mn416

Hi @wimrijnders, Accessing the SFU sounds very similar to accessing the TMU. You could follow the `gather()` and `receive()` functions through the compiler to see how it works.

My suggestion to look at `receive()` and `gather()` was not just to see how the DSL syntax construction works. You will see the AST elements (`LOAD_RECEIVE` and `TMU0_ADDR`) used to...

Hi @wimrijnders, > Do you optimize for that already? Otherwise, there is much to be won here! Sadly not! Would be cool if we did...

Indeed. I think the main bottleneck in QPULib is the inability for the programmer to cache arbitrary data in the VPM and repeatedly access it without having to keep going...

Hi @robiwano, I agree, this is a desirable feature. There seem to be two possible approaches: 1. Support `Ptr` in kernel arguments 2. Support a new variant of kernel `call`,...

Thanks for the debug info. The `getPointer()` method in `SharedArray.h` looks wrong: ```c++ T* getPointer() { return (T*) &emuHeap[address]; } ``` I think it should be: ```c++ T* getPointer() {...

Correction, I think it's: ```c++ T* getPointer() { return (T*) (address*4); } ```

Thanks @crmann25, @zertyz, and @m516 for reporting this. I've pushed a commit to include `-fpermissive` in the default compiler flags as a workaround for now. Sorry I've been so slow...

Hi @wimrijnders, > I hope you can approve of this. Yes, sounds good. > However, it also looks like you're removing the previous code for direct memory access. Is this...

By the way, I had to disable the platform detection code because it said my Pi was not a Pi :). No doubt I am on a very old kernel,...