Re: OpenCL miscompiles and I have a clean reproducible case
Yes. Though, I have to admit, I did have to wait half a year for it (yes, AMD had an internal bug number assigned, as I submitted a non-public, working, reproducible, bug-triggering code). So, next...
View ArticleClik here to view.
Re: OpenCL 8 GPU DGEMM (5.1 TFlop/s double precision). Heterogeneous HPL...
We say hello to our dear heterogeneous computing friends! Today we will discuss the recent news from the battlefield, and unfortunately they are not the cheerful news. For almost two years we have been...
View ArticleRe: trueaudio api?
Hello, we are interested in TrueAudio features and would like to test the API. Please reply.
View ArticleClik here to view.
DSYMM vs. DGEMM performance in ACML4.4.0
I observed something surprising (to me) about the performance of DSYMM vs. DGEMM in ACML4.4.0. Here is a snippet of of F90 code that applies a symmetric 1536-by-1536 matrix to a 1536-by-25 matrix:...
View ArticleRe: Radeon R9 290 4GB cards OpenCL info says 2GB global memory???
nou beat me to it AMD should make this the default (and fully support it), at least for card with 4Gb+For the Kaveri APU it should be the default. Especially under 64 bit OS's(or is Kaveri limited to...
View ArticleRe: OpenCL 8 GPU DGEMM (5.1 TFlop/s double precision). Heterogeneous HPL...
Thanks Anton, I just wanted to show my appreciation for your work and for reporting your findings. My opencl application is heavily dependent on double precision performance. A lot of people out there...
View ArticleRe: OpenCL miscompiles and I have a clean reproducible case
Hi Mate, Please report the other 3 bugs. I will have a look at it. Regards,Ravi
View ArticleRe: AMD 7970 reporting incorrect DEVICE_GLOBAL_MEM_SIZE
Hi everyone, I would like to re-post this question, as I don't think the two links provide an answer and I experience the same problem when querying the total amount of RAM using a R9 280X card with 3...
View ArticleRe: Radeon R9 290 4GB cards OpenCL info says 2GB global memory???
You might want to take a look here. I assume its the same problem (still waiting for an answer): AMD 7970 reporting incorrect DEVICE_GLOBAL_MEM_SIZE
View ArticleRe: Blender Cycles(Opencl on AMD GPUS)
Nou apology but I should modify variable name and variable value?.___________Nou disculpa pero que debo modificar en nombre de variable y valor de variable?.
View ArticleRe: Blender Cycles(Opencl on AMD GPUS)
don't edit PATH variable. just create new one with name CYCLES_OPENCL_TEST and value all. so you don't have start Blender through cmd.
View ArticleWhat's the reason for limiting input size in clAmdFft (clFFT)?
The FFT length in the clFFT library is limited to 2^24 SP and 2^22 DP respectively. What was the reason to do so? I'd like to tackle this in the open source version. But if there's a bigger limitation...
View ArticleClik here to view.
V4900 Blank Screens at Startup
I am having blank screens & have to restart a couple a times before the video card works correctly. Do you know how to eliminate that problem? We are using Autocad Inventor 2014 and the website...
View ArticleRe: OpenCL miscompiles and I have a clean reproducible case
msoos wrote: Yes. Though, I have to admit, I did have to wait half a year for it (yes, AMD had an internal bug number assigned, as I submitted a non-public, working, reproducible, bug-triggering code)....
View ArticleRe: Blender Cycles(Opencl on AMD GPUS)
This only works in cycles hd amd from 7000 onwards. Nou thank you very much. http://blenderartists.org/forum/attachment.php?attachmentid=287601&d=1391793621
View ArticleHow can you make it so that floating point operations are performed on the...
Kaveri has arrived, and as we all know there is some sharing of resources in the architecture of Kaveri and their predecessors. For one, two cores essentially share one floating point pipeline. I am...
View ArticleRe: Re: OpenCL miscompiles and I have a clean reproducible case
msoos wrote:PS: It's really-really not a good idea to have 2 libamdocl64.so. One of them will be loaded, and you won't know which one. I personally would delete all of /opt/AMDAPP + all of...
View ArticleRe: How can you make it so that floating point operations are performed on...
well Kaveri is first APU which have unified memory space between CPU and GPU part. that mean you don't need copy data between CPU and GPU. this is main overhead in GPGPU computing. starting the task is...
View ArticleRe: Re: OpenCL miscompiles and I have a clean reproducible case
Personally I don't install AMD APP SDK on Linux. it have quite lot of issues. I just manually extract include/CL to /usr/include and leave everything else to catalyst driver installation. Putting...
View ArticleRe: Multiple contexts parallel allocating or writing to memory of a single...
Does all these mean that I can do operations below? 1)Create single context. 2)Create single oredered queue for all kernels. 3)Create an oredered queue for each write/read operation. So if I have N...
View Article
