On 10/25/2022 7:27 AM, Andrew Haley wrote:
On Thu, 20 Oct 2022 20:26:47 GMT, Vladimir Ivanov <vliva...@openjdk.org> wrote:
The GCC bugs with `-ffast-math` only corrupts `FTZ` and `DAZ`.
But `RC` and exception masks may be corrupted as well the same way and I
believe the consequences are be similar (silent divergence in results during FP
computations).
I think we can catch the things that are likely, and will result in silent
corruption. We should limit this, I think, to rounding modes and
denormals-to-zero. I don't think we should bother with exception masks.
-------------
PR: https://git.openjdk.org/jdk/pull/10661
In terms of the overhead of using floating-point expression evaluation
as a guard, are there still platforms where operating on subnormal
values is pathologically slower? Some generations of SPARC chips had
that behavior where a subnormal multiply would take, say 10,000 cycles,
rather than 3 or 4 since the subnormal operations were implemented via
trap handling.
-Joe