[llvm-dev] Implementing a proposed InstCombine optimization

[Stephen Canon via llvm-dev]

> On Apr 11, 2016, at 12:55 PM, via llvm-dev <llvm-dev at lists.llvm.org> wrote:
> 
> 
>> On Apr 11, 2016, at 4:23 AM, Daniel Sanders <Daniel.Sanders at imgtec.com <mailto:Daniel.Sanders at imgtec.com>> wrote:
>> 
>> > I am not entirely sure this is safe. Transforming this to an fsub could change the value stored on platforms that implement negates using arithmetic instead of with bitmath (such as ours)
>>  
>> I think it's probably safe for IEEE754-2008 conformant platforms because negation was clarified to be a non-arithmetic bit flip that cannot cause exceptions in that specification.
> 
> 
> I did some digging into IEEE-754 and it seems like this is actually not even safe on fully conformant IEEE-754-2008 platforms.
> 
> 5.5.1 Sign bit operations
> 5.5.1.0 Implementations shall provide the following homogeneous quiet-computational sign bit operations for all supported arithmetic formats; they only affect the sign bit. The operations treat floating-point numbers and NaNs alike, and signal no exception. These operations may propagate non-canonical encodings.
> 
> copy(x) copies a floating-point operand x to a destination in the same format, with no change to the sign bit. 
> negate(x) copies a floating-point operand x to a destination in the same format, reversing the sign bit. negate(x) is not the same as subtraction(0, x) (see 6.3).
> 
> Note the MAY. fneg is required to flip the top bit even if the input is a NaN. But fneg is not required to maintain the other bits. If the input is a non-canonical NaN, the fneg MAY canonicalize it. In fact, even the ‘copy’ MAY canonicalize it. (it also MAY choose to not canonicalize it)
> 
> Thus, if the integer being fneg’d is a non-canonical NaN, fneg MAY modify bits other than the top bit.
> 
> —eschar

[The language frontend plus runtime plus] LLVM is the "implementation”.  LLVM can define fneg to be a pure signbit operation if we choose to do so.

Also, there are no non-canonical encodings in binary16, binary32, or binary64, which I believe are what is under discussion on that thread.

– Steve
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160411/55390240/attachment.html>