🚀 go-pugleaf

Christopher C. Wood wrote:
> Tetsuji Ueda wrote:
> |> I apologize for the misunderstanding, what I said wasn't very clearly
> |> stated.  The article concerning the BYTEMark bug is at:
> 
> |> http://www.byte.com/art/9512/sec4/art2.htm
> 
> Which was published in December of 1995.  Do you think that the same
> magazine would run the erroneous November 1995 numbers a month after
> they published their correction?  Or the corrected numbers?
> 
> |> I pointed out this reference since the November 95 article seems to be
> |> passed around as gospel, quite often without mention of the bug.
> 
> I clearly identify the text above as taken from the January 1996
> Byte.  Which was published a month after the corrections were
> announced.

That is correct.  And I did state that the original comment concerning
the December article was as an addendum to the November article.  The
January article does have the corrected values.  I did not assert
otherwise.  The comment about the better performance was for the 200MHz
version and not 150MHz version of the P6; the BYTEMark values for the
200MHz version is not given in the January'96 issue but in the
February'96 issue of BYTE  (of course, standard disclaimer of how useful
BYTEMark benchmarks are in comparing cpu's apply).  I wasn't clear about
this in my original post, thus the misunderstanding.

> |> I did want to point out that I (IMHO) disagree with people posting
> |> benchmark references without being clear about the systems (cpu, bus,
> |> cache, memory, core logic, etc) and the compilers (optimization,
> |> library, etc.) which are used. For instance, one interesting page to
> |> look at is
> 
> Granted, Byte did not publish which compiler was used for the
> benchmarks I quoted.  The systems were specified, and one could go to
> the manufacturers for the rest of the specs.
> 

My posts weren't intended to support the superiority of either chip, but
to caution those who would hold specific benchmark results as gospel.
Please do look at the reference which I indicated earlier:
 http://www.mot.com/SPS/PowerPC/library/technical_papers/performance/mac_bm/b12.html
(PowerMAC9500/132 BYTEMark fp test results with various compilers)

to see an indication of how comparative differences in benchmarks for
various platforms can easily be overshadowed by using superior
compilers.


Peace and good will,

Tetsuji Ueda
----------------------------
My other computer is a Cray!
----------------------------