float xfermodes (burn, dodge, softlight) in Sk8f, possibly using AVX.

src/opts/SkNx_sse.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_sse_DEFINED
 #define SkNx_sse_DEFINED
 
 // This file may assume <= SSE2, but must check SK_CPU_SSE_LEVEL for anything more recent.
 
 namespace {  // See SkNx.h
 
 
 template <>
 class SkNf<2> {
 public:
     SkNf(const __m128& vec) : fVec(vec) {}
 
     SkNf() {}
-    explicit SkNf(float val) : fVec(_mm_set1_ps(val)) {}
+    SkNf(float val) : fVec(_mm_set1_ps(val)) {}
     static SkNf Load(const float vals[2]) {
         return _mm_castsi128_ps(_mm_loadl_epi64((const __m128i*)vals));
     }
     SkNf(float a, float b) : fVec(_mm_setr_ps(a,b,0,0)) {}
 
     void store(float vals[2]) const { _mm_storel_pi((__m64*)vals, fVec); }
 
     SkNf operator + (const SkNf& o) const { return _mm_add_ps(fVec, o.fVec); }
     SkNf operator - (const SkNf& o) const { return _mm_sub_ps(fVec, o.fVec); }
     SkNf operator * (const SkNf& o) const { return _mm_mul_ps(fVec, o.fVec); }
@@ skipping 28 matching lines @@
 
     __m128 fVec;
 };
 
 template <>
 class SkNi<4, int> {
 public:
     SkNi(const __m128i& vec) : fVec(vec) {}
 
     SkNi() {}
-    explicit SkNi(int val) : fVec(_mm_set1_epi32(val)) {}
+    SkNi(int val) : fVec(_mm_set1_epi32(val)) {}
     static SkNi Load(const int vals[4]) { return _mm_loadu_si128((const __m128i*)vals); }
     SkNi(int a, int b, int c, int d) : fVec(_mm_setr_epi32(a,b,c,d)) {}
 
     void store(int vals[4]) const { _mm_storeu_si128((__m128i*)vals, fVec); }
 
     SkNi operator + (const SkNi& o) const { return _mm_add_epi32(fVec, o.fVec); }
     SkNi operator - (const SkNi& o) const { return _mm_sub_epi32(fVec, o.fVec); }
     SkNi operator * (const SkNi& o) const {
         __m128i mul20 = _mm_mul_epu32(fVec, o.fVec),
                 mul31 = _mm_mul_epu32(_mm_srli_si128(fVec, 4), _mm_srli_si128(o.fVec, 4));
@@ skipping 17 matching lines @@
 
     __m128i fVec;
 };
 
 template <>
 class SkNf<4> {
 public:
     SkNf(const __m128& vec) : fVec(vec) {}
 
     SkNf() {}
-    explicit SkNf(float val)           : fVec( _mm_set1_ps(val) ) {}
+    SkNf(float val)           : fVec( _mm_set1_ps(val) ) {}
     static SkNf Load(const float vals[4]) { return _mm_loadu_ps(vals); }
 
     static SkNf FromBytes(const uint8_t bytes[4]) {
         __m128i fix8 = _mm_cvtsi32_si128(*(const int*)bytes);
     #if SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSSE3
         const char _ = ~0;  // Zero these bytes.
         __m128i fix8_32 = _mm_shuffle_epi8(fix8, _mm_setr_epi8(0,_,_,_, 1,_,_,_, 2,_,_,_, 3,_,_,_));
     #else
         __m128i fix8_16 = _mm_unpacklo_epi8 (fix8,    _mm_setzero_si128()),
                 fix8_32 = _mm_unpacklo_epi16(fix8_16, _mm_setzero_si128());
@@ skipping 51 matching lines @@
 
     __m128 fVec;
 };
 
 template <>
 class SkNi<4, uint16_t> {
 public:
     SkNi(const __m128i& vec) : fVec(vec) {}
 
     SkNi() {}
-    explicit SkNi(uint16_t val) : fVec(_mm_set1_epi16(val)) {}
+    SkNi(uint16_t val) : fVec(_mm_set1_epi16(val)) {}
     static SkNi Load(const uint16_t vals[4]) { return _mm_loadl_epi64((const __m128i*)vals); }
     SkNi(uint16_t a, uint16_t b, uint16_t c, uint16_t d) : fVec(_mm_setr_epi16(a,b,c,d,0,0,0,0)) {}
 
     void store(uint16_t vals[4]) const { _mm_storel_epi64((__m128i*)vals, fVec); }
 
     SkNi operator + (const SkNi& o) const { return _mm_add_epi16(fVec, o.fVec); }
     SkNi operator - (const SkNi& o) const { return _mm_sub_epi16(fVec, o.fVec); }
     SkNi operator * (const SkNi& o) const { return _mm_mullo_epi16(fVec, o.fVec); }
 
     SkNi operator << (int bits) const { return _mm_slli_epi16(fVec, bits); }
     SkNi operator >> (int bits) const { return _mm_srli_epi16(fVec, bits); }
 
     template <int k> uint16_t kth() const {
         SkASSERT(0 <= k && k < 4);
         return _mm_extract_epi16(fVec, k);
     }
 
     __m128i fVec;
 };
 
 template <>
 class SkNi<8, uint16_t> {
 public:
     SkNi(const __m128i& vec) : fVec(vec) {}
 
     SkNi() {}
-    explicit SkNi(uint16_t val) : fVec(_mm_set1_epi16(val)) {}
+    SkNi(uint16_t val) : fVec(_mm_set1_epi16(val)) {}
     static SkNi Load(const uint16_t vals[8]) { return _mm_loadu_si128((const __m128i*)vals); }
     SkNi(uint16_t a, uint16_t b, uint16_t c, uint16_t d,
          uint16_t e, uint16_t f, uint16_t g, uint16_t h) : fVec(_mm_setr_epi16(a,b,c,d,e,f,g,h)) {}
 
     void store(uint16_t vals[8]) const { _mm_storeu_si128((__m128i*)vals, fVec); }
 
     SkNi operator + (const SkNi& o) const { return _mm_add_epi16(fVec, o.fVec); }
     SkNi operator - (const SkNi& o) const { return _mm_sub_epi16(fVec, o.fVec); }
     SkNi operator * (const SkNi& o) const { return _mm_mullo_epi16(fVec, o.fVec); }
 
@@ skipping 21 matching lines @@
 
     __m128i fVec;
 };
 
 template <>
 class SkNi<16, uint8_t> {
 public:
     SkNi(const __m128i& vec) : fVec(vec) {}
 
     SkNi() {}
-    explicit SkNi(uint8_t val) : fVec(_mm_set1_epi8(val)) {}
+    SkNi(uint8_t val) : fVec(_mm_set1_epi8(val)) {}
     static SkNi Load(const uint8_t vals[16]) { return _mm_loadu_si128((const __m128i*)vals); }
     SkNi(uint8_t a, uint8_t b, uint8_t c, uint8_t d,
          uint8_t e, uint8_t f, uint8_t g, uint8_t h,
          uint8_t i, uint8_t j, uint8_t k, uint8_t l,
          uint8_t m, uint8_t n, uint8_t o, uint8_t p)
         : fVec(_mm_setr_epi8(a,b,c,d, e,f,g,h, i,j,k,l, m,n,o,p)) {}
 
     void store(uint8_t vals[16]) const { _mm_storeu_si128((__m128i*)vals, fVec); }
 
     SkNi saturatedAdd(const SkNi& o) const { return _mm_adds_epu8(fVec, o.fVec); }
@@ skipping 19 matching lines @@
         return _mm_or_si128(_mm_and_si128   (fVec, t.fVec),
                             _mm_andnot_si128(fVec, e.fVec));
     }
 
     __m128i fVec;
 };
 
 }  // namespace
 
 #endif//SkNx_sse_DEFINED