Add is_ascii function optimized for x86-64 for [u8]

The new `is_ascii` function is optimized to use the
`pmovmskb` vector instruction which tests the high bit in a lane.
This corresponds to the same check of whether a byte is ASCII so
ASCII validity checking can be vectorized. This instruction
does not exist on other platforms so it is likely to regress performance
and is gated to all(target_arch = "x86_64", target_feature = "sse2").

Add codegen test
Remove crate::mem import for functions included in the prelude

tests/codegen/slice-is-ascii.rs

@@ -0,0 +1,16 @@
+//@ only-x86_64
+//@ compile-flags: -C opt-level=3
+#![crate_type = "lib"]
+
+/// Check that the fast-path of `is_ascii` uses a `pmovmskb` instruction.
+/// Platforms lacking an equivalent instruction use other techniques for
+/// optimizing `is_ascii`.
+// CHECK-LABEL: @is_ascii_autovectorized
+#[no_mangle]
+pub fn is_ascii_autovectorized(s: &[u8]) -> bool {
+    // CHECK: load <32 x i8>
+    // CHECK-NEXT: icmp slt <32 x i8>
+    // CHECK-NEXT: bitcast <32 x i1>
+    // CHECK-NEXT: icmp eq i32
+    s.is_ascii()
+}