Path: ...!news.nobody.at!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: Terje Mathisen Newsgroups: comp.arch Subject: Re: Misc: Applications of small floating point formats. Date: Sat, 3 Aug 2024 11:47:01 +0200 Organization: A noiseless patient Spider Lines: 25 Message-ID: References: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Injection-Date: Sat, 03 Aug 2024 11:47:02 +0200 (CEST) Injection-Info: dont-email.me; posting-host="f92b7cac1ac350d69bc0d0d755577e22"; logging-data="3576112"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1/0cZYr8fmo00hPHpW+hbd/ajEE/LUdtfGQlZak0GW0yw==" User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Firefox/91.0 SeaMonkey/2.53.18.2 Cancel-Lock: sha1:Hxa5NDwoK6TooJ0GAn9iTW4tnps= In-Reply-To: Bytes: 1993 Lawrence D'Oliveiro wrote: > On Wed, 31 Jul 2024 18:31:35 -0500, BGB wrote: > >> Binary16 is useful for graphics and audio processing. > > The common format for CG work is OpenEXR, and that allows for 32-bit and > even 64-bit floats, per pixel component. So for example R-G-B-Alpha is 4 > components. > >> The 8-bit formats get a bit more niche; main use-cases mostly to save >> memory. > > Heavily used in AI work. The nicest property of fp8, as seen from a GPUs point of view, is that arbitrary operations can be seen as texture map lookups. I don't think that's how they are implemented but an 8x8->16 FMUL would only need a few very small lookup tables, probably doable even on a regular CPU with 16-element permute operations. Terje -- - "almost all programming can be viewed as an exercise in caching"