diff options
| author | David Phillips <david@sighup.nz> | 2017-02-18 15:07:47 +1300 |
|---|---|---|
| committer | David Phillips <david@sighup.nz> | 2017-02-18 15:07:47 +1300 |
| commit | cbffd522bf85c0acd15c630a62eb7c0e0c36b6df (patch) | |
| tree | 34bd26e16574c19565e68eb79d1eead4293caf9c | |
| parent | d356d2bea1a5c0012bf6ef746a90f86b2076d9c2 (diff) | |
| download | fractal-gen-opencl-cbffd522bf85c0acd15c630a62eb7c0e0c36b6df.tar.xz | |
Tidy performance data, disclose float size difference
| -rw-r--r-- | README.md | 13 |
1 files changed, 5 insertions, 8 deletions
@@ -22,11 +22,8 @@ than CPU, but once you start upping the image size and detail, a modern GPU will provide endless benefit over a modern CPU. For example, using the CPU-based fractal-gen, a 10240x10240 pixel image at -1000 iteration cutout per pixel, the image will complete in just under 4 -minutes when running on all 32 threads of a dual-Xeon E5-2670 setup. Compare -this to the runtime of this software on a (much cheaper) NVIDIA GTX 1070; about -0.5 to 1 second. - -The gap only widens with more detail. Keeping the same image dimensions and -climbing up to 10000 iterations, the Xeons will take 2200 seconds; just under -37 minutes. The GTX 1070 takes just over 1 second. +10000 iteration cutout per pixel, the image will complete in about 2200 seconds +when running on all 32 threads of a dual-Xeon E5-2670 setup. Compare this to +the runtime of this software on a (much cheaper) NVIDIA GTX 1070; 1 second. + +This is using single-precision floats on the GPU. |