On 12/28/21 13:03, [email protected] wrote:
From: Matheus Ferst <[email protected]>The non-signalling versions of VSX scalar convert to shorter/longer precision insns doesn't silence SNaNs in the hardware. To better match this behavior, use the non-arithmatic conversion of helper_todouble instead of float32_to_float64. A test is added to prevent future regressions. Signed-off-by: Matheus Ferst <[email protected]>
Applied in ppc-next. Thanks, C.
