Revert of Implement four more xfermodes with Sk4px.

src/opts/SkNx_neon.h

Index: src/opts/SkNx_neon.h
diff --git a/src/opts/SkNx_neon.h b/src/opts/SkNx_neon.h
index d1760b3d945a9a59c45c50534b01358ef56a641d..da926e0b4c2fafe57bba7b919e5d668e21ea6171 100644
--- a/src/opts/SkNx_neon.h
+++ b/src/opts/SkNx_neon.h
@@ -33,7 +33,34 @@
     case 31: return op(v, 31); } return fVec
 
 template <>
+class SkNb<2, 4> {
+public:
+    SkNb(uint32x2_t vec) : fVec(vec) {}
+
+    SkNb() {}
+    bool allTrue() const { return vget_lane_u32(fVec, 0) && vget_lane_u32(fVec, 1); }
+    bool anyTrue() const { return vget_lane_u32(fVec, 0) || vget_lane_u32(fVec, 1); }
+
+    uint32x2_t fVec;
+};
+
+template <>
+class SkNb<4, 4> {
+public:
+    SkNb(uint32x4_t vec) : fVec(vec) {}
+
+    SkNb() {}
+    bool allTrue() const { return vgetq_lane_u32(fVec, 0) && vgetq_lane_u32(fVec, 1)
+                               && vgetq_lane_u32(fVec, 2) && vgetq_lane_u32(fVec, 3); }
+    bool anyTrue() const { return vgetq_lane_u32(fVec, 0) || vgetq_lane_u32(fVec, 1)
+                               || vgetq_lane_u32(fVec, 2) || vgetq_lane_u32(fVec, 3); }
+
+    uint32x4_t fVec;
+};
+
+template <>
 class SkNf<2, float> {
+    typedef SkNb<2, 4> Nb;
 public:
     SkNf(float32x2_t vec) : fVec(vec) {}
 
@@ -66,14 +93,12 @@
     #endif
     }
 
-    SkNf operator == (const SkNf& o) const { return vreinterpret_f32_u32(vceq_f32(fVec, o.fVec)); }
-    SkNf operator  < (const SkNf& o) const { return vreinterpret_f32_u32(vclt_f32(fVec, o.fVec)); }
-    SkNf operator  > (const SkNf& o) const { return vreinterpret_f32_u32(vcgt_f32(fVec, o.fVec)); }
-    SkNf operator <= (const SkNf& o) const { return vreinterpret_f32_u32(vcle_f32(fVec, o.fVec)); }
-    SkNf operator >= (const SkNf& o) const { return vreinterpret_f32_u32(vcge_f32(fVec, o.fVec)); }
-    SkNf operator != (const SkNf& o) const {
-        return vreinterpret_f32_u32(vmvn_u32(vceq_f32(fVec, o.fVec)));
-    }
+    Nb operator == (const SkNf& o) const { return vceq_f32(fVec, o.fVec); }
+    Nb operator  < (const SkNf& o) const { return vclt_f32(fVec, o.fVec); }
+    Nb operator  > (const SkNf& o) const { return vcgt_f32(fVec, o.fVec); }
+    Nb operator <= (const SkNf& o) const { return vcle_f32(fVec, o.fVec); }
+    Nb operator >= (const SkNf& o) const { return vcge_f32(fVec, o.fVec); }
+    Nb operator != (const SkNf& o) const { return vmvn_u32(vceq_f32(fVec, o.fVec)); }
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return vmin_f32(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmax_f32(l.fVec, r.fVec); }
@@ -101,21 +126,25 @@
         return vget_lane_f32(fVec, k&1);
     }
 
-    bool allTrue() const {
-        auto v = vreinterpret_u32_f32(fVec);
-        return vget_lane_u32(v,0) && vget_lane_u32(v,1);
-    }
-    bool anyTrue() const {
-        auto v = vreinterpret_u32_f32(fVec);
-        return vget_lane_u32(v,0) || vget_lane_u32(v,1);
-    }
-
     float32x2_t fVec;
 };
 
 #if defined(SK_CPU_ARM64)
 template <>
+class SkNb<2, 8> {
+public:
+    SkNb(uint64x2_t vec) : fVec(vec) {}
+
+    SkNb() {}
+    bool allTrue() const { return vgetq_lane_u64(fVec, 0) && vgetq_lane_u64(fVec, 1); }
+    bool anyTrue() const { return vgetq_lane_u64(fVec, 0) || vgetq_lane_u64(fVec, 1); }
+
+    uint64x2_t fVec;
+};
+
+template <>
 class SkNf<2, double> {
+    typedef SkNb<2, 8> Nb;
 public:
     SkNf(float64x2_t vec) : fVec(vec) {}
 
@@ -131,13 +160,13 @@
     SkNf operator * (const SkNf& o) const { return vmulq_f64(fVec, o.fVec); }
     SkNf operator / (const SkNf& o) const { return vdivq_f64(fVec, o.fVec); }
 
-    SkNf operator==(const SkNf& o) const { return vreinterpretq_f64_u64(vceqq_f64(fVec, o.fVec)); }
-    SkNf operator <(const SkNf& o) const { return vreinterpretq_f64_u64(vcltq_f64(fVec, o.fVec)); }
-    SkNf operator >(const SkNf& o) const { return vreinterpretq_f64_u64(vcgtq_f64(fVec, o.fVec)); }
-    SkNf operator<=(const SkNf& o) const { return vreinterpretq_f64_u64(vcleq_f64(fVec, o.fVec)); }
-    SkNf operator>=(const SkNf& o) const { return vreinterpretq_f64_u64(vcgeq_f64(fVec, o.fVec)); }
-    SkNf operator != (const SkNf& o) const {
-        return vreinterpretq_f64_u32(vmvnq_u32(vreinterpretq_u32_u64(vceqq_f64(fVec, o.fVec))));
+    Nb operator == (const SkNf& o) const { return vceqq_f64(fVec, o.fVec); }
+    Nb operator  < (const SkNf& o) const { return vcltq_f64(fVec, o.fVec); }
+    Nb operator  > (const SkNf& o) const { return vcgtq_f64(fVec, o.fVec); }
+    Nb operator <= (const SkNf& o) const { return vcleq_f64(fVec, o.fVec); }
+    Nb operator >= (const SkNf& o) const { return vcgeq_f64(fVec, o.fVec); }
+    Nb operator != (const SkNf& o) const {
+        return vreinterpretq_u64_u32(vmvnq_u32(vreinterpretq_u32_u64(vceqq_f64(fVec, o.fVec))));
     }
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return vminq_f64(l.fVec, r.fVec); }
@@ -173,15 +202,6 @@
         return vgetq_lane_f64(fVec, k&1);
     }
 
-    bool allTrue() const {
-        auto v = vreinterpretq_u64_f64(fVec);
-        return vgetq_lane_u64(v,0) && vgetq_lane_u64(v,1);
-    }
-    bool anyTrue() const {
-        auto v = vreinterpretq_u64_f64(fVec);
-        return vgetq_lane_u64(v,0) || vgetq_lane_u64(v,1);
-    }
-
     float64x2_t fVec;
 };
 #endif//defined(SK_CPU_ARM64)
@@ -215,6 +235,7 @@
 
 template <>
 class SkNf<4, float> {
+    typedef SkNb<4, 4> Nb;
 public:
     SkNf(float32x4_t vec) : fVec(vec) {}
 
@@ -249,14 +270,12 @@
     #endif
     }
 
-    SkNf operator==(const SkNf& o) const { return vreinterpretq_f32_u32(vceqq_f32(fVec, o.fVec)); }
-    SkNf operator <(const SkNf& o) const { return vreinterpretq_f32_u32(vcltq_f32(fVec, o.fVec)); }
-    SkNf operator >(const SkNf& o) const { return vreinterpretq_f32_u32(vcgtq_f32(fVec, o.fVec)); }
-    SkNf operator<=(const SkNf& o) const { return vreinterpretq_f32_u32(vcleq_f32(fVec, o.fVec)); }
-    SkNf operator>=(const SkNf& o) const { return vreinterpretq_f32_u32(vcgeq_f32(fVec, o.fVec)); }
-    SkNf operator!=(const SkNf& o) const {
-        return vreinterpretq_f32_u32(vmvnq_u32(vceqq_f32(fVec, o.fVec)));
-    }
+    Nb operator == (const SkNf& o) const { return vceqq_f32(fVec, o.fVec); }
+    Nb operator  < (const SkNf& o) const { return vcltq_f32(fVec, o.fVec); }
+    Nb operator  > (const SkNf& o) const { return vcgtq_f32(fVec, o.fVec); }
+    Nb operator <= (const SkNf& o) const { return vcleq_f32(fVec, o.fVec); }
+    Nb operator >= (const SkNf& o) const { return vcgeq_f32(fVec, o.fVec); }
+    Nb operator != (const SkNf& o) const { return vmvnq_u32(vceqq_f32(fVec, o.fVec)); }
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return vminq_f32(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmaxq_f32(l.fVec, r.fVec); }
@@ -284,17 +303,6 @@
         return vgetq_lane_f32(fVec, k&3);
     }
 
-    bool allTrue() const {
-        auto v = vreinterpretq_u32_f32(fVec);
-        return vgetq_lane_u32(v,0) && vgetq_lane_u32(v,1)
-            && vgetq_lane_u32(v,2) && vgetq_lane_u32(v,3);
-    }
-    bool anyTrue() const {
-        auto v = vreinterpretq_u32_f32(fVec);
-        return vgetq_lane_u32(v,0) || vgetq_lane_u32(v,1)
-            || vgetq_lane_u32(v,2) || vgetq_lane_u32(v,3);
-    }
-
     float32x4_t fVec;
 };
 
@@ -355,18 +363,12 @@
     SkNi operator - (const SkNi& o) const { return vsubq_u8(fVec, o.fVec); }
 
     static SkNi Min(const SkNi& a, const SkNi& b) { return vminq_u8(a.fVec, b.fVec); }
-    SkNi operator < (const SkNi& o) const { return vcltq_u8(fVec, o.fVec); }
 
     template <int k> uint8_t kth() const {
         SkASSERT(0 <= k && k < 15);
         return vgetq_lane_u8(fVec, k&16);
     }
 
-    SkNi thenElse(const SkNi& t, const SkNi& e) const {
-        return vorrq_u8(vandq_u8(t.fVec, fVec),
-                        vbicq_u8(e.fVec, fVec));
-    }
-
     uint8x16_t fVec;
 };