On Fri, 15 Feb 2019 at 19:23, Richard Henderson <richard.hender...@linaro.org> wrote: > > Signed-off-by: Richard Henderson <richard.hender...@linaro.org>
Encoding stuff is all OK, but as noted in previous email I think we're going to have fpstatus awkwardness. (The code in this patch always selects the non-fp16 fpstatus, which is right for everything except for handling FZ16 on the float16 inputs.) thanks -- PMM
