Re: Direct State Access on Radeon 5870
This card is available for free at High performance computing on graphics processing units | hgpu.org. I think, you can test this there.
View ArticleRe: HSA Specification 1.0 released
Does Kaveri comply 100% with the HSA 1.0 specifications or will that come with Carrizo or Godavari or even later with Bristol Ridge?
View ArticleRe: S400 Synchronization Regression
Wondering if there any update on this. I haven't recieved any responses to my questions I sent to support in relation to this ticket. I was told to try the 15.3 Beta drivers, however the latest drivers...
View ArticleRe: glMultiDrawElementsIndirect() system hangs
I found the cause - it seems it doesn't like a zero count of elements in the indirect draw structs for some reason? If I remove said null elements its all fine. But that's a bit worrying if I want to...
View ArticleClik here to view.
HSA-OpenMP-GCC-AMD
Hi,I'm trying out HSAFoundation/HSA-OpenMP-GCC-AMD · GitHubThe instruction says to untar hsagcc.tar package. However, I can't find it in the repository. Is it supposed to be part of the git repository?...
View ArticleRe: Re: atiadlxy.dll not present on 32 Bit Windows
I don't know why are there 2 dlls. HADLModule:=LoadLibrary('atiadlxx.dll'); if HADLModule=0 then HADLModule:=LoadLibrary('atiadlxy.dll'); All I know is that this code loads the proper dll on...
View ArticleFailure to allocate buffer bigger than 2 GB on Windows 10
I have a R9 290X with 8GB and I'm using Windows 10 Build 10041. I have installed no extra software, SDKs or drivers on this test computer. The device claims to support allocations in one chunk of close...
View ArticleRe: glMultiDrawElementsIndirect() system hangs
Hi, Just to be clear, it sounds like you're seeing two problems here. First is that if you have a single draw in the indirect buffer with a count of zero indices, then the GPU hangs. The second is that...
View Articledouble-double for opencl
I'm after more precision than double. There is a couple of double-double libraries for CUDAOne from Nvidia...
View ArticleRe: Exact meaning of ALU latency measurements?
This is oddly informative. I can tell an answer is there but I cannot make sense of most of it! I'm not even sure what is this 4 stage pipeline. It was my understanding a wavefront would stay on a...
View ArticleRe: Failure to allocate buffer bigger than 2 GB on Windows 10
Try to set environmental variables GPU_MAX_HEAP_SIZE and GPU_MAX_ALLOC_PERCENT to 100 and check.Re: radeon 7970 3gb card only showing 2gb in 32bit linux For allocation of larger memory (4GB or more),...
View ArticleRe: BSOD / hang-up for OpenCL program
Hi Thomas, As you mentioned, you are able to reproduce the problem quite regularly, would it be possible to share a reproducible test-case with us? It would help us to investigate the problem from our...
View ArticleClik here to view.
Re: Old AMD-APP-SDK
You can download older app sdk packages from here: http://developer.amd.com/tools-and-sdks/opencl-zone/amd-accelerated-parallel-processing-app-sdk/download-archive/ For newer versions (2.9 and...
View ArticleRe: S400 Synchronization Regression
Unfortunately this is beyond what our development engineers can handle, so no further help here on the developer forum. The support team will have to replicate and deal with this.
View ArticleRe: clReleaseCommandQueue at program exit never returns
Yes, that explains it. See here opencl - clReleaseCommandQueue hangs when queue contains unexecuted kernels that are waiting on completion events - Stac… forfurther discussion. It turns out that...
View ArticleRe: Out of order queues
Out of order queues is part of the OpenCL standard since 1.0. Every GPU should support it AFAIK. I know however of one device that does not! Altera clearly states in its programming guide that its...
View ArticleRe: HSA-HLC stable and enqueue_kernel
Hi, Thanks for the ETA. As for the sample unfortunately it has two problems. First - it still uses provisional API. Second - it does not demonstrate enqueue_kernel call inside the kernel and does not...
View Articleprintf weirdness
Adding this to my kernel will print a message: printf("foo %d", 1);But adding this to my kernel will not print anything: printf("foo"); I am using the latest catalyst release driver. Thanks.
View ArticleRe: Direct State Access on Radeon 5870
Sure I understand, I imagine DSA isn't a hardware restriction for it. The Radeon 5870 is a good low end target these days and from the latest drivers it halfway supports OpenGL 4.5 already, so if it...
View Article