ARM64 NEON SIMD impl. of prog. Huffman encoding

This commit adds ARM64 NEON optimizations for the
encode_mcu_AC_first() and encode_mcu_AC_refine() functions used in
progressive Huffman encoding.

Compression speedups for the typical set of five libjpeg-turbo test
images (https://libjpeg-turbo.org/About/Performance):
Cortex-A53: 23.8-39.2% (avg. 32.2%)
Cortex-A72: 26.8-41.1% (avg. 33.5%)
Apple A7:  29.7-45.9% (avg. 39.6%)

Closes #229

Author: mayeut

ChangeLog.md

@@ -92,6 +92,11 @@ segfault or other user-visible errant behavior, and given that the lossless
 transformer (unlike the decompressor) is not generally exposed to arbitrary
 data exploits, this issue did not likely pose a security risk.
 
+12. Added SIMD acceleration for progressive Huffman encoding on ARM 64-bit
+(ARMv8) platforms.  This speeds up the compression of full-color progressive
+JPEGs by about 30-40% on average (relative to libjpeg-turbo 2.0.x) when using
+modern ARMv8 CPUs.
+
 
 2.0.3
 =====

simd/arm64/jsimd.c

@@ -22,6 +22,7 @@
 #include "../../jdct.h"
 #include "../../jsimddct.h"
 #include "../jsimd.h"
+#include "jconfigint.h"
 
 #include <stdio.h>
 #include <string.h>
@@ -773,6 +774,18 @@ jsimd_huff_encode_one_block(void *state, JOCTET *buffer, JCOEFPTR block,
 GLOBAL(int)
 jsimd_can_encode_mcu_AC_first_prepare(void)
 {
+  init_simd();
+
+  if (DCTSIZE != 8)
+    return 0;
+  if (sizeof(JCOEF) != 2)
+    return 0;
+  if (SIZEOF_SIZE_T != 8)
+    return 0;
+
+  if (simd_support & JSIMD_NEON)
+    return 1;
+
   return 0;
 }
 
@@ -781,11 +794,25 @@ jsimd_encode_mcu_AC_first_prepare(const JCOEF *block,
                                   const int *jpeg_natural_order_start, int Sl,
                                   int Al, JCOEF *values, size_t *zerobits)
 {
+  jsimd_encode_mcu_AC_first_prepare_neon(block, jpeg_natural_order_start,
+                                         Sl, Al, values, zerobits);
 }
 
 GLOBAL(int)
 jsimd_can_encode_mcu_AC_refine_prepare(void)
 {
+  init_simd();
+
+  if (DCTSIZE != 8)
+    return 0;
+  if (sizeof(JCOEF) != 2)
+    return 0;
+  if (SIZEOF_SIZE_T != 8)
+    return 0;
+
+  if (simd_support & JSIMD_NEON)
+    return 1;
+
   return 0;
 }
 
@@ -794,5 +821,7 @@ jsimd_encode_mcu_AC_refine_prepare(const JCOEF *block,
                                    const int *jpeg_natural_order_start, int Sl,
                                    int Al, JCOEF *absvalues, size_t *bits)
 {
-  return 0;
+  return jsimd_encode_mcu_AC_refine_prepare_neon(block,
+                                                 jpeg_natural_order_start,
+                                                 Sl, Al, absvalues, bits);
 }