This content has been marked as final. Show 2 replies
Your testing is correct in that doing _neg on a double produces incorrect results for dmul and dmad but not dadd. As you have found out, the only correct way to negate is by negating the y and w components. Negating all components of a double should produce incorrect results because you are flipping a bit in the mantissa. Lu_decomposition is being removed from the SDK for now until we can clean up its code and produce better documentation for it. I'll make sure that this gets corrected before lu_decomposition is replaced in the SDK.
Thanks for confirming this.
Are there any other problems with IL known at the moment?
Perhaps AMD could consider keeping an updated "readme" or something available for the current SDK listing known issues and workarounds?
Thanks a lot,