phd_ivo@gsbacd.uchicago.edu (04/04/89)
floating point performance of the Motorola 68882. Is there help on the horizon? A plug-in compatible chip along the Weitek 80387 replacements that can speed up flp? And why is the 68882 so slow when compared with other chips that do essentially the same mathematical operations? Any info appreciated, with or without a disclaimer as to the employer's opinion. /ivo
mccalpin@loligo.uucp (John McCalpin) (04/04/89)
In article <2583@tank.uchicago.edu> phd_ivo@gsbacd.uchicago.edu writes: >floating point performance of the Motorola 68882. Is there help on the horizon? >A plug-in compatible chip along the Weitek 80387 replacements that can speed up >flp? And why is the 68882 so slow when compared with other chips that do >essentially the same mathematical operations? The 68881/2 are not really any worse performance-wise than their main competition, the 80x87 family. Both families are very slow. A substantial contributor to this is that both families of chips convert all input to an 80-bit format internally before use, and convert back to 32 or 64-bit formats afterward. Maybe someone from Motorola can say how the cycles are spent, but the 68882 takes about 40 cycles to do a floating-point add, compared with about 5 cycles on the MC88000 and 2 cycles on the MIPS R2010/3010. (No flames, please, these numbers are from memory and may be off a bit.) Maybe the co-processor for the 68040 will improve on this situation. On the bright side, both the Intel and Motorola chips make it easy to implement a robust IEEE-compliant floating-point system, since just about everything is done by the hardware. If the compiler is smart about keeping intermediate results on the co-processor's internal stack, then the extra accuracy can be helpful. The worst problem is that it is nearly impossible to figure out how much of your calculation got done in extended precision on-chip before being truncated back to 32 bits or 64 bits for storage in main memory. ---------------------- John D. McCalpin ------------------------ Dept of Oceanography & Supercomputer Computations Research Institute mccalpin@masig1.ocean.fsu.edu mccalpin@nu.cs.fsu.edu --------------------------------------------------------------------
beres@cadnetix.COM (Tim Beres) (04/05/89)
In article <7829@pyr.gatech.EDU> mccalpin@loligo.cc.fsu.edu (John McCalpin) writes: >The 68881/2 are not really any worse performance-wise than their main >competition, the 80x87 family. Both families are very slow... >...Maybe the co-processor for the 68040 will improve on >this situation. > Nit time: It has been reported (4/3/89 EE Times, for one) that the '040 will have an on-chip FPU, as will the '486. The '486 will also go with an on-chip 8K mixed instruction/data cache. I just read these rumours in the trade rags. ------>MY SOAPBOX (I speak for myself) NFS server george_bush not responding still trying Tim Beres beres@cadnetix.com {uunet,boulder,nbires}!cadnetix!beres
jangr@microsoft.UUCP (Jan Gray) (04/06/89)
In article <2583@tank.uchicago.edu> phd_ivo@gsbacd.uchicago.edu writes: >floating point performance of the Motorola 68882. Is there help on the horizon? >A plug-in compatible chip along the Weitek 80387 replacements that can speed up The Feb. 89 Microprocessor Report "Recent IC Announcements" describes the new Weitek 3168, a floating-point coprocessor for 680[23]0 systems that is claimed to be 2-4x faster than a 68882. Price(25 MHz): $499, quantity 2500; in production in September. Jan Gray uunet!microsoft!jangr Microsoft Corp., Redmond Wash. 206-882-8080