{"id":2249,"date":"2024-05-31T12:33:47","date_gmt":"2024-05-31T12:33:47","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=2249"},"modified":"2024-05-31T12:41:50","modified_gmt":"2024-05-31T12:41:50","slug":"ramspeed","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/ramspeed\/","title":{"rendered":"ramspeed"},"content":{"rendered":"\n<p>This test looks like a variation of the stream benchmark with copy\/scale\/triad and average.  It uses floating point and integer data types.  It looks to be mostly one or two threads.<\/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-2.png\" alt=\"\" class=\"wp-image-2250\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-2.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-2-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/systemtime-2-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile shows a backend bound program<\/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-2.png\" alt=\"\" class=\"wp-image-2251\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-2.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-2-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/05\/amdtopdown-2-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics confirm this as memory bound with high rate of L2 access. Despite moving floating point, there are almost no floating point intructions.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              1557.486\non_cpu               0.055          # 0.88 \/ 16 cores\nutime                1326.810\nstime                41.987\nnvcsw                68351          # 92.84%\nnivcsw               5271           # 7.16%\ninblock              32             # 0.02\/sec\nonblock              13816          # 8.87\/sec\ncpu-clock            2742989846478  # 2742.990 seconds\ntask-clock           2743086882030  # 2743.087 seconds\npage faults          49322001       # 17980.474\/sec\ncontext switches     105687         # 38.528\/sec\ncpu migrations       532            # 0.194\/sec\nmajor page faults    2              # 0.001\/sec\nminor page faults    49321999       # 17980.473\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             147713856443   # 93.840 branches per 1000 inst\nbranch misses        7525003207     # 5.09% branch miss\nconditional          114162095786   # 72.525 conditional branches per 1000 inst\nindirect             98555933       # 0.063 indirect branches per 1000 inst\ncpu-cycles           12641110483498 # 0.51 GHz\ninstructions         1554483337148  # 0.12 IPC low\nslots                25288565605854 #\nretiring             618318956718   #  2.4% ( 2.4%) low\n-- ucode             775636722      #     0.0%\n-- fastpath          617543319996   #     2.4%\nfrontend             841830393022   #  3.3% ( 3.3%) low\n-- latency           497749780566   #     2.0%\n-- bandwidth         344080612456   #     1.4%\nbackend              23818249605363 # 94.2% (94.2%) high\n-- cpu               597500871971   #     2.4%\n-- memory            23220748733392 #    91.8%\nspeculation          10018864501    #  0.0% ( 0.0%) low\n-- branch mispredict 9753004805     #     0.0%\n-- pipeline restart  265859696      #     0.0%\nsmt-contention       146921617      #  0.0% ( 0.0%)\ncpu-cycles           12618813414012 # 0.51 GHz\ninstructions         1556603033250  # 0.12 IPC low\ninstructions         517961772956   # 980.903 l2 access per 1000 inst\nl2 hit from l1       288657905828   # 40.52% l2 miss\nl2 miss from l1      8939564541     #\nl2 hit from l2 pf    22494472717    #\nl3 hit from l2 pf    210256769      #\nl3 miss from l2 pf   196707682284   #\ninstructions         517796842548   # 0.447 float per 1000 inst\nfloat 512            100            # 0.000 AVX-512 per 1000 inst\nfloat 256            650            # 0.000 AVX-256 per 1000 inst\nfloat 128            231462915      # 0.447 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         0              # 0.000 scalar per 1000 inst\ninstructions         1554155337938  #\nopcache              127266670070   # 81.888 opcache per 1000 inst\nopcache miss         53635397087    # 42.1% opcache miss rate\nl1 dTLB miss         13222015095    # 8.508 L1 dTLB per 1000 inst\nl2 dTLB miss         12953589496    # 8.335 L2 dTLB per 1000 inst\ninstructions         1554100729697  #\nicache               121460160159   # 78.155 icache per 1000 inst\nicache miss          3758654716     #  3.1% icache miss rate\nl1 iTLB miss         9921047        # 0.006 L1 iTLB per 1000 inst\nl2 iTLB miss         0              # 0.000 L2 iTLB per 1000 inst\ntlb flush            26472          # 0.000 TLB flush per 1000 inst\n<\/code><\/pre>\n\n\n\n<p>Intel metrics confirm memory stalls with 38% dram and 16% L3<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              2181.952\non_cpu               0.057          # 0.92 \/ 16 cores\nutime                1973.303\nstime                28.338\nnvcsw                19700          # 74.29%\nnivcsw               6818           # 25.71%\ninblock              1776           # 0.81\/sec\nonblock              2424           # 1.11\/sec\ncpu-clock            4002738390187  # 4002.738 seconds\ntask-clock           4002789217081  # 4002.789 seconds\npage faults          49256733       # 12305.603\/sec\ncontext switches     61697          # 15.414\/sec\ncpu migrations       3389           # 0.847\/sec\nmajor page faults    15             # 0.004\/sec\nminor page faults    49256718       # 12305.599\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             133960761624   # 40.246 branches per 1000 inst\nbranch misses        53656019       # 0.04% branch miss\nconditional          133960773688   # 40.246 conditional branches per 1000 inst\nindirect             115513238      # 0.035 indirect branches per 1000 inst\nslots                79291431925904 #\nretiring             3147625843228  #  4.0% ( 4.0%) low\n-- ucode             63566823852    #     0.1%\n-- fastpath          3084059019376  #     3.9%\nfrontend             425391016890   #  0.5% ( 0.5%) low\n-- latency           241218002295   #     0.3%\n-- bandwidth         184173014595   #     0.2%\nbackend              75525111531388 # 95.3% (95.3%) high\n-- cpu               6323241151248  #     8.0%\n-- memory            69201870380140 #    87.3%\nspeculation          38772786029    #  0.0% ( 0.0%) low\n-- branch mispredict 6942804511     #     0.0%\n-- pipeline restart  31829981518    #     0.0%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           13254648321108 # 0.37 GHz\ninstructions         3310529227804  # 0.25 IPC low\nl2 access            1554923758519  # 469.826 l2 access per 1000 inst\nl2 miss              1118397500954  # 71.93% l2 miss\ncpu-cycles           13269097487447 # 85.4% memory latency\nload stalls          9214888159006  #  1.6% l1 bound\nl1 miss              9003832128730  # 13.4% l2 bound\nl2 miss              7221520942138  # 16.1% l3 bound\nl3 miss              5088357775927  # 38.3% dram bound\nstore_stalls         2114460128716  # 15.9% store bound\n<\/code><\/pre>\n\n\n\n<p>Process overview shows ramsp as the execution process<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>441 processes\n\t 60 ramsmp                2668.41    76.81\n\t 68 clinfo                  17.54     5.60\n\t 38 vulkaninfo               1.14     1.15\n\t  6 php                      0.16     0.65\n\t  4 vulkani:disk$0           0.12     0.13\n\t  2 llvmpipe-0               0.06     0.07\n\t  2 llvmpipe-1               0.06     0.07\n\t  2 llvmpipe-10              0.06     0.07\n\t  2 llvmpipe-11              0.06     0.07\n\t  2 llvmpipe-12              0.06     0.07\n\t  2 llvmpipe-13              0.06     0.07\n\t  2 llvmpipe-14              0.06     0.07\n\t  2 llvmpipe-15              0.06     0.07\n\t  2 llvmpipe-2               0.06     0.07\n\t  2 llvmpipe-3               0.06     0.07\n\t  2 llvmpipe-4               0.06     0.07\n\t  2 llvmpipe-5               0.06     0.07\n\t  2 llvmpipe-6               0.06     0.07\n\t  2 llvmpipe-7               0.06     0.07\n\t  2 llvmpipe-8               0.06     0.07\n\t  2 llvmpipe-9               0.06     0.07\n\t  6 clang                    0.06     0.06\n\t  3 rocminfo                 0.03     0.00\n\t  1 lspci                    0.00     0.02\n\t102 sh                       0.00     0.00\n\t 30 ramspeed                 0.00     0.00\n\t 13 gcc                      0.00     0.00\n\t 11 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  3 gmain                    0.00     0.00\n\t  2 cc                       0.00     0.00\n\t  2 dconf worker             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 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 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\n<\/code><\/pre>\n\n\n\n<p>Computation blocks show two ramssmp processes<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      239720) sh               cpu=11 start=5.59  finish=5.60 \n        239721) stty             cpu=6 start=5.59  finish=5.60 \n      239722) ramspeed         cpu=0 start=5.60  finish=51.38\n        239723) ramsmp           cpu=3 start=5.60  finish=51.38\n          239724) ramsmp           cpu=12 start=5.60  finish=51.38\n      239727) ramspeed         cpu=11 start=55.38 finish=101.25\n        239728) ramsmp           cpu=4 start=55.38 finish=101.25\n          239729) ramsmp           cpu=14 start=55.39 finish=101.25\n      239730) ramspeed         cpu=11 start=105.26 finish=151.06\n        239731) ramsmp           cpu=4 start=105.26 finish=151.06\n          239732) ramsmp           cpu=6 start=105.26 finish=151.06\n      239733) sh               cpu=7 start=151.06 finish=151.06\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>This test looks like a variation of the stream benchmark with copy\/scale\/triad and average. It uses floating point and integer data types. It looks to be mostly one or two threads. Topdown profile shows a backend bound program AMD metrics <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/ramspeed\/\"><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-2249","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2249","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=2249"}],"version-history":[{"count":2,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2249\/revisions"}],"predecessor-version":[{"id":2258,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2249\/revisions\/2258"}],"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=2249"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}