Don't use a potentially expensive shift if all we want is one set bit.
[oota-llvm.git] / lib / Target / R600 / AMDGPUSubtarget.h
2013-06-07 Tom StellardR600: Rework subtarget info and remove AMDILDevice...
2013-05-17 Vincent LejeuneR600: Factorize Fetch size limit inside AMDGPUSubTarget
2013-04-30 Vincent LejeuneR600: Add FetchInst bit to instruction defs to denote...
2013-01-13 Dmitri GribenkoRemove redundant 'llvm::' qualifications
2012-12-11 Tom StellardAdd R600 backend