| commit | 4d6ead734c4999b3dca2dbb5bec7648a59eada71 | |
| author | Szilárd Páll <pall.szilard@gmail.com> | |
| Tue, 29 Sep 2015 00:06:09 +0000 (29 02:06 +0200) | ||
| committer | Mark Abraham <mark.j.abraham@gmail.com> | |
| Thu, 15 Oct 2015 12:59:49 +0000 (15 14:59 +0200) | ||
| tree | 9681845dd255a66de1da5546ea2ec06b84552172 | treesnapshot (tar.gz zip) |
| parent | 8e5fbe6d8d1d18392613a3b034cdba18cceb42ce | commitdiff |
Add CUDA nvcc >=7.0 support
With CUDA 7.x, there is a few % performance benefit to using sm_52
arch as target instead of JIT-ed compute_50, mostly relevant with
the newly released v7.5 (as v7.0 has other regressions which make it
slower).
This change adds a single new target architecture (5.2) and changes
the virtual architecture included in the binary from 5.0 to 5.2 with
new enough nvcc to make 5.1.x versions future-proof when new hardware is
released.
Change-Id: I062cc48a151da3ab15b0508f4ebd59d95880ae9a
With CUDA 7.x, there is a few % performance benefit to using sm_52
arch as target instead of JIT-ed compute_50, mostly relevant with
the newly released v7.5 (as v7.0 has other regressions which make it
slower).
This change adds a single new target architecture (5.2) and changes
the virtual architecture included in the binary from 5.0 to 5.2 with
new enough nvcc to make 5.1.x versions future-proof when new hardware is
released.
Change-Id: I062cc48a151da3ab15b0508f4ebd59d95880ae9a
| cmake/gmxManageNvccConfig.cmake | diffblobblamehistory |