Displaying 1 result from an estimated 1 matches for "r32iregs".
Did you mean:
i32regs
2012 Apr 11
0
[LLVMdev] float16/half float support situation? (and a problem)
...this.
first I just tried to use fp16 data type, without any support in
backend. This was expected to fail.
I got error:
LLVM ERROR: Cannot select: 0x2f566b0: i32 = fp32_to_fp16 0x2f66bb0 [ID=876]
So I created an instruction pattern which matches this fp32_to_fp16
def CFHrf : InstTCE<(outs R32IRegs:$op2), (ins R32FPRegs:$op1), "",
[(set R32IRegs:$op2, (fp32_to_fp16 R32FPRegs:$op1))]>;
But then I got error
/tmp/tcecc-dKBdca/GenInstrInfo.td:30:91: error: Variable not defined:
'fp32_to_fp16'