Deutsch English Français Italiano |
<2024May20.125648@mips.complang.tuwien.ac.at> View for Bookmarking (what is this?) Look up another Usenet article |
Path: ...!news.mixmin.net!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: anton@mips.complang.tuwien.ac.at (Anton Ertl) Newsgroups: comp.arch Subject: binary128 implementation (was: Making Lemonade (Floating-point format changes) Date: Mon, 20 May 2024 10:56:48 GMT Organization: Institut fuer Computersprachen, Technische Universitaet Wien Lines: 26 Message-ID: <2024May20.125648@mips.complang.tuwien.ac.at> References: <abe04jhkngt2uun1e7ict8vmf1fq8p7rnm@4ax.com> <memo.20240512203459.16164W@jgd.cix.co.uk> <v1rab7$2vt3u$1@dont-email.me> <20240513151647.0000403f@yahoo.com> <v1to2h$3km86$1@dont-email.me> <20240514221659.00001094@yahoo.com> <v234nr$12p27$1@dont-email.me> <20240516001628.00001031@yahoo.com> <v2cn4l$3bpov$1@dont-email.me> <v2d9sv$3fda0$1@dont-email.me> <20240519203403.00003e9b@yahoo.com> Injection-Date: Mon, 20 May 2024 13:10:45 +0200 (CEST) Injection-Info: dont-email.me; posting-host="481c197852760d18650e1e4ce71128a0"; logging-data="4161579"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18/hy1RlFptITKjiF51Yr2J" Cancel-Lock: sha1:xI/t+Qh5S/cOMbQ4UmxwtN83H2Q= X-newsreader: xrn 10.11 Bytes: 2359 Michael S <already5chosen@yahoo.com> writes: >On Sun, 19 May 2024 18:37:51 +0200 >Terje Mathisen <terje.mathisen@tmsw.no> wrote: >> The FMA normalizer has to handle a maximally bad cancellation, so it >> needs to be around 350 bits wide. Mitch knows of course but I'm >> guessing that this could at least be close to needing an extra cycle >> on its own and/or heroic hardware? >> >> Terje >> > >Why so wide? >Assuming that subnormal multiplier inputs are normalized before >multiplication, the product of multiplication is 226 bits The product of the mantissa multiplication is at most 226 bits even if you don't normalize subnormal numbers. For cancellation to play a role the addend has to be close in absolute value and have the opposite sign as the product, so at most one additional bit comes into play for that case (for something like the product being 0111111... and the addend being -10000000...). - anton -- 'Anyone trying for "industrial quality" ISA should avoid undefined behavior.' Mitch Alsup, <c17fcd89-f024-40e7-a594-88a85ac10d20o@googlegroups.com>