Why is IEEE compliance for CW floating point add/mul set to 0?
Opened this issue · 2 comments
Line 137 in 367774c
Line 157 in 367774c
This causes errors when simulating lassen with CW floats:
StanfordAHA/lassen#178
Setting ieee_compliance to true fixes this issue. Is there any reason why it was set to false in the first place?
ieee_compliance is essentially a switch indicating compliance with subnormal/denormal floating point values. If you are seeing testing errors, that might mean that we are generating subnormal numbers in the tests. If I recall correctly, we were not trying to support these. Ill try to dig up an email discussing this issue.
That being said, CoreIR should probably expose that flag as a parameter to be decided by the user of the library