[libclc] Fix double NAN_MASK in __clc_nan #163522
Conversation
0x7ff0000000000000 is +inf. Change it to quiet nan 0x7ff8000000000000.
There was a problem hiding this comment.
Pull Request Overview
This PR fixes an incorrect NaN mask value for 64-bit floating point numbers in libclc. The value 0x7ff0000000000000 represents positive infinity, not NaN, and is corrected to 0x7ff8000000000000 which represents a quiet NaN.
- Corrects the NAN_MASK constant for 64-bit floating point from positive infinity to quiet NaN
wenju-he
changed the title
…pirv_ocl_nan NAN_MASK fix is cherry-pick of llvm/llvm-project#163522 Also fix a few build warnings `'__CLC_FUNCTION' macro redefined`.
arsenm
left a comment
arsenm
left a comment
There was a problem hiding this comment.
Should really just use __builtin_nan
done in de867d4 |
frasercrmck
left a comment
frasercrmck
left a comment
There was a problem hiding this comment.
LGTM. I looked at this before but wasn't sure about removing the payload. As you point out it still adheres to the spec so I'm fine with it.
|
Oh right I forgot about the weird string format for __builtin_nan. Technically you could try to find a string to map the value to |
|
It's probably better to go back to not using the builtin, failing a way to get the string |
This reverts commit de867d4.
done, reverted to original version |
…rv_ocl_nan (#20366) NAN_MASK fix is cherry-pick of llvm/llvm-project#163522 Also fix a few build warnings `'__CLC_FUNCTION' macro redefined`.
0x7ff0000000000000 is +inf. Change it to quiet nan 0x7ff8000000000000.
0x7ff0000000000000 is +inf. Change it to quiet nan 0x7ff8000000000000.
4 participants
0x7ff0000000000000 is +inf. Change it to quiet nan 0x7ff8000000000000.