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

tests/SkNxTest.cpp

 /*
  * Copyright 2015 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include "Sk4px.h"
 #include "SkNx.h"
 #include "SkRandom.h"
@@ skipping 270 matching lines @@
             (uint16_t)rand.nextU16(), (uint16_t)rand.nextU16(),
         };
         auto u4_0 = Sk4h::Load(s16);
         auto f4 = SkNx_cast<float>(u4_0);
         auto u4_1 = SkNx_cast<uint16_t>(f4);
         uint16_t d16[4];
         u4_1.store(d16);
         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);
+    }
+}