LI78234: HARDWARE DFP NOT ALLOWED WITH -QARCH=PWR8

XL C/C++ for Linux Fix Pack 2 (February 2015 Update) for 13.1
XL C/C++ for Linux Fix Pack 1 (October 2014 Update) for 13.1

APAR status

• Closed as program error.

Error description

• Enabling decimal floating point support via -qdfp on builds
  using -qarch=pwr8 is generating calls to the DFP emulate library
  instead of generating hardware instructions.
  
  Adding the -qfloat=nodfpemulate option to force DFP hardware
  calls results in the following message:
  
  1540-2142 (W) "-qfloat=nodfpemulate" is not compatible with
  "-qarch=pwr8". "-qfloat=dfpemulate" is being set.
  

Local fix

• Compile code using -qarch=pwr7
  

Problem summary

• PROBLEM DESCRIPTION:
  Compiler was not generating hardware decimal floating point
  instructions when -qarch=pwr8 was set.
  
  USERS AFFECTED:
  Users compiling DFP code for use on POWER8 systems.
  

Problem conclusion

• A fix was implemented, and the -qarch=pwr8 option now generates
  hardware DFP instructions.
  

Temporary fix

Comments

APAR Information

• APAR is sysrouted FROM one or more of the following:

  IV61518

• APAR is sysrouted TO one or more of the following:

Fix information

• Fixed component name

  XL C/C++ FOR LI

• Fixed component ID

  5725C7300

Applicable component levels

• RD10 PSN IV61518

     UP06/09/13