skcpu: sse4.1 floor, f16c f16<->f32

src/core/SkHalf.h

 /*
  * Copyright 2014 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #ifndef SkHalf_DEFINED
 #define SkHalf_DEFINED
 
+#include "SkCpu.h"
 #include "SkNx.h"
 #include "SkTypes.h"
 
 // 16-bit floating point value
 // format is 1 bit sign, 5 bits exponent, 10 bits mantissa
 // only used for storage
 typedef uint16_t SkHalf;
 
 #define SK_HalfMin      0x0400   // 2^-24  (minimum positive normal value)
 #define SK_HalfMax      0x7bff   // 65504
@@ skipping 94 matching lines @@
     }
     r = (uint64_t)hs[3] << 48
       | (uint64_t)hs[2] << 32
       | (uint64_t)hs[1] << 16
       | (uint64_t)hs[0] <<  0;
 #endif
     return r;
 }
 
 #endif
+
+static inline Sk4f SkHalfToFloat_01(const uint64_t* hs) {
+#if !defined(SKNX_NO_SIMD) && SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
+    if (SkCpu::Supports(SkCpu::F16C)) {
+        __m128 fs;
+    #if defined(__GNUC__) || defined(__clang__)
+        asm("vcvtph2ps %[hs], %[fs]" : [fs]"=x"(fs) : [hs]"m"(*hs));
+    #else
+        fs = _mm_cvtph_ps(_mm_loadl_epi64((const __m128i*)hs));
+    #endif
+        return fs;
+    }
+#endif
+    return SkHalfToFloat_01(*hs);
+}
+
+static inline void SkFloatToHalf_01(const Sk4f& fs, uint64_t* hs) {
+#if !defined(SKNX_NO_SIMD) && SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
+    if (SkCpu::Supports(SkCpu::F16C)) {
+    #if defined(__GNUC__) || defined(__clang__)
+        asm("vcvtps2ph $0, %[fs], %[hs]" : [hs]"=m"(*hs) : [fs]"x"(fs.fVec));
+    #else
+        _mm_storel_epi64((__m128i*)hs, _mm_cvtps_ph(fs.fVec, 0));
+    #endif
+        return;
+    }
+#endif
+    *hs = SkFloatToHalf_01(fs);
+}