cancel
Showing results for 
Search instead for 
Did you mean: 

OpenCL

Highlighted
Adept II
Adept II

Bug in OpenCL compiler

Finally I made a minimal reproducing example of a bug in OpenCL compilers for Thaiti in Adrenalin Win10 x64 drivers (tested on two workstations with 19.12.2, 20.1.1 and 20.5.1 drivers with -O0 and -O5). Kernel is attached (it is a part of my realization of improved iterative Gauss-Seidel WDK-method for complex polynomial roots finding). As is, it gives wrong result for poly and its parts poly1 and poly2:

l=0, poly=0.0768369+0.00147968i, prod=13+6.62408e-17i, tau=-0.999259-0.0385005i
poly1=-8.84608e-18+1.99574i, poly2=0.0768369-1.99426i
{0,0.483322,0.966644,1.44997,1.93329,2.41661,2.89993,-2.89993,-2.41661,-1.93329,-1.44997,-0.966644,-0.483322}

Changing 1 to 2 in the loop upper limit miraculously gives the right result:

l=0, poly=-1.11022e-16+0i, prod=13+6.62408e-17i, tau=-0.999259-0.0385005i
poly1=0.997775+0.0192146i, poly2=-0.997775-0.0192146i
{0,0.483322,0.966644,1.44997,1.93329,2.41661,2.89993,-2.89993,-2.41661,-1.93329,-1.44997,-0.966644,-0.483322}

Another small changes in the code switch right and wrong results in a seemingly random way. For example, commenting out third line of output in printf here gives always right results, but when line of initial code

z -= cdiv(poly, prod);

is added before printf, result starts to be consistently wrong even without printf.

On my old laptop with 15.200.1065.0 drivers this bug is absent.

dipak #opencl 1.2#amd driver bug

5 Replies
Highlighted
Staff
Staff

Re: Bug in OpenCL compiler

Thank you for reporting this issue and providing the reproducible test-case. I'll try to reproduce it locally and get back to you shortly.

Thanks.

Highlighted
Staff
Staff

Re: Bug in OpenCL compiler

As I know, the AMDIL compiler toolchain, which was used for GCN1 cards like Tahiti, has been  discontinued and currently there is no plan to fix any issue related to this compiler. So, I doubt that the above issue will get fixed unless it is also reproducible on some newer cards (GCN2 and above).  

I ran the attached code on a GCN2 card but could not reproduce the issue. Please let us know if you observe the issue on any newer card.

Thanks.

Highlighted
Adept II
Adept II

Re: Bug in OpenCL compiler

That's a pity to know such a thing not from release notes of drivers but on the support forum only. My calculations need double precision so I'm locked to Tahiti. What is the latest version of drivers that had supported OpenCL on GCN1 cards then? I can roll back to 15.200.1065.0, but maybe later drivers will be faster.

0 Kudos
Reply
Highlighted
Staff
Staff

Re: Bug in OpenCL compiler

The latest Adrenalin drivers support OpenCL on GCN1 cards, but currently there is no plan to fix any OpenCL compiler related issues for these devices. I have also edited my earlier reply to clarify this point. 

Thanks.

0 Kudos
Reply
Highlighted
Adept II
Adept II

Re: Bug in OpenCL compiler

In case if somebody will have the same problem—it seems that the latest OpenCL implementation without this bug is 2004.6 of 16.4.2 Crimson drivers.