| PLEX86 | ||
MVCIN instructionLeonard Woren 3081d engine was only slightly faster than 3033 ... about five mips. 3081k engine was around seven mips (two processor aggregate 14mips). for two-processors, 370 typically slowed down each engine by 10 activity. originally 3081 was never targeted as having a single processor operation (3081 was two processors, 3084 was two 3081s tied together for four processors). somewhat because tpf (airline control program) didn't have multiprocessor support, 3083 was brought out ... which had the cycle time unslowed down ... so 3083j engine was nearly 15 percent faster than 3081k engine. Vintage Computer Festival 8.0 Event Guide Vintage Computer Festival 8.0 Saturday & Sunday, November 5-6 Computer History Museum Mountain View, California This is your complete VCF 8.0 event guide! Vintage Computer Festival 8.0 happens this... a recent thread in comp.arch mentioning pok strong memory consistency and cycle slow-down some older posts mentioning kernel allocation cache-line work in the 3081 time-frame: a quick use of search engine turns up a little bit from above: This document contains performance claims and estimates for more than 2000 mainframes, minicomputers, supercomputers and workstations, from around 120 suppliers and produced between 1980 and 1996. Speed is given as MIPS (Millions of Instructions Per Second). Maximum MFLOPS (Millions of Floating Point Instructions Per Second) are also provided, usually for systems with supercomputer vector processing capabilities. Where available, production dates and cost is also shown. Details of IBM's larger mainframes and PC CPUs up to 2004 have also been included. .... 1311 vs 2311 disk capacity 2477 Okay, let's try this again; a power glitch caused my machine to crash, but apparently not before it spat... Manufacturer No. of OS MHz MIPS MAX Type Year Cost Processor CPUs CPU chip Claim MFLOPS £=GBP IBM OS VM-MVS 3083 E 1 ECL 38.5 4.7 MF 1982 $1.2M 3083 B 1 ECL 38.5 6.9 MF 1982 $2M 3083 J 1 ECL 38.5 8.9 MF 1982 $3M 3081 D 2 ECL 11 MF 1981 3081 G 2 ECL 38.5 12.6 MF 1983 $3.3M 3081 K 1 ECL 38.5 16 MF 1982 $4.3M 3084 Q 4 ECL 38.5 28 MF 1983 $8.7M 3083 CX 1 ECL 41.7 3.7 MF 1985 $605K 3083 EX 1 ECL 41.7 5 MF 1984 $960K 3083 BX 1 ECL 41.7 7.3 MF 1984 $1.7M 3083 JX 1 ECL 41.7 9.5 MF 1984 $2.6M 3081 GX 2 ECL 41.7 13.6 MF 1984 $2.8M 3081 KX 2 ECL 41.7 17.8 MF 1984 $3.4M 3084 QX 4 ECL 41.7 31 MF 1984 $6.9M 1311 vs 2311 disk capacity 2475 Sarr J. Blumson Well, I wouldn't trust my memory either. :-) But I believe the 1620 only had 4 data bits, or at... IBM OS MVS Cost excludes VF (MFLOPS results) Big Bertha Thing blogs 2473 Big Bertha Thing PI Cosmic Ray Series Possible Real World System Constructs Access page to 46K ZIP... 3090-120E 1 ECL 54.1 9 108 MF 1987 $985K 3090-150E 1 ECL 56.2 12.2 112 MF 1987 $1.65M 3090-180E 1 ECL 58.1 19.4 116 MF 1987 $2.7M 3090-280E 2 ECL 58.1 35.5 232 MF 1988 $4.9M 3090-200E 2 ECL 58.1 35.5 232 MF 1987 $4.6M 3090-300E 3 ECL 58.1 52 348 MF 1987 $5.6M 3090-400E 4 ECL 58.1 64 464 MF 1987 $8.4M 3090-500E 5 ECL 58.1 78 580 MF 1988 $9.7M 3090-600E 6 ECL 58.1 89 68 plus 16 MF 1987 $10.3M ... snip ... 1311 vs 2311 disk capacity 2476 Charlie Gibbs There was a whole art to calculating optimized block sizes for various S-360 tapes and disks. As you said, the maximum was theortical only. Not only did you...
|
||||
Alt Folklore Computers from Newsgroups The #1 Usenet Provider on the Internet
|
||||