Revert of Implement four more xfermodes with Sk4px.

src/opts/SkNx_neon.h

 /*
  * Copyright 2015 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #ifndef SkNx_neon_DEFINED
 #define SkNx_neon_DEFINED
 
@@ skipping 15 matching lines @@
 
 #define SHIFT32(op, v, bits) if (bits < 16) { SHIFT16(op, v, bits); } switch(bits) { \
     case 16: return op(v, 16);  case 17: return op(v, 17);  case 18: return op(v, 18); \
     case 19: return op(v, 19);  case 20: return op(v, 20);  case 21: return op(v, 21); \
     case 22: return op(v, 22);  case 23: return op(v, 23);  case 24: return op(v, 24); \
     case 25: return op(v, 25);  case 26: return op(v, 26);  case 27: return op(v, 27); \
     case 28: return op(v, 28);  case 29: return op(v, 29);  case 30: return op(v, 30); \
     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) {}
 
     SkNf() {}
     explicit SkNf(float val)           : fVec(vdup_n_f32(val)) {}
     static SkNf Load(const float vals[2]) { return vld1_f32(vals); }
     SkNf(float a, float b) { fVec = (float32x2_t) { a, b }; }
 
     void store(float vals[2]) const { vst1_f32(vals, fVec); }
 
@@ skipping 12 matching lines @@
     SkNf operator - (const SkNf& o) const { return vsub_f32(fVec, o.fVec); }
     SkNf operator * (const SkNf& o) const { return vmul_f32(fVec, o.fVec); }
     SkNf operator / (const SkNf& o) const {
     #if defined(SK_CPU_ARM64)
         return vdiv_f32(fVec, o.fVec);
     #else
         return vmul_f32(fVec, o.invert().fVec);
     #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); }
 
     SkNf rsqrt0() const { return vrsqrte_f32(fVec); }
     SkNf rsqrt1() const {
         float32x2_t est0 = this->rsqrt0().fVec;
         return vmul_f32(vrsqrts_f32(fVec, vmul_f32(est0, est0)), est0);
     }
     SkNf rsqrt2() const {
         float32x2_t est1 = this->rsqrt1().fVec;
         return vmul_f32(vrsqrts_f32(fVec, vmul_f32(est1, est1)), est1);
     }
 
     SkNf sqrt() const {
     #if defined(SK_CPU_ARM64)
         return vsqrt_f32(fVec);
     #else
         return *this * this->rsqrt2();
     #endif
     }
 
     template <int k> float kth() const {
         SkASSERT(0 <= k && k < 2);
         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) {}
 
     SkNf() {}
     explicit SkNf(double val)           : fVec(vdupq_n_f64(val))  {}
     static SkNf Load(const double vals[2]) { return vld1q_f64(vals); }
     SkNf(double a, double b) { fVec = (float64x2_t) { a, b }; }
 
     void store(double vals[2]) const { vst1q_f64(vals, fVec); }
 
     SkNf operator + (const SkNf& o) const { return vaddq_f64(fVec, o.fVec); }
     SkNf operator - (const SkNf& o) const { return vsubq_f64(fVec, o.fVec); }
     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); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return vmaxq_f64(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return vsqrtq_f64(fVec);  }
 
     SkNf rsqrt0() const { return vrsqrteq_f64(fVec); }
     SkNf rsqrt1() const {
         float64x2_t est0 = this->rsqrt0().fVec;
@@ skipping 15 matching lines @@
                     est2 = vmulq_f64(vrecpsq_f64(est1, fVec), est1),
                     est3 = vmulq_f64(vrecpsq_f64(est2, fVec), est2);
         return est3;
     }
 
     template <int k> double kth() const {
         SkASSERT(0 <= k && k < 2);
         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)
 
 template <>
 class SkNi<4, int> {
 public:
     SkNi(const int32x4_t& vec) : fVec(vec) {}
 
     SkNi() {}
@@ skipping 13 matching lines @@
     template <int k> int kth() const {
         SkASSERT(0 <= k && k < 4);
         return vgetq_lane_s32(fVec, k&3);
     }
 
     int32x4_t fVec;
 };
 
 template <>
 class SkNf<4, float> {
+    typedef SkNb<4, 4> Nb;
 public:
     SkNf(float32x4_t vec) : fVec(vec) {}
 
     SkNf() {}
     explicit SkNf(float val)           : fVec(vdupq_n_f32(val)) {}
     static SkNf Load(const float vals[4]) { return vld1q_f32(vals); }
     SkNf(float a, float b, float c, float d) { fVec = (float32x4_t) { a, b, c, d }; }
 
     void store(float vals[4]) const { vst1q_f32(vals, fVec); }
 
@@ skipping 14 matching lines @@
     SkNf operator - (const SkNf& o) const { return vsubq_f32(fVec, o.fVec); }
     SkNf operator * (const SkNf& o) const { return vmulq_f32(fVec, o.fVec); }
     SkNf operator / (const SkNf& o) const {
     #if defined(SK_CPU_ARM64)
         return vdivq_f32(fVec, o.fVec);
     #else
         return vmulq_f32(fVec, o.invert().fVec);
     #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); }
 
     SkNf rsqrt0() const { return vrsqrteq_f32(fVec); }
     SkNf rsqrt1() const {
         float32x4_t est0 = this->rsqrt0().fVec;
         return vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est0, est0)), est0);
     }
     SkNf rsqrt2() const {
         float32x4_t est1 = this->rsqrt1().fVec;
         return vmulq_f32(vrsqrtsq_f32(fVec, vmulq_f32(est1, est1)), est1);
     }
 
     SkNf sqrt() const {
     #if defined(SK_CPU_ARM64)
         return vsqrtq_f32(fVec);
     #else
         return *this * this->rsqrt2();
     #endif
     }
 
     template <int k> float kth() const {
         SkASSERT(0 <= k && k < 4);
         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;
 };
 
 template <>
 class SkNi<8, uint16_t> {
 public:
     SkNi(const uint16x8_t& vec) : fVec(vec) {}
 
     SkNi() {}
     explicit SkNi(uint16_t val) : fVec(vdupq_n_u16(val)) {}
@@ skipping 40 matching lines @@
     }
 
     void store(uint8_t vals[16]) const { vst1q_u8(vals, fVec); }
 
     SkNi saturatedAdd(const SkNi& o) const { return vqaddq_u8(fVec, o.fVec); }
 
     SkNi operator + (const SkNi& o) const { return vaddq_u8(fVec, o.fVec); }
     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;
 };
 
 #undef SHIFT32
 #undef SHIFT16
 #undef SHIFT8
 
 }  // namespace
 
 #endif//SkNx_neon_DEFINED