Following up on the as yet unresolved thread initiated here: http://mail.openjdk.java.net/pipermail/core-libs-dev/2015-September/035289.html
Thanks, Brian On Sep 21, 2015, at 11:15 AM, Brian Burkhalter <brian.burkhal...@oracle.com> wrote: > Hello, Sergey, > > On Sep 19, 2015, at 12:51 PM, Sergey Bylokhov <sergey.bylok...@oracle.com> > wrote: > >> Hello, I have a related question about the adding of methods to the Math >> class. Some methods **Exact methods were added to the Math class in jdk8, >> which throws an exceptions in case of overflow. Is it possible to add the >> similar saturation arithmetic? It would be quite good to realize a full >> range of these methods, and give the chance to hotspot to use an intrinsic. > > If there are particular methods of interest and there are no corresponding > issues on file, then one or more issues should be filed in the Java Bug > System so that we may consider and track them according to the usual process. > As there is currently an attempt to address some of the omissions in the Math > area, now would be a good time to get these issues on record. So I suggest > that the interested parties do just that. I think that one issue containing > several method requests would be sufficient if it concerns the same area of > code. > > As to the compiler intrinsics, we are looking into adding a few math-related > things here as well. This would be tracked by a separate issue which we would > file ourselves. > > Regards, > > Brian > >> This is mostly request from the java2d team: >> >> http://mail.openjdk.java.net/pipermail/core-libs-dev/2008-December/000954.html >> "I currently use an utility-class heavily for the XRender Java2D >> backend, which performs saturated casts: >> >> 1.) return (short) (x > Short.MAX_VALUE ? Short.MAX_VALUE : (x < >> Short.MIN_VALUE ? Short.MIN_VALUE : x)); >> 2.) return (short) (x > 65535 ? 65535 : (x < 0) ? 0 : x); >> >> I spent quite some time benchmarking/tuning the >> protocol-generation-methods, and a lot of cycles are spent in those >> saturated casts, even if the utility methods are static. >> E.g. XRenderFillRectangle takes 40 cycles without clamping, but >> already 70 cycles with on my core2duo with hotspot-server/jdk 14.0. >> Hotspot seems to solve the problem always with conditional jumps, >> although well predictable ones. >> >> Modern processors seem to have support for this kind of operation, in >> x86 there's packssdw in MMX/SSE2. >> I think something like a saturated cast could be quite useful, there >> are already cast-methods in Long/Integer/Short - what do you think >> about adding saturated casts to that API? >> Those could be instrified to use MMX/SSE2 if available. >> >> If that would be too specific how hard would it be to add this kind of >> optimization to hotspot? >> How far does SIMD support in hotspot go (I read some time ago there've >> been some optimizations), if SIMD would be supported 4 casts could be >> done in a single cycle :) >
