pdpe1gb flag just means that your CPU understands 1GB mappings (i.e. page mapping in L3 page table).
This effort is to have THP mechanism create...
Announcement
Collapse
No announcement yet.
Search Result
Collapse
85 results in 0.0105 seconds.
Keywords
Members
Tags
-
[STRIKE]Nothing says 'welcoming environment' better than naming a component after a rape drug... [/STRIKE]
It shares a name with medication...Last edited by orome; 17 August 2020, 02:13 PM.
- Likes 1
Leave a comment:
-
There's WIP for mercurial. starting from mercurial 5 you canCode:HGPYTHON3=1 pip3 install --user mercurial
- Likes 1
Leave a comment:
-
it's more like:
AMD(2016): Buy APUs! It's next next heterogeneous thing! Call it HSA!
AMD: Don't call it HSA it's ROCm now!
AMD (2018):...
- Likes 7
Leave a comment:
-
I there was a patch every time someone whines about clover. It'd be feature complete OCL 2.2 by now....
Leave a comment:
-
it's more than that. Every ebuild was changed to include "rm -rf /". It wouldn't do much since ebuilds are run under non-privileged user.
Leave a comment:
-
yes, github enterprise allows on premises instances.
The license is not FOSS though.
"cgit and anongit will not be orphaned:...
- Likes 2
Leave a comment:
-
You can disagree as much as you want. If you were not supposed to use it you wouldn't need conformant implementation. You can force enable the extension...
Leave a comment:
-
No. OpenCL uses different compiler (LLVM), even native fp64 for pre-GCN asics that support it is missing. GL compute shaders should work though.
...Last edited by orome; 19 January 2018, 11:11 AM.
- Likes 3
Leave a comment:
-
even iGPU can use more bandwidth than DDR4 can provide. Most AMD GCN dGPU designs have ~7-9 GB/s bandwidth per CU. raven ridge (supposedly up to 11CUs)...
Leave a comment:
Bottom Ad
Collapse
Leave a comment: