split span.count into its own PR

Signed-off-by: martinvuyk <[email protected]>

docs/changelog.md

@@ -185,12 +185,6 @@ what we publish.
   ([PR #3160](https://github.com/modularml/mojo/pull/3160) by
    [@bgreni](https://github.com/bgreni))
 
-- `Span` now implements a generic `.count()` method which can be passed a
-  function that returns a boolean SIMD vector. The function counts how many
-  times it returns true evaluating it in a vectorized manner. This works for any
-  `Span[Scalar[D]]` e.g. `Span[Byte]`. PR [#3686](https://github.com/modularml/mojo/pull/3686)
-  by [@martinvuyk](https://github.com/martinvuyk).
-
 - `StringRef` now implements `split()` which can be used to split a
   `StringRef` into a `List[StringRef]` by a delimiter.
   ([PR #2705](https://github.com/modularml/mojo/pull/2705) by [@fknfilewalker](https://github.com/fknfilewalker))

stdlib/src/utils/span.mojo

@@ -358,43 +358,3 @@ struct Span[
         return Span[T, _lit_mut_cast[origin, False].result](
             ptr=self._data, length=self._len
         )
-
-    fn count[
-        D: DType, //, func: fn[w: Int] (SIMD[D, w]) -> SIMD[DType.bool, w]
-    ](self: Span[Scalar[D]]) -> Int:
-        """Count the amount of times the function returns `True`.
-
-        Parameters:
-            D: The DType.
-            func: The function to evaluate.
-
-        Returns:
-            The amount of times the function returns `True`.
-        """
-
-        alias widths = (256, 128, 64, 32, 16, 8)
-        var ptr = self.unsafe_ptr()
-        var num_bytes = len(self)
-        var amnt = 0
-        var processed = 0
-
-        @parameter
-        for i in range(len(widths)):
-            alias w = widths.get[i, Int]()
-
-            @parameter
-            if simdwidthof[D]() >= w:
-                for _ in range((num_bytes - processed) // w):
-                    var vec = (ptr + processed).load[width=w]()
-
-                    @parameter
-                    if w >= 256:
-                        amnt += int(func(vec).cast[DType.uint16]().reduce_add())
-                    else:
-                        amnt += int(func(vec).cast[DType.uint8]().reduce_add())
-                    processed += w
-
-        for i in range(num_bytes - processed):
-            amnt += int(func(ptr[processed + i]))
-
-        return amnt