Differences

This shows you the differences between two versions of the page.

--- faq:cuda_support [2014/02/25 10:02] – created oschuett
+++ faq:cuda_support [2022/03/09 13:17] (current) – oschuett
@@ Line 1: / Line 1: @@
 ====== Which parts of CP2K are CUDA-accelerated? ======
-  * FFTs, when compiled with ''%%-D__PW_CUDA%%''
+Have a look at our [[:gpu | GPU page]] as well as [[howto:compile_with_cuda | this howto ]].
-  * Anything that uses ''dbcsr_multiply'', when compiled with ''%%-D__DBCSR_CUDA%%''. This includes in particular the [[linear scaling DFT]] code.
-  * Anything that uses ''dgemm'' (**not** ''pdgem''), when linked against Cray's accelerated LibSci. Currently, this is most useful for the ''MP2'' method.