Compile kernel as task not as NDRange

[Altera_Forum]

Hi, 

 My design has multiple kernels communicating through channels forming a chain like this:  Kga -> Kconf -> Kene -> Kst  It is running correctly in emulation, but some information in the optimization report seems strange to me: Specifically, one kernel (Kga) is compiled as NDRange, although no work-item function is used in any kernel.  Is there any function/statement that is causing this kernel to be compiled as NDRange?

[Altera_Forum]

Try adding __attribute__((max_global_work_dim(0))) for that kernel, this should ensure it is compiled as a single work-item kernel.  

 source: aocl programming guide, 2.3.1.1 (https://www.altera.com/en_us/pdfs/literature/hb/opencl-sdk/aocl_programming_guide.pdf#page=136)

[Altera_Forum]

Thanks for the info.  

I added that attribute, but unfortunately that kernel is still being compiled as ND-Range.  The log shows warnings: "Compiler Warning: Channel ordering barrier insertion in X of Kernel Kga, but kernels may hang as a result"  I don´t know how to interpret this warning. Have you experienced something like this before?

[Altera_Forum]

If you are able to post your code it will help immensely :)

[Altera_Forum]

I recompiled it and now it gets compiled as task. 

 thank you.

[Altera_Forum]

An alternative to using __attribute__((max_global_work_dim(0))) is also __attribute__((task)) which should also do the same thing