From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me X-Spam-Level: X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00 autolearn=unavailable autolearn_force=no version=3.4.4 X-Received: by 2002:a6b:1a8e:: with SMTP id a136-v6mr7419746ioa.66.1529446457228; Tue, 19 Jun 2018 15:14:17 -0700 (PDT) X-Received: by 2002:a9d:4b04:: with SMTP id q4-v6mr6486otf.3.1529446457126; Tue, 19 Jun 2018 15:14:17 -0700 (PDT) Path: eternal-september.org!reader01.eternal-september.org!reader02.eternal-september.org!feeder.eternal-september.org!border1.nntp.ams1.giganews.com!nntp.giganews.com!newsfeed.xs4all.nl!newsfeed8.news.xs4all.nl!85.12.16.68.MISMATCH!peer01.ams1!peer.ams1.xlned.com!news.xlned.com!peer01.am4!peer.am4.highwinds-media.com!peer02.iad!feed-me.highwinds-media.com!news.highwinds-media.com!u78-v6no490165itb.0!news-out.google.com!z3-v6ni546iti.0!nntp.google.com!u78-v6no490160itb.0!postnews.google.com!glegroupsg2000goo.googlegroups.com!not-for-mail Newsgroups: comp.lang.ada Date: Tue, 19 Jun 2018 15:14:16 -0700 (PDT) Complaints-To: groups-abuse@google.com Injection-Info: glegroupsg2000goo.googlegroups.com; posting-host=47.185.195.62; posting-account=zwxLlwoAAAChLBU7oraRzNDnqQYkYbpo NNTP-Posting-Host: 47.185.195.62 User-Agent: G2/1.0 MIME-Version: 1.0 Message-ID: Subject: Ada lacks lighterweight-than-task parallelism From: "Dan'l Miller" Injection-Date: Tue, 19 Jun 2018 22:14:17 +0000 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Received-Bytes: 3601 X-Received-Body-CRC: 2103364177 Xref: reader02.eternal-september.org comp.lang.ada:53177 Date: 2018-06-19T15:14:16-07:00 List-Id: http://www.theregister.co.uk/2018/06/18/microsoft_e2_edge_windows_10 As discussed in the article above, Microsoft is starting to unveil its form= erly-secret development of what could be described as =E2=80=9CItanium done= right=E2=80=9C. Whereas Itanium was VLIW jammed force-fit into an otherwise traditional ISA= that had 8 concurrent sub-instructions per VLIW-instruction (and where mos= t simultaneous multithreading [SMT] processor cores can execute up to 2 thr= eads per processor-core on Intel, AMD, and IBM POWER processors), Microsoft= 's Explicit Data Graph Execution (EDGE) processor slices programs into up t= o 32 independent slices per thread/task. Whereas Itanium insisted on the =E2=80=A2compiler=E2=80=A2 at engineering-t= ime finding 8 independent slices within a program, EDGE performs the analog= ue of such analysis in hardware at runtime=E2=80=94hence, overcoming one of= Itanium's fatal flaws. (The other fatal flaw on which Itanium was misfoun= ded was that the compiler could not predict at engineering-time the wildly = varying latencies of L1 cache versus L2 cache versus L3 cache versus local = DRAM versus ccNUMA-network DRAM; EDGE appears to mitigate that as well by a= pparently picking slices with the same timing characteristics or compatibly= -interleavable timing characteristics.) And EDGE processor is being currently sampled at 10nm manufacturing process= through Qualcomm. And Windows 10 has been successfully ported to EDGE processor (which is sta= rting to look like a future product announcement for some forthcoming new M= icrosoft device). And viola neither Ada nor POSIX threads, on the front end, have representat= ions of slices. Nor do any extant Ada compilers have representation of sli= ces on the backend=E2=80=94which is a true shame because slices would have = been one of the enabling technologies for Itanium 18 (!) years ago. 18 yea= rs ago. I think Rumpelstiltskin slept for less time duration than that. And this initial era of EDGE appears to be single-core. Imagine 2-core and= 4-core and 8-core editions in the future for 64-, 96-, and 128-slice paral= lelism. Ada for the Cold War in 1983 would focus on tasks as the only vehicle for p= arallelism. Ada for the 21st century would also embrace/facilitate slices = somehow, via some sort of locality of reference or via some sort of demarca= tion of independence.