tech-userlevel archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Support for non-default rounding modes in the softfloat layer



On Tue, Apr 30, 2013 at 01:28:47PM +0200, ????? ???????????? wrote:
> A lot of scientific software uses non-default rounding modes as
> optimisation short cut. but then this is software which runs on high
> end hardware a la SPARC T5, SPARC64, NEC SX9 or the very latest
> IA32/AMD64 hardware.

Ok, but the basic questions are:

 - does it switch between non standard rounding modes often?
 - does it use different rounding modes in different threads?

But, what I wonder most:

 - would the per-thread rounding mode penalty even matter if doing softfloat?

However, right now we also use softfloat for 128bit long doubles on
sparc64, maybe it is time to re-evaluate the timing vs. the fpu
emulation and fix this (it is a violation of the abi anyway).

Martin


Home | Main Index | Thread Index | Old Index