GNU workaround for Intel performance bug?

GNU workaround for Intel performance bug?

Post by Robert La Ferl » Fri, 20 Feb 1998 04:00:00



Is there a new version of the GNU compiler that works around the
latest Intel x86 performance bug?  If developers can get a new
compiler, you can increase memory read performance by up to 71%.

For detailed info on the bug affected 486, Pentium, Pentium Pro and
Pentium II CPUs:

http://www.intelligentfirm.com/membench/index.shtml

Robert

--
Robert La Ferla
Registered OPENSTEP/Rhapsody Consultant
HTI
Boston, MA - Washington, DC
+ 1 (617) 252-0088

 
 
 

GNU workaround for Intel performance bug?

Post by John Stur » Fri, 20 Feb 1998 04:00:00



> Is there a new version of the GNU compiler that works around the
> latest Intel x86 performance bug?  If developers can get a new
> compiler, you can increase memory read performance by up to 71%.

> For detailed info on the bug affected 486, Pentium, Pentium Pro and
> Pentium II CPUs:

> http://www.intelligentfirm.com/membench/index.shtml

> Robert

> --
> Robert La Ferla
> Registered OPENSTEP/Rhapsody Consultant
> HTI
> Boston, MA - Washington, DC
> + 1 (617) 252-0088

And pay $ to see the code that describes the flaw? Sheeyaw?

 
 
 

1. Workaround for GNU Obstack package?

Is there a workaround for using GNU's Obstack package under Windows 3.1?
I am porting a large machine-generated program from UNIX to MS-DOS, but
it crashes in the Obstack code although it compiles without a problem.
Before I put a lot of effort into learning how Obstack works, I'm hoping
that someone has been down this road before and that there is some way
to "dumb it down" (obstack) to 16-bits so that it will run in Windows.

More Details:
The C program I'm porting is a compiler generated by ELI, a compiler
construction tool.  On the Unix side, the gcc compiler is used and on
the MS-DOS side, the Borland C++ 4.0 compiler is used to make the DOS
.EXE.  What I want is to be able to invoke the compiler from inside
another Windows 3.1 application.

Thanks in advance,
Greg

2. Getting ATI-Mach64 to work properly under OS/2??

3. Somewhat OT: Anyone used Intel's Integrated Performance Primitives with DirectShow.

4. S25+Palm III

5. Intel CPU performance

6. Norwegian developers

7. Immediate Send - MS MAPI bug? Workaround?

8. Wanted: Printable C# coding standards document

9. Workaround for SetConsoleCtrlHandler() bug (Q130717)

10. XP DragImage Bug Report & Workaround

11. Visual C++ 2.0 bug, know a simple workaround?

12. Q: Win2000 NDIS.SYS bug & workaround ?

13. Workaround for XP tooltips/WS_EX_COMPOSITED bug