[LLVMdev] Half Float fp16 Native Support

beat n.stavropoulos at think-silicon.com
Thu Jan 24 07:47:59 PST 2013


you had  right 
 i used opencl patch for clang to generate IR with half and after that 
 declared fp16 legal instructions and some defs and it worked. 
 the with a  load half fp with immediate instruction.
:)


p.s
then i did something  i can not remember and it  stopped :S 




--
View this message in context: http://llvm.1065342.n5.nabble.com/Half-Float-fp16-Native-Support-tp50665p54136.html
Sent from the LLVM - Dev mailing list archive at Nabble.com.



More information about the llvm-dev mailing list