{"id":5702,"date":"2015-04-08T09:41:05","date_gmt":"2015-04-08T08:41:05","guid":{"rendered":"http:\/\/www.walkingrandomly.com\/?p=5702"},"modified":"2015-04-08T09:41:05","modified_gmt":"2015-04-08T08:41:05","slug":"nvidia-gt-750m-gpu-performance-on-a-macbook-pro-using-matlab","status":"publish","type":"post","link":"https:\/\/walkingrandomly.com\/?p=5702","title":{"rendered":"Nvidia GT 750M GPU performance on a MacBook Pro using MATLAB"},"content":{"rendered":"

I recently got a 15 inch Retina Macbook Pro which contains an NVIDIA GT 750M GPU<\/a>. It’s been a while since I last got a laptop with a decent GPU in it so I wondered how it would perform in MATLAB<\/a> using the Parallel Computing Toolbox<\/a>.<\/p>\n

Of course I didn’t read any documentation; I simply fired up MATLAB 2015a and issued the gpuDevice<\/strong> command.<\/p>\n

>> gpuDevice\r\nError using gpuDevice (line 26)\r\nThere is a problem with the CUDA driver or with this GPU device. Be sure\r\nthat you have a supported GPU and that the latest driver is installed.\r\n\r\nCaused by:\r\n    The CUDA driver could not be loaded. The library name used was\r\n    '\/usr\/local\/cuda\/lib\/libcuda.dylib'. The error was:\r\n    dlopen(\/usr\/local\/cuda\/lib\/libcuda.dylib, 10): image not found<\/pre>\n
This is because I didn’t install a load of CUDA-related stuff! Following these instructions<\/a> did the trick!<\/p>\n
>> gpuDevice()\r\n\r\nans = \r\n\r\n  CUDADevice with properties:\r\n\r\n                      Name: 'GeForce GT 750M'\r\n                     Index: 1\r\n         ComputeCapability: '3.0'\r\n            SupportsDouble: 1\r\n             DriverVersion: 6.5000\r\n            ToolkitVersion: 6.5000\r\n        MaxThreadsPerBlock: 1024\r\n          MaxShmemPerBlock: 49152\r\n        MaxThreadBlockSize: [1024 1024 64]\r\n               MaxGridSize: [2.1475e+09 65535 65535]\r\n                 SIMDWidth: 32\r\n               TotalMemory: 2.1470e+09\r\n           AvailableMemory: 444055552\r\n       MultiprocessorCount: 2\r\n              ClockRateKHz: 925500\r\n               ComputeMode: 'Default'\r\n      GPUOverlapsTransfers: 1\r\n    KernelExecutionTimeout: 1\r\n          CanMapHostMemory: 1\r\n           DeviceSupported: 1\r\n            DeviceSelected: 1<\/pre>\n
I headed over to the MATLAB File Exchange to get the GPU Bench App<\/a> for MATLAB and fired it up. The summary of the results is below. Click on the image to see the detailed results.<\/p>\n
\"Nvivida<\/a><\/p>\n
 <\/p>\n
The double precision performance of this GPU card is very poor – MUCH slower than the CPU on the Macbook Pro.<\/p>\n
Looking on the bright side, the numbers for the CPU are pretty good for a laptop!<\/p>\n","protected":false},"excerpt":{"rendered":"
I recently got a 15 inch Retina Macbook Pro which contains an NVIDIA GT 750M GPU. It’s been a while since I last got a laptop with a decent GPU in it so I wondered how it would perform in MATLAB using the Parallel Computing Toolbox. Of course I didn’t read any documentation; I simply […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[75,51,11],"tags":[],"class_list":["post-5702","post","type-post","status-publish","format-standard","hentry","category-apple","category-gpu","category-matlab"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_shortlink":"https:\/\/wp.me\/p3swhs-1tY","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/posts\/5702","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5702"}],"version-history":[{"count":4,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/posts\/5702\/revisions"}],"predecessor-version":[{"id":5721,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=\/wp\/v2\/posts\/5702\/revisions\/5721"}],"wp:attachment":[{"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5702"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5702"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/walkingrandomly.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5702"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}