Expand _01 half<->float limitation to _finite. Simplify.

tests/SkNxTest.cpp

Index: tests/SkNxTest.cpp
diff --git a/tests/SkNxTest.cpp b/tests/SkNxTest.cpp
index 5509814c07ee1b6ff27037ef6cd65a12a2fb44ee..51d937dd4dc29b25da65630981cc3417f43ad2eb 100644
--- a/tests/SkNxTest.cpp
+++ b/tests/SkNxTest.cpp
@@ -288,3 +288,22 @@ DEF_TEST(SkNx_u16_float, r) {
         REPORTER_ASSERT(r, !memcmp(s16, d16, sizeof(s16)));
     }
 }
+
+// The SSE2 implementation of SkNx_cast<uint16_t>(Sk4i) is non-trivial, so worth a test.
+DEF_TEST(SkNx_int_u16, r) {
+    // These are pretty hard to get wrong.
+    for (int i = 0; i <= 0x7fff; i++) {
+        uint16_t expected = (uint16_t)i;
+        uint16_t actual = SkNx_cast<uint16_t>(Sk4i(i))[0];
+
+        REPORTER_ASSERT(r, expected == actual);
+    }
+
+    // A naive implementation with _mm_packs_epi32 would succeed up to 0x7fff but fail here:
+    for (int i = 0x8000; (1) && i <= 0xffff; i++) {
+        uint16_t expected = (uint16_t)i;
+        uint16_t actual = SkNx_cast<uint16_t>(Sk4i(i))[0];
+
+        REPORTER_ASSERT(r, expected == actual);
+    }
+}