{"id":2190,"date":"2024-03-24T20:21:52","date_gmt":"2024-03-24T20:21:52","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=2190"},"modified":"2024-03-27T12:28:32","modified_gmt":"2024-03-27T12:28:32","slug":"furmark","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/furmark\/","title":{"rendered":"furmark"},"content":{"rendered":"\n<p>A cross-platform GPU stress test with OpenGL and Vulkan drivers. There are 160 combinations of drivers, screen sizes and MSAA settings. This test picks 1920&#215;1200 resolution with OpenGL and all MSAA settings. Overall system shows this is now a CPU benchmark and runes with just a few 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\/03\/systemtime-45.png\" alt=\"\" class=\"wp-image-2219\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-45.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-45-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/systemtime-45-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile shows the little CPU time is spent in frontend 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-47.png\" alt=\"\" class=\"wp-image-2220\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-47.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-47-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/03\/amdtopdown-47-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics show only 1\/30th of a core time spent.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              1076.862\non_cpu               0.002          # 0.03 \/ 16 cores\nutime                20.084\nstime                16.793\nnvcsw                162027         # 99.31%\nnivcsw               1122           # 0.69%\ninblock              8              # 0.01\/sec\nonblock              13640          # 12.67\/sec\ncpu-clock            32019749507    # 32.020 seconds\ntask-clock           32688331876    # 32.688 seconds\npage faults          476048         # 14563.239\/sec\ncontext switches     168328         # 5149.483\/sec\ncpu migrations       1007           # 30.806\/sec\nmajor page faults    2              # 0.061\/sec\nminor page faults    476046         # 14563.178\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             8777901101     # 159.914 branches per 1000 inst\nbranch misses        365812203      # 4.17% branch miss\nconditional          5205216990     # 94.828 conditional branches per 1000 inst\nindirect             507105797      # 9.238 indirect branches per 1000 inst\ncpu-cycles           53961154591    # 0.00 GHz\ninstructions         54738144413    # 1.01 IPC\nslots                108780603978   #\nretiring             19232090905    # 17.7% (17.7%)\n-- ucode             52330631       #     0.0%\n-- fastpath          19179760274    #    17.6%\nfrontend             64353407460    # 59.2% (59.3%) high\n-- latency           58838576598    #    54.1%\n-- bandwidth         5514830862     #     5.1%\nbackend              21298430222    # 19.6% (19.6%)\n-- cpu               2146489744     #     2.0%\n-- memory            19151940478    #    17.6%\nspeculation          3655643434     #  3.4% ( 3.4%)\n-- branch mispredict 3554005285     #     3.3%\n-- pipeline restart  101638149      #     0.1%\nsmt-contention       240343787      #  0.2% ( 0.0%)\ncpu-cycles           54536598047    # 0.00 GHz\ninstructions         54631269920    # 1.00 IPC\ninstructions         18245618756    # 37.691 l2 access per 1000 inst\nl2 hit from l1       615783822      # 43.13% l2 miss\nl2 miss from l1      254071074      #\nl2 hit from l2 pf    29368657       #\nl3 hit from l2 pf    16021795       #\nl3 miss from l2 pf   26518276       #\ninstructions         18197223178    # 62.137 float per 1000 inst\nfloat 512            64             # 0.000 AVX-512 per 1000 inst\nfloat 256            674            # 0.000 AVX-256 per 1000 inst\nfloat 128            1130722912     # 62.137 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         0              # 0.000 scalar per 1000 inst\ninstructions         54655192673    #\nopcache              12529239376    # 229.242 opcache per 1000 inst\nopcache miss         3057310348     # 24.4% opcache miss rate\nl1 dTLB miss         105870486      # 1.937 L1 dTLB per 1000 inst\nl2 dTLB miss         24007702       # 0.439 L2 dTLB per 1000 inst\ninstructions         54611990576    #\nicache               7369764703     # 134.948 icache per 1000 inst\nicache miss          1623602659     # 22.0% icache miss rate\nl1 iTLB miss         39060559       # 0.715 L1 iTLB per 1000 inst\nl2 iTLB miss         0              # 0.000 L2 iTLB per 1000 inst\ntlb flush            25177          # 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              1083.609\non_cpu               0.002          # 0.03 \/ 16 cores\nutime                15.516\nstime                15.960\nnvcsw                116053         # 99.64%\nnivcsw               423            # 0.36%\ninblock              64             # 0.06\/sec\nonblock              2344           # 2.16\/sec\ncpu-clock            27100165512    # 27.100 seconds\ntask-clock           27755281301    # 27.755 seconds\npage faults          375809         # 13540.090\/sec\ncontext switches     121705         # 4384.931\/sec\ncpu migrations       1051           # 37.867\/sec\nmajor page faults    1              # 0.036\/sec\nminor page faults    375808         # 13540.054\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             6642555358     # 150.585 branches per 1000 inst\nbranch misses        110237614      # 1.66% branch miss\nconditional          6642575742     # 150.585 conditional branches per 1000 inst\nindirect             478025670      # 10.837 indirect branches per 1000 inst\nslots                195395490248   #\nretiring             59217355013    # 30.3% (30.3%)\n-- ucode             6707380516     #     3.4%\n-- fastpath          52509974497    #    26.9%\nfrontend             30497378415    # 15.6% (15.6%)\n-- latency           17340657935    #     8.9%\n-- bandwidth         13156720480    #     6.7%\nbackend              94477580844    # 48.4% (48.4%)\n-- cpu               28046200975    #    14.4%\n-- memory            66431379869    #    34.0%\nspeculation          11809887438    #  6.0% ( 6.0%)\n-- branch mispredict 10842411803    #     5.5%\n-- pipeline restart  967475635      #     0.5%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           34678455881    # 0.00 GHz\ninstructions         46157951024    # 1.33 IPC\nl2 access            1951534064     # 45.139 l2 access per 1000 inst\nl2 miss              1285026344     # 65.85% l2 miss\ncpu-cycles           32708750023    # 39.3% memory latency\nload stalls          6497272907     #  3.9% l1 bound\nl1 miss              5216356433     #  4.1% l2 bound\nl2 miss              3877407117     #  2.1% l3 bound\nl3 miss              3202485247     #  9.8% dram bound\nstore_stalls         6343834109     # 19.4% store bound\n<\/code><\/pre>\n\n\n\n<p>Overall, this is a GPU test and not a CPU test.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A cross-platform GPU stress test with OpenGL and Vulkan drivers. There are 160 combinations of drivers, screen sizes and MSAA settings. This test picks 1920&#215;1200 resolution with OpenGL and all MSAA settings. Overall system shows this is now a CPU <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/furmark\/\"><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-2190","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2190","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=2190"}],"version-history":[{"count":2,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2190\/revisions"}],"predecessor-version":[{"id":2221,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2190\/revisions\/2221"}],"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=2190"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}