[cfe-dev] ARM assembler regression?
renato.golin at linaro.org
Fri Nov 7 08:07:41 PST 2014
On 7 November 2014 15:33, Oliver Stannard <oliver.stannard at arm.com> wrote:
> This was caused by using “-mfpu=vfpv3-d16”, which only has 16 D registers.
> Switching to –mfpu=vfpv3 (with 32 D registers) is safe for Cortex-A targets,
> as all Cortex-A CPUs have 32 D registers (or no FPU).
Even those without NEON, like Tegra 3?
Using -mfpu=vfpv3 when you only have vfpv3-d16 is bound to create problems.
More information about the cfe-dev