Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM

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 "SkNx.h"
 #include "Test.h"
 
@@ skipping 32 matching lines @@
     assert_eq(a+b, 6, 8, 10, 12);
     assert_eq(a*b, 9, 16, 25, 36);
     assert_eq(a*b-b, 6, 12, 20, 30);
     assert_eq((a*b).sqrt(), 3, 4, 5, 6);
     assert_eq(a/b, 1, 1, 1, 1);
     assert_eq(-a, -3, -4, -5, -6);
 
     SkNf<N,T> fours(4);
 
     assert_eq(fours.sqrt(), 2,2,2,2);
-    assert_nearly_eq(0.001, fours.rsqrt(), 0.5, 0.5, 0.5, 0.5);
+    assert_nearly_eq(0.001, fours.rsqrt0(), 0.5, 0.5, 0.5, 0.5);
+    assert_nearly_eq(0.001, fours.rsqrt1(), 0.5, 0.5, 0.5, 0.5);
+    assert_nearly_eq(0.001, fours.rsqrt2(), 0.5, 0.5, 0.5, 0.5);
 
     assert_eq(              fours.      invert(), 0.25, 0.25, 0.25, 0.25);
     assert_nearly_eq(0.001, fours.approxInvert(), 0.25, 0.25, 0.25, 0.25);
 
     assert_eq(SkNf<N,T>::Min(a, fours), 3, 4, 4, 4);
     assert_eq(SkNf<N,T>::Max(a, fours), 4, 4, 5, 6);
 
     // Test some comparisons.  This is not exhaustive.
     REPORTER_ASSERT(r, (a == b).allTrue());
     REPORTER_ASSERT(r, (a+b == a*b-b).anyTrue());
@@ skipping 57 matching lines @@
 
 DEF_TEST(SkNi, r) {
     test_Ni<2, uint16_t>(r);
     test_Ni<4, uint16_t>(r);
     test_Ni<8, uint16_t>(r);
 
     test_Ni<2, int>(r);
     test_Ni<4, int>(r);
     test_Ni<8, int>(r);
 }