From 0a425d27c38a386c272739f20dfaca5881ddba1e Mon Sep 17 00:00:00 2001 From: "W. Trevor King" Date: Sat, 13 Nov 2010 10:09:05 -0500 Subject: [PATCH] Add GPGPU post. --- posts/GPGPU.mdwn | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 posts/GPGPU.mdwn diff --git a/posts/GPGPU.mdwn b/posts/GPGPU.mdwn new file mode 100644 index 0000000..ef5e8db --- /dev/null +++ b/posts/GPGPU.mdwn @@ -0,0 +1,48 @@ +[[!meta title="General-purpose computing on graphics processing units"]] + +[GPGPU][] utilizes the number crunching speed and massive +parallelization of your [graphics card][GPU] to accelerate +general-purpose tasks. When your algorithm is compatible with GPU +hardware, the speedup of running hundreds of concurrent threads can be +enormous. + +There are a number of ways to implement GPGPU, ranging from +multi-platform frameworks such as [OpenCL][] to single-company +frameworks such as [NVIDIA][]'s [CUDA][]. I've gotten to play around +with [CUDA][] while TAing the [[parallel computing]] class, and its +lots of fun. + +With NVIDIA (other vendors are probably similar, I'll update this as I +learn more), each GPU *device* has a block of global memory serving a +number of multi-processors, and each multi-processor contains several +cores which can execute concurrent threads. + +Specs on NVIDIA's [GeForce GTX 580][]: + +* 512 cores (16 (MP) ⋅ 32 (Cores/MP)) +* 1.5 GB GDDR5 RAM +* 192.4 GB/sec memory bandwidth +* 1.54 GHz processor clock rate +* 1,581.1 GFLOPs per second + +Zoom. + +The GFLOP/s computaton is `cores⋅clock⋅2`, because (from [page 94][] +of the CUDA programming guide) each core can exectute a single +multiply-add operation (2 FLOPs) per cycle. Also take a look at the +graph of historical performance on [page 14], the table of device +capabilities that starts on [page 111][], and the description of +*warps* on [page 93][]. + +[GPGPU]: http://en.wikipedia.org/wiki/GPGPU +[GPU]: http://en.wikipedia.org/wiki/Graphics_processing_unit +[NVIDIA]: http://www.nvidia.com/ +[CUDA]: http://en.wikipedia.org/wiki/CUDA +[GeForce GTX 580]: http://www.nvidia.com/object/product-geforce-gtx-580-us.html +[page 14]: http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/CUDA_C_Programming_Guide.pdf#page=14 +[page 93]: http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/CUDA_C_Programming_Guide.pdf#page=93 +[page 94]: http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/CUDA_C_Programming_Guide.pdf#page=94 +[page 111]: http://developer.download.nvidia.com/compute/cuda/3_2/toolkit/docs/CUDA_C_Programming_Guide.pdf#page=111 + +[[!tag tags/hardware]] +[[!tag tags/programming]] -- 2.26.2