From 892e47a653a8a3f0874cda194c7c31948957c97d Mon Sep 17 00:00:00 2001 From: Andrzej Janik Date: Mon, 23 Nov 2020 22:37:57 +0100 Subject: [PATCH] Update README with links to GeekBench results --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4a90b96b..181a71f4 100644 --- a/README.md +++ b/README.md @@ -9,9 +9,13 @@ One measurement has been done using OpenCL and another measurement has been done Performance below is normalized to OpenCL performance. 110% means that ZLUDA-implemented CUDA is 10% faster on Intel UHD 630. -![](GeekBench_5_2_3.svg) +![Performance graph](GeekBench_5_2_3.svg) -Overall in this suite of benchmarks ZLUDA is roughly 4% faster. +[ZLUDA detailed log on Geekbench.com](https://browser.geekbench.com/v5/compute/1918048) + +[OpenCL detailed log on Geekbench.com](https://browser.geekbench.com/v5/compute/1918080) + +Overall in this suite of benchmarks faster by approximately 4% on ZLUDA. ### Explanation of the results * Why is ZLUDA faster in Stereo Matching, Gaussian Blur and Depth of Field?\