================
@@ -17430,30 +17379,36 @@ type.
 
 Semantics:
 """"""""""
-Follows the semantics of minNum in IEEE-754-2008, except that -0.0 < +0.0 for 
the purposes
-of this intrinsic. As for signaling NaNs, per the minNum semantics, if either 
operand is sNaN,
-the result is qNaN. This matches the recommended behavior for the libm
-function ``fmin``, although not all implementations have implemented these 
recommended behaviors.
 
-If either operand is a qNaN, returns the other non-NaN operand. Returns NaN 
only if both operands are
-NaN or if either operand is sNaN. Note that arithmetic on an sNaN doesn't 
consistently produce a qNaN,
-so arithmetic feeding into a minnum can produce inconsistent results. For 
example,
-``minnum(fadd(sNaN, -0.0), 1.0)`` can produce qNaN or 1.0 depending on whether 
``fadd`` is folded.
+If both operands are qNaNs, returns a :ref:`NaN <floatnan>`. If one operand is
+qNaN and another operand is a number, returns the number. If both operands are
+numbers, returns the lesser of the two arguments. -0.0 is considered to be less
+than +0.0 for this intrinsic.
+
+If an operand is a signaling NaN, then the intrinsic will non-deterministically
+either:
 
-IEEE-754-2008 defines minNum, and it was removed in IEEE-754-2019. As the 
replacement, IEEE-754-2019
-defines :ref:`minimumNumber <i_minimumnum>`.
+ * Return a :ref:`NaN <floatnan>`.
+ * Or treat the signaling NaN as a quiet NaN.
 
-If the intrinsic is marked with the nsz attribute, then the effect is as in 
the definition in C
-and IEEE-754-2008: the result of ``minnum(-0.0, +0.0)`` may be either -0.0 or 
+0.0.
+If the ``nsz`` flag is specified, ``llvm.minnum`` with one +0.0 and one
+-0.0 operand may non-deterministically return either operand. Contrary to 
normal
+``nsz`` semantics, if both operands have the same sign, the result must also
+have the same sign.
 
-Some architectures, such as ARMv8 (FMINNM), LoongArch (fmin), MIPSr6 
(min.fmt), PowerPC/VSX (xsmindp),
-have instructions that match these semantics exactly; thus it is quite simple 
for these architectures.
-Some architectures have similar ones while they are not exact equivalent. Such 
as x86 implements ``MINPS``,
-which implements the semantics of C code ``a<b?a:b``: NUM vs qNaN always 
return qNaN. ``MINPS`` can be used
-if ``nsz`` and ``nnan`` are given.
+When used with the ``nsz`` flag, this intrinsic follows the semantics of
+``fmin`` in C and ``minNum`` in IEEE 754-2008, except for signaling NaN inputs,
+which follow :ref:`LLVM's usual signaling NaN behavior <floatnan>` instead.
 
-For existing libc implementations, the behaviors of fmin may be quite 
different on sNaN and signed zero behaviors,
-even in the same release of a single libm implementation.
+The ``llvm.minnum`` intrinsic can be refined into ``llvm.minimumnum``, as the
+latter exhibits a subset of behaviors of the former.
+
+.. warning::
+
+  If the intrinsic is used without nsz, not all backends currently respect the
+  specified signed zero ordering. Do not rely on it until this warning has
+  been removed. See `issue #174730
+  <https://github.com/llvm/llvm-project/issues/174730>`_.
----------------
arsenm wrote:

No, this is the worst possible world and leaves us back where we started. Every 
intrinsic needs to have a fixed definition, without target flexibility. 
Otherwise it's useless to any analysis or transformation that might as well be 
a black box 

https://github.com/llvm/llvm-project/pull/172012
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to