{"id":2245,"date":"2024-05-31T12:26:01","date_gmt":"2024-05-31T12:26:01","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=2245"},"modified":"2024-05-31T12:40:36","modified_gmt":"2024-05-31T12:40:36","slug":"mbw","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/mbw\/","title":{"rendered":"mbw"},"content":{"rendered":"\n<p>A test of the memory bandwidth with 10 tests not all of whom run.  It provides a set of memory MiB\/s for various sizes.  This looks to be mostly single-threaded test<\/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\/05\/systemtime-1.png\" alt=\"\" class=\"wp-image-2246\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-1.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-1-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-1-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile confirms this is a backend bound test with some frontend stalls in larger sizes.<\/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\/05\/amdtopdown-1.png\" alt=\"\" class=\"wp-image-2247\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-1.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-1-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-1-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics show integer code with a large amount of L2 access and moderate L2 misses.  Retirement is low and branch speculation is also low.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              1906.853\non_cpu               0.054          # 0.86 \/ 16 cores\nutime                1465.009\nstime                168.283\nnvcsw                2300           # 26.27%\nnivcsw               6455           # 73.73%\ninblock              11800          # 6.19\/sec\nonblock              15256          # 8.00\/sec\ncpu-clock            1633730433783  # 1633.730 seconds\ntask-clock           1633769790814  # 1633.770 seconds\npage faults          118525539      # 72547.271\/sec\ncontext switches     17991          # 11.012\/sec\ncpu migrations       492            # 0.301\/sec\nmajor page faults    161            # 0.099\/sec\nminor page faults    118525378      # 72547.172\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             184498880490   # 125.478 branches per 1000 inst\nbranch misses        17912279504    # 9.71% branch miss\nconditional          104707448177   # 71.211 conditional branches per 1000 inst\nindirect             220068086      # 0.150 indirect branches per 1000 inst\ncpu-cycles           9419362477582  # 0.25 GHz\ninstructions         1577981338302  # 0.17 IPC low\nslots                18847418332872 #\nretiring             1050894854958  #  5.6% ( 5.6%) low\n-- ucode             2259314547     #     0.0%\n-- fastpath          1048635540411  #     5.6%\nfrontend             5607452820130  # 29.8% (29.8%)\n-- latency           1088308031532  #     5.8%\n-- bandwidth         4519144788598  #    24.0%\nbackend              12170699176018 # 64.6% (64.6%)\n-- cpu               1136102468324  #     6.0%\n-- memory            11034596707694 #    58.5%\nspeculation          18222191413    #  0.1% ( 0.1%) low\n-- branch mispredict 17960309928    #     0.1%\n-- pipeline restart  261881485      #     0.0%\nsmt-contention       148500392      #  0.0% ( 0.0%)\ncpu-cycles           7614828753868  # 0.25 GHz\ninstructions         1422724198869  # 0.19 IPC low\ninstructions         474208968884   # 884.989 l2 access per 1000 inst\nl2 hit from l1       263889056294   # 34.85% l2 miss\nl2 miss from l1      21212440530    #\nl2 hit from l2 pf    30746495113    #\nl3 hit from l2 pf    93217343       #\nl3 miss from l2 pf   124940831103   #\ninstructions         473877223684   # 1.407 float per 1000 inst\nfloat 512            105            # 0.000 AVX-512 per 1000 inst\nfloat 256            628            # 0.000 AVX-256 per 1000 inst\nfloat 128            666869221      # 1.407 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         0              # 0.000 scalar per 1000 inst\ninstructions         1629693076163  #\nopcache              346637082277   # 212.701 opcache per 1000 inst\nopcache miss         94188496323    # 27.2% opcache miss rate\nl1 dTLB miss         8230083399     # 5.050 L1 dTLB per 1000 inst\nl2 dTLB miss         8044640037     # 4.936 L2 dTLB per 1000 inst\ninstructions         1682572313999  #\nicache               239322611531   # 142.236 icache per 1000 inst\nicache miss          5556630826     #  2.3% icache miss rate\nl1 iTLB miss         9942612        # 0.006 L1 iTLB per 1000 inst\nl2 iTLB miss         0              # 0.000 L2 iTLB per 1000 inst\ntlb flush            32020          # 0.000 TLB flush per 1000 inst\n<\/code><\/pre>\n\n\n\n<p>Intel metrics show some L2 misses and 35% memory wait.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              517.446\non_cpu               0.041          # 0.65 \/ 16 cores\nutime                292.934\nstime                45.784\nnvcsw                6723           # 72.07%\nnivcsw               2606           # 27.93%\ninblock              338344         # 653.87\/sec\nonblock              2760           # 5.33\/sec\ncpu-clock            338823248265   # 338.823 seconds\ntask-clock           338834035232   # 338.834 seconds\npage faults          41152904       # 121454.458\/sec\ncontext switches     11710          # 34.560\/sec\ncpu migrations       384            # 1.133\/sec\nmajor page faults    3868           # 11.416\/sec\nminor page faults    41149035       # 121443.039\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             54342363240    # 123.020 branches per 1000 inst\nbranch misses        53810125       # 0.10% branch miss\nconditional          54342374216    # 123.020 conditional branches per 1000 inst\nindirect             108688801      # 0.246 indirect branches per 1000 inst\nslots                6532654943156  #\nretiring             638473263119   #  9.8% ( 9.8%) low\n-- ucode             161532651554   #     2.5%\n-- fastpath          476940611565   #     7.3%\nfrontend             345713728545   #  5.3% ( 5.3%)\n-- latency           206060283622   #     3.2%\n-- bandwidth         139653444923   #     2.1%\nbackend              5642367685225  # 86.4% (86.4%) high\n-- cpu               313856952783   #     4.8%\n-- memory            5328510732442  #    81.6%\nspeculation          122339221354   #  1.9% ( 1.9%)\n-- branch mispredict 54754544255    #     0.8%\n-- pipeline restart  67584677099    #     1.0%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           1099257587698  # 0.13 GHz\ninstructions         423991355150   # 0.39 IPC low\nl2 access            196921917831   # 464.565 l2 access per 1000 inst\nl2 miss              151420460256   # 76.89% l2 miss\ncpu-cycles           1108264144554  # 84.2% memory latency\nload stalls          760509116721   #  1.8% l1 bound\nl1 miss              740812702789   # 12.4% l2 bound\nl2 miss              603439901224   # 18.7% l3 bound\nl3 miss              395727304135   # 35.7% dram bound\nstore_stalls         172596010117   # 15.6% store bound\n<\/code><\/pre>\n\n\n\n<p>Process overview shows time is spent in invocations of mbw process<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>435 processes\n\t 42 mbw                    875.10    97.92\n\t 68 clinfo                  15.87     6.64\n\t 38 vulkaninfo               1.31     1.33\n\t  6 php                      0.14     0.45\n\t  4 vulkani:disk$0           0.13     0.14\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  6 clang                    0.03     0.09\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\t102 sh                       0.00     0.00\n\t 42 mbw-benchmark            0.00     0.00\n\t 13 gcc                      0.00     0.00\n\t  8 gsettings                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 glxinfo                  0.00     0.00\n\t  5 phoronix-test-s          0.00     0.00\n\t  4 dconf worker             0.00     0.00\n\t  4 gmain                    0.00     0.00\n\t  2 cc                       0.00     0.00\n\t  2 grep                     0.00     0.00\n\t  2 lscpu                    0.00     0.00\n\t  2 setterm                  0.00     0.00\n\t  2 uname                    0.00     0.00\n\t  2 which                    0.00     0.00\n\t  1 date                     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 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 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\n0 processes running\n47 maximum processes\n<\/code><\/pre>\n\n\n\n<p>Process structure is simple<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      235063) sh               cpu=1 start=81.78 finish=81.78\n        235064) sh               cpu=3 start=81.78 finish=81.78\n      235065) mbw-benchmark    cpu=8 start=91.98 finish=115.85\n        235066) mbw              cpu=1 start=91.99 finish=115.85\n      235067) mbw-benchmark    cpu=0 start=119.85 finish=143.70\n        235068) mbw              cpu=1 start=119.86 finish=143.70\n      235069) mbw-benchmark    cpu=0 start=147.71 finish=172.00\n        235070) mbw              cpu=1 start=147.71 finish=171.99\n      235071) sh               cpu=1 start=172.00 finish=172.00\n        235072) sh               cpu=10 start=172.00 finish=172.00\n      235074) mbw-benchmark    cpu=9 start=182.18 finish=229.48\n        235075) mbw              cpu=2 start=182.18 finish=229.48\n      235076) mbw-benchmark    cpu=9 start=233.49 finish=281.12\n        235077) mbw              cpu=10 start=233.49 finish=281.12\n      235078) mbw-benchmark    cpu=1 start=285.12 finish=332.32\n        235079) mbw              cpu=10 start=285.13 finish=332.32\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>A test of the memory bandwidth with 10 tests not all of whom run. It provides a set of memory MiB\/s for various sizes. This looks to be mostly single-threaded test Topdown profile confirms this is a backend bound test <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/mbw\/\"><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-2245","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2245","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=2245"}],"version-history":[{"count":2,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2245\/revisions"}],"predecessor-version":[{"id":2257,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2245\/revisions\/2257"}],"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=2245"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}