    1052336) lto1-ltrans      cpu=6 start=6.61  finish=6.94 \n                    1052337) as               cpu=15 start=6.94  finish=6.97 \n          1052338) a.out            cpu=11 start=7.00  finish=19.06\n            1052339) a.out            cpu=1 start=7.01  finish=7.93 \n            1052340) a.out            cpu=2 start=7.01  finish=7.93 \n            1052341) a.out            cpu=11 start=7.01  finish=7.93 \n            1052342) a.out            cpu=4 start=7.01  finish=7.93 \n            1052343) a.out            cpu=7 start=7.01  finish=7.93 \n            1052344) a.out            cpu=0 start=7.01  finish=7.93 \n            1052345) a.out            cpu=6 start=7.01  finish=7.93 \n            1052346) a.out            cpu=13 start=7.01  finish=7.93 \n            1052347) a.out            cpu=5 start=7.01  finish=7.93 \n            1052348) a.out            cpu=8 start=7.01  finish=7.93 \n            1052349) a.out            cpu=3 start=7.01  finish=7.93 \n            1052350) a.out            cpu=12 start=7.01  finish=7.93 \n            1052351) a.out            cpu=15 start=7.01  finish=7.93 \n            1052352) a.out            cpu=9 start=7.01  finish=7.93 \n            1052353) a.out            cpu=14 start=7.01  finish=7.93 \n            1052354) a.out            cpu=10 start=7.01  finish=7.93 \n            1052355) a.out            cpu=13 start=7.93  finish=9.98 \n            1052356) a.out            cpu=15 start=7.93  finish=9.98 \n            1052357) a.out            cpu=12 start=7.93  finish=9.98 \n            1052358) a.out            cpu=6 start=7.93  finish=9.98 \n            1052359) a.out            cpu=9 start=7.93  finish=9.98 \n            1052360) a.out            cpu=3 start=7.93  finish=9.98 \n            1052361) a.out            cpu=0 start=7.93  finish=9.98 \n            1052362) a.out            cpu=2 start=7.93  finish=9.97 \n            1052363) a.out            cpu=4 start=7.93  finish=9.98 \n            1052364) a.out            cpu=7 start=7.93  finish=9.98 \n            1052365) a.out            cpu=5 start=7.93  finish=9.98 \n            1052366) a.out            cpu=8 start=7.93  finish=9.98 \n            1052367) a.out            cpu=14 start=7.93  finish=9.98 \n            1052368) a.out            cpu=1 start=7.93  finish=9.98 \n            1052369) a.out            cpu=11 start=7.93  finish=9.98 \n            1052370) a.out            cpu=10 start=7.93  finish=9.98 \n            1052371) a.out            cpu=14 start=9.98  finish=19.05\n            1052372) a.out            cpu=7 start=9.98  finish=19.05\n            1052373) a.out            cpu=0 start=9.98  finish=19.06\n            1052374) a.out            cpu=1 start=9.98  finish=19.06\n            1052375) a.out            cpu=5 start=9.98  finish=19.05\n            1052376) a.out            cpu=2 start=9.98  finish=19.05\n            1052377) a.out            cpu=12 start=9.98  finish=19.05\n            1052378) a.out            cpu=3 start=9.98  finish=19.05\n            1052379) a.out            cpu=10 start=9.98  finish=19.05\n            1052380) a.out            cpu=13 start=9.98  finish=19.04\n            1052381) a.out            cpu=6 start=9.98  finish=19.04\n            1052382) a.out            cpu=15 start=9.98  finish=19.05\n            1052383) a.out            cpu=8 start=9.98  finish=19.06\n            1052384) a.out            cpu=9 start=9.98  finish=19.06\n            1052385) a.out            cpu=4 start=9.98  finish=19.04\n            1052386) a.out            cpu=11 start=9.98  finish=19.05\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>A simple path-tracer\/ray-tracer with one workload. Looks like it runs in ~20 seconds per iteration. Topdown profile shows a fairly high retirement rate with some backend stalls. AMD metrics confirm a 53% retirement rate and low L2 access and low <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/rays1bench\/\"><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-2068","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2068","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=2068"}],"version-history":[{"count":1,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2068\/revisions"}],"predecessor-version":[{"id":2071,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2068\/revisions\/2071"}],"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=2068"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}