Originally posted by entropy
View Post
Announcement
Collapse
No announcement yet.
Bridgman Is No Longer "The AMD Open-Source Guy"
Collapse
X
-
I like to thank John for his replies on this forum.
I learned allot from it, and was happy the way he replied when I had a problem.
No bs because he worked for amd.
I am also happy he did not run away from the sometimes unfair attacks. ( unfair as in, that he was too blame for everything amd ever did, or did not )
Tim welcome.
I might be an optimist, but what I understand from this thread, is that AMD has learned from earlier mistakes.
More people are now working on the linux part.
Comment
-
Originally posted by Plombo View PostThere isn't any reverse engineering effort that I know of. The reason is probably less technical and more that no one's bothered to do it.
and thus a major obstacle to reverse-engineering efforts, even for unprotected data streams.
Comment
-
Well, speaking of compilers:
Do you have any information regarding open CL support on AMD GNC?
Folding on AMD 7970 is worthless. PG claims that AMD sdk does not sufficiently support open CL, hence open MM is not optimized, and hence Folding Cores are not optimized.
I know it is a topic that is a bit of a stretch for this forum....but I do see in this case where robust compilers, open Cl drivers will be paramount to the success of the HSA initiative.
I have had my card since January, and it works well for gaming, but the compute potential of the new architecture is certainly not being utilized to its fullest across the software ecosystem.
Blame is often directed back at AMD for failures of compilers and drivers.
Just curious about your inside perspective and opinion if this will happen soon, or if the compute capability of discrete graphics will be eclipsed / replaced by the HSA initiative.
Comment
-
Originally posted by cube View PostHow is that possible, that Intel has open source video acceleration for a long time (from the beginning?) on (AFAIK) nearly all graphics chips, and AMD can't do it ? And they still support DRM and HDCP on Windows - as we can see, it can be done...## VGA ##
AMD: X1950XTX, HD3870, HD5870
Intel: GMA45, HD3000 (Core i5 2500K)
Comment
-
Originally posted by mdk777 View PostWell, speaking of compilers:
Do you have any information regarding open CL support on AMD GNC?
Folding on AMD 7970 is worthless. PG claims that AMD sdk does not sufficiently support open CL, hence open MM is not optimized, and hence Folding Cores are not optimized.
The scientific community still swears by CUDA, because nvidia dumped a lot of marketing effort into the science community. Convincing them to try OpenCL instead of CUDA, is like trying to convert a Fortran user to C/C++/..., because "Fortran is on average 10% faster" (you hear that a lot from these guys).
I don't know who PG is, but send him some current benchmarks of similar code on CUDA and OpenCL and tell him that the SDKs are ready.
Comment
-
Originally posted by Gps4l View PostI like to thank John for his replies on this forum.
I learned allot from it, and was happy the way he replied when I had a problem.
No bs because he worked for amd.
I am also happy he did not run away from the sometimes unfair attacks. ( unfair as in, that he was too blame for everything amd ever did, or did not )
Tim welcome.
I might be an optimist, but what I understand from this thread, is that AMD has learned from earlier mistakes.
More people are now working on the linux part.
and.. I long for a day when opensource AMD's linux GPU on par with Intel's
Comment
-
1. Moving to a new shader architecture (GCN), new memory management (GPUVM) and new shader compiler (llvm) at the same time. This was kind-of necessary but it meant that we had far more work in process where you couldn't see an obvious benefit. Using llvm was partly to build a good foundation for an open source OpenCL stack, and partly to get a more capable shader compiler into the graphics stack.
This first point in Bridgeman's post is what I was talking about.
These steps made code optimized for the previous architecture run like crap on the new.
While your experience:
This is not true from my experience. Back in the Stream SDK < 2.4 days there were always some bugs encountered, but OpenCL is fully supported now.
I understand that HSA will benefit from eliminating the PCIE bus and associated legacy.
However, it will be difficult to develop a software ecosystem when you can't model a integrated GPU on the start of the art discrete card (AMD 7970 performing worse than a AMD 6850)
Anyway, I didn't come to complain, just asking how they see the SDK development, if they are achieving their goals.
Comment
Comment