Re: Commutative law in addition in XL Fortran

On May 11, 7:40 pm, Dick Hendrickson <dick.hendrick...@xxxxxxx> wrote:
James Giles wrote:
robert.corb...@xxxxxxx wrote:
On May 10, 3:11 pm, "James Giles" <jamesgi...@xxxxxxxxxxxxxxxx> wrote:

(the original Cray had a non-commutative multiply and it was
so unpopular that later versions has a slightly less accurate
multiply that *was* commutative).
IIRC, the first two Cray 1's had the problem. Again IIRC, the fix was
to sort the operands, which would not affect the accuracy.

Could be. Still I seem to remember there was some sort of price
to pay. Maybe it was a clock slower. With pipelining that would
have been a minor price. Anyone know for sure?

It's been a long time. My recollection is that serial 1 had a
non-commutative multiply. It also had a memory system that only had
a simple parity check. Los Alamos had issues with both features.
Because of the problems, serial 2 was scrapped and serials 3+ were
modified to include a commutative multiply and SECDED in the memory
system. I think this added one cycle to the multiply time and one
or two to the memory time. I believe the fix was a real change to
the multiply pyramid and didn't involve sorting the operands.

You are correct. I found both a Cray-1 and a Cray-1S hardware
reference manual at http://bitsavers.org. The change to make the
multiplication commutative was to change which bits were retained for
the sum of the products of the bits.

Bob Corbett

.

Relevant Pages

  • [ANNOUNCE] Linux-2.4.32-hf32.5
    ... Fix memory corruption caused by snmp_trap_decode which may free ... to 2.4.32 kernels use neither of these timers. ... on 2.4 update the inode ctime on rename. ...
    (Linux-Kernel)
  • Re: [RFC][mmotm] Documentation update
    ... Memory Resource ControllerImplementation Memo. ... will fix. ... charge against oldpage or newpage will be committed. ... Page Migration ...
    (Linux-Kernel)
  • Re: XP Setup hangs with dual PIII-550 on Asus P2B-DS v1.04
    ... I have one IDE 80Gb drive attached to Primary IDE and one CD-ROM on the secondary IDE. ... It might be a memory issue, but in the one CPU config the installation always works without a hitch, which leads me to believe the memory issue if it exists is not the main problem. ... Do you happen to know if moving the R79 to R80 is the correct fix for ACPI and what it actually does? ... about 2-3 minutes with only a reset helping.. ...
    (alt.comp.periphs.mainboard.asus)
  • Re: USB transfer_buffer allocations on 64bit systems
    ... memory that is suitable for DMA. ... That is not a good fix. ... a clear note about how to allocate buffers for USB drivers. ...
    (Linux-Kernel)
  • Re: [tip:perfcounters/core] perf_counter: Simplify and fix task migration counting
    ... Simplify and fix task migration counting ... memory corruptions under load. ... return ctx; ...
    (Linux-Kernel)