NEON: implement several alpha-processing functions

- ApplyAlphaMultiply
 - DispatchAlpha
 - DispatchAlphaToGreen
 - ExtractAlpha

Decoding to Argb / rgbA / ... is 10-15% faster (measured on N4)

new file: alpha_processing_neon.c

Change-Id: I40f1a809e9885d1031ff0bc886d8d001efa66bca
This commit is contained in:
Pascal Massimino
2017-01-11 17:39:29 +01:00
parent 48b1e85fbe
commit 49d0280df1
7 changed files with 190 additions and 0 deletions

View File

@@ -346,6 +346,7 @@ int (*WebPExtractAlpha)(const uint8_t*, int, int, int, uint8_t*, int);
extern void WebPInitAlphaProcessingMIPSdspR2(void);
extern void WebPInitAlphaProcessingSSE2(void);
extern void WebPInitAlphaProcessingSSE41(void);
extern void WebPInitAlphaProcessingNEON(void);
static volatile VP8CPUInfo alpha_processing_last_cpuinfo_used =
(VP8CPUInfo)&alpha_processing_last_cpuinfo_used;
@@ -373,6 +374,11 @@ WEBP_TSAN_IGNORE_FUNCTION void WebPInitAlphaProcessing(void) {
#endif
}
#endif
#if defined(WEBP_USE_NEON)
if (VP8GetCPUInfo(kNEON)) {
WebPInitAlphaProcessingNEON();
}
#endif
#if defined(WEBP_USE_MIPS_DSP_R2)
if (VP8GetCPUInfo(kMIPSdspR2)) {
WebPInitAlphaProcessingMIPSdspR2();