Optimized premultiplying swizzles for NEON

Improves decode performance for RGBA encoded PNGs.

Swizzle Time on Nexus 9 (with clang):
SwapPremul 0.44x
Premul     0.44x
Decode Time On Nexus 9 (with clang):
ZeroInit Decodes 0.85x
Regular  Decodes 0.86x

Swizzle Time on Nexus 6P (with clang)
SwapPremul 0.14x
Premul     0.14x
Decode Time On Nexus 6P (with clang):
ZeroInit Decodes 0.93x
Regular  Decodes 0.95x

Notes:
ZeroInit means memory is zero initialized, and we do not write to
memory for large sections of zero pixels (memory use opt for Android).

A profile on Nexus 9 shows that the premultiplication step of PNG
decoding is now ~5% of decode time (down from ~20%).

BUG=skia:4767
GOLD_TRYBOT_URL= https://gold.skia.org/search2?unt=true&query=source_type%3Dgm&master=false&issue=1577703006
CQ_EXTRA_TRYBOTS=client.skia:Test-Ubuntu-GCC-GCE-CPU-AVX2-x86_64-Release-SKNX_NO_SIMD-Trybot

Review URL: https://codereview.chromium.org/1577703006

1 files changed, 1 insertions, 52 deletions

diff --git a/src/core/SkOpts.cpp b/src/core/SkOpts.cpp
index ee88b23169..5f1a36c1be 100644
--- a/src/core/SkOpts.cpp
+++ b/src/core/SkOpts.cpp
@@ -16,6 +16,7 @@
 #include "SkFloatingPoint_opts.h"
 #include "SkMatrix_opts.h"
 #include "SkMorphologyImageFilter_opts.h"
+#include "SkSwizzler_opts.h"
 #include "SkTextureCompressor_opts.h"
 #include "SkUtils_opts.h"
 #include "SkXfermode_opts.h"
@@ -49,58 +50,6 @@
     #include <cpu-features.h>
 #endif
 
-namespace sk_default {
-
-// These variable names in these functions just pretend the input is BGRA.
-// They work fine with both RGBA and BGRA.
-
-static void premul_xxxa(uint32_t dst[], const uint32_t src[], int count) {
-    for (int i = 0; i < count; i++) {
-        uint8_t a = src[i] >> 24,
-                r = src[i] >> 16,
-                g = src[i] >>  8,
-                b = src[i] >>  0;
-        r = (r*a+127)/255;
-        g = (g*a+127)/255;
-        b = (b*a+127)/255;
-        dst[i] = (uint32_t)a << 24
-               | (uint32_t)r << 16
-               | (uint32_t)g <<  8
-               | (uint32_t)b <<  0;
-    }
-}
-
-static void swaprb_xxxa(uint32_t dst[], const uint32_t src[], int count) {
-    for (int i = 0; i < count; i++) {
-        uint8_t a = src[i] >> 24,
-                r = src[i] >> 16,
-                g = src[i] >>  8,
-                b = src[i] >>  0;
-        dst[i] = (uint32_t)a << 24
-               | (uint32_t)b << 16
-               | (uint32_t)g <<  8
-               | (uint32_t)r <<  0;
-    }
-}
-
-static void premul_swaprb_xxxa(uint32_t dst[], const uint32_t src[], int count) {
-    for (int i = 0; i < count; i++) {
-        uint8_t a = src[i] >> 24,
-                r = src[i] >> 16,
-                g = src[i] >>  8,
-                b = src[i] >>  0;
-        r = (r*a+127)/255;
-        g = (g*a+127)/255;
-        b = (b*a+127)/255;
-        dst[i] = (uint32_t)a << 24
-               | (uint32_t)b << 16
-               | (uint32_t)g <<  8
-               | (uint32_t)r <<  0;
-    }
-}
-
-}  // namespace sk_default
-
 namespace SkOpts {
     // Define default function pointer values here...
     // If our global compile options are set high enough, these defaults might even be