Pradeep Garigipati

> This will have a serious performance impact, since the code generation is take more time than the exécution of the resulting kernel. You will also have to generate the...

@willyborn I was under the impression you closed it intentionally to avoid repetitive ci builds or something similar.

@willyborn Also, can you please remove the merge commit from this branch With your master even with arayfire's master branch, `git rebase master` should remove it the merge commit. Also,...

@willyborn Sorry about the delay on my end. Have been caught up with some work and other things. I will take a stab at this week. If it isn't hard,...

@willyborn Any idea on the ETA when this should be ready ? rough estimate is good.

@willyborn Sure, please do. We can have the JIT caching issue fix in 3.8.1. I am curious, if this fix is relevant to master or is it on top of...

@laser101 I think the solution suggested by @umar456 [here](https://github.com/arrayfire/arrayfire/issues/2917#issuecomment-636993181) about adding another version of API suffixed by V2 is good way to go about it I think. We are due...

@christopher-gee Can you please run the test using gdb and share the stack trace. Error from issue description indicates that is not accuracy error but routine failed to launch totally....

@willyborn I will look into it this week, thanks for the logs. Update: Note that, CPU backend compute upstreams won't have any effect on OpenCL backend. OpenCL backend uses combination...

I was unable to reproduce the svd_dense failure on windows so far both in debug and relwithdebinfo configurations using MSVC toolchain. Nevertheless, will try to reproduce on linux if not...