Re: Softfloat on i386

[Greg Troxel <gdt%lexort.com@localhost>]

Taylor R Campbell <riastradh%NetBSD.org@localhost> writes:

> For `NetBSD/i386' (which for a long time has really been i486DX -- the
> x87 floating-point unit has been mandatory for over a decade, though I
> did hear of someone working to revive optional x87 support for i386 or
> i486SX CPUs in the last year or so with kernel softfloat), that means
> x87 floating-point can be assumed but MMX/SSE/SSE2 requires runtime
> conditionals.
>
> In practice, well...  This only affects hardware that is >>20 years
> old, and there's likely to be a hefty performance impact on anyone
> using <20-year-old 32-bit CPUs (of which there are plenty, or 64-bit
> CPUs in a 32-bit userland).  How do we weigh these against each other?

I am not sure that your >>20 characterization is accurate for sse2.
There are embeddedish CPUs that lack sse2 that i think are newer than
that but I'm unclear on the details.


I am ok with requiring floating point instructions, and run-time sse2 is
fine.  But with go, it seems that it's either "assume sse2" or
softfloat.

But it seems all are ok with just making it an option.  Or asking the
submitter of the PR to send a patch to do that.  (really)