#COMPILE JAVA FOR POWERPC FULL#
Not enabled or disabled by the -mcpu option at present becauseĪIX does not have full support for these options. On AIX, the -maltivec and -mpowerpc64 options are Value, you may specify it after the -mcpu option, like If you wish to set an individual option to a particular The particular options set for any particular CPU varies betweenĬompiler versions, depending on what setting seems to produce optimalĬode for that CPU it doesn’t necessarily reflect the actual hardware’sĬapabilities. mfloat128-hardware -mprefixed -mpcrel -mmma mquad-memory -mquad-memory-atomic -mfloat128 mcrypto -mhtm -mpower8-fusion -mpower8-vector maltivec -mfprnd -mhard-float -mmfcrf -mmultiple The -mcpu options automatically enable or disable the Those options runs best on that processor, and may not run at all on The other options specify a specific processor. mcpu=native has no effect if GCC does not recognize the Specifying ‘ native’ as cpu type detects and selects theĪrchitecture option that corresponds to the host processor of the mcpu=powerpc64le specify pure 32-bit PowerPC (eitherĮndian), 64-bit big endian PowerPC and 64-bit little endian PowerPCĪrchitecture machine types, with an appropriate, generic processor ‘ power9’, ‘ future’, ‘ powerpc’, ‘ powerpc64’, Supported values for cpu_type are ‘ 401’, ‘ 403’, Instruction scheduling parameters for machine type cpu_type. Set architecture type, register usage, and The -mpowerpc64 option allows GCC to generate the additionalĦ4-bit instructions that are found in the full PowerPC64 architectureĪnd to treat GPRs as 64-bit, doubleword quantities. The -mhard-dfp option allows GCC to generate the decimalįloating-point instructions implemented on some POWER processors. That support the PowerPC V2.05 architecture. Instruction implemented on the POWER6 processor and other processors The -mcmpb option allows GCC to generate the compare bytes Processors that support the PowerPC V2.03 architecture. Integer instructions implemented on the POWER5+ processor and other The -mfprnd option allows GCC to generate the FP round to That support the PowerPC V2.06 architecture. Instruction implemented on the POWER7 processor and other processors The -mpopcntd option allows GCC to generate the popcount POWER5 processor and other processors that support the PowerPC V2.02 The -mpopcntb option allows GCC to generate the popcount andĭouble-precision FP reciprocal estimate instruction implemented on the Processor and other processors that support the PowerPC V2.01 The -mmfcrf option allows GCC to generate the move fromĬondition register field instruction implemented on the POWER4 Use the optional PowerPC architecture instructions in the Graphics General Purpose group, including floating-point square root. GCC to use the optional PowerPC architecture instructions in the We recommend you use the -mcpu= cpu_type option mcpu= cpu_type overrides the specification of these The default value of these options isĭetermined when configuring GCC. You use these options to specify which instructions are available on the mpowerpc-gpopt -mno-powerpc-gpopt -mpowerpc-gfxopt -mno-powerpc-gfxopt -mpowerpc64 -mno-powerpc64 -mmfcrf -mno-mfcrf -mpopcntb -mno-popcntb -mpopcntd -mno-popcntd -mfprnd -mno-fprnd -mcmpb -mno-cmpb -mhard-dfp -mno-hard-dfp These ‘ -m’ options are defined for the IBM RS/6000 and PowerPC: Next: RX Options, Previous: RL78 Options, Up: Submodel Options