Convex Computer: Difference between revisions

Revision as of 15:10, 3 May 2023

Revision as of 19:18, 2 November 2023

Line 22:

[[File:Convex C-1 (1985) - Computer History Museum (2007-11-10 22.58.44 by Carlo Nardone).jpg|thumb|165px|Convex C-1 (1985)]]

Their first machine was the '''C1''', released in 1985. The C1 was very similar to the [[Cray-1]] in general design, but its CPU and main memory was implemented with slower but less expensive CMOS technology. They offset this by increasing the capabilities of the vector units, including doubling the vector registers' length to 128 64-bit elements each.<ref>{{cite web | date=Fall 1996 |page=8| first= David A. |last=Patterson | title = Lecture 6: Vector Processing | url = http://www.eecs.berkeley.edu/~pattrsn/252F96/Lecture06.pdf | accessdateaccess-date = 2011-04-29 | authorlinkauthor-link = David Patterson (scientist)}}</ref> It also used [[virtual memory]] as opposed to the static memory system of the Cray machines, which improved programming. It was generally rated at 20 MFLOPS peak for double precision (64-bit), and 40 MFLOPS peak for single precision (32-bit), about one fifth the normal speed of the Cray-1. They also invested heavily in advanced automatic vectorizing [[compiler]]s in order to gain performance when existing programs were ported to their systems. The machines ran a [[Berkeley Software Distribution|BSD]] version of [[Unix]] known initially as '''Convex Unix''' then later as '''ConvexOS''' due to trademark and licensing issues. ConvexOS has DEC [[OpenVMS|VMS]] compatibility features as well as Cray Fortran features. Their Fortran compiler went on to be licensed to other computers such as [[Ardent Computer]] and Stellar (and merged Stardent).

[[File:BSC-Convex-240.JPG|right|thumb|250px|Convex 240 supercomputer (1988))]]

Line 31:

Another speed boost used in the '''C3''' and '''C4''', which moved the hardware implementation to [[Gallium arsenide|GaAs]]-based chips, following an evolution identical to that of the Cray machines, but the effort was too little, too late. Some considered the whole C4 program to be nothing more than chasing a business in decline.{{sayswho|date=July 2017}} By this time, even though Convex was the first vendor to ship a GaAs based product, they were losing money.

In 1994, Convex introduced an entirely new design, known as the '''Exemplar'''. Unlike the C-series vector computer, the Exemplar was a parallel-computing machine that used HP [[PA-7200]] microprocessors, connected together using [[Scalable Coherent Interconnect|SCI]]. First dubbed '''MPP''', these machines were later called '''SPP''' <ref>{{cite conference|first1=R. |last1=Cataneda|first2= Xiaodong |last2=Zhang|first3= J. M., Jr. |last3=Hoover|title=A comparative evaluation of hierarchical network architecture of the HP-Convex Exemplar|conference=IEEE International Conference on Computer Design|year= 1997|doi=10.1109/ICCD.1997.628877}}</ref> and '''Exemplar''' and sold under the '''SPP-1600''' moniker. The expectation was that a software programming model for parallel computing could draw in customers. But the type of customers Convex attracted believed in [[Fortran]] and brute force rather than sophisticated technology. The operating system also had terrible performance problems which could not easily be fixed. Eventually, Convex established a working partnership with HP's hardware and software divisions. Initially it was intended that the Exemplar would be binary-compatible with HP's [[HP-UX]] operating system but eventually it was decided to port HP-UX to the platform and sell the platform as standalone servers.

[[File:BSC-HP-V-Class.JPG|right|thumb|250px|HP V-Class computer.]]