Update with table-less version.

Author: cnlohr

README.md

@@ -38,6 +38,8 @@ Also, the code is very small, about 768 bytes each for reading and writing when
 .text	0016 (22 bytes)   vpx_reader_has_error
 ```
 
+If you are on a platform that supports `__builtin_clz`, then you may want to define `VPXCODING_NOTABLE` as that will replace the table call with a `clz` and `andi` operation, which may be faster, and use less cache/RAM.  If you are on a RAM constrained system, you may want to do this as well, but see the note in the header file about the manually unwound log2.
+
 In my tests, depending on the application, this seems to be able to save between 1-5% over huffman trees.  But, notably, there are situations where you can use this to much greater effect and simplicity than huffman trees (but not all situations).
 
 ## Example

bittester.c

@@ -4,6 +4,7 @@
 
 #define VPXCODING_READER
 #define VPXCODING_WRITER
+#define VPXCODING_NOTABLE
 #include "vpxcoding.h"
 
 double GetAbsoluteTime()
@@ -14,9 +15,21 @@ double GetAbsoluteTime()
 }
 
 uint8_t dummydata[1024*1024*16];
+uint8_t dummyprobs[1024*1024*16*8];
 int main( int argc, char ** argv )
 {
 	int i;
+#if 0
+	for( i = 0; i < 256; i++ )
+	{
+		printf( "%2d", VPXCODING_VPXNORM( i ) );
+		if( ( i & 15 ) == 15 )
+		{
+			printf( "\n" );
+		}
+	}
+	return 0;
+#endif
 	for( i = 0; i < sizeof(dummydata); i++ )
 	{
 		//dummydata[i] = rand();
@@ -27,18 +40,18 @@ int main( int argc, char ** argv )
 	uint8_t * bufferO = malloc(sizeof(dummydata)*20);
 	vpx_start_encode( &w, bufferO, sizeof(dummydata)*20);
 
-	const int arbitrary_prob = 187;
-
 	double startEnc = GetAbsoluteTime();
+	int bitno = 0;
 	for( i = 0; i < sizeof(dummydata); i++ )
 	{
 		int data = dummydata[i];
 		int bits = 8;
 		int bit;
 		for (bit = bits - 1; bit >= 0; bit--)
 		{
+			int prob = dummyprobs[bitno++] = rand()&0xff;
 			int outbit = (data >> bit) & 1;
-			vpx_write(&w, outbit, arbitrary_prob);
+			vpx_write(&w, outbit, prob);
 		}
 	}
 	vpx_stop_encode(&w);
@@ -56,13 +69,14 @@ int main( int argc, char ** argv )
 	vpx_reader reader;
 	int ret = vpx_reader_init(&reader, bufferO, w.pos, 0, 0 );
 	double startDec = GetAbsoluteTime();
+	bitno = 0;
 	for( i = 0; i < sizeof(dummydata); i++ )
 	{
 		int bits = 8;
 		int bit;
 		uint8_t data = 0;
 		for (bit = bits - 1; bit >= 0; bit--)// Arbitrary, for testing
-			data = (data<<1) | vpx_read(&reader, arbitrary_prob);
+			data = (data<<1) | vpx_read(&reader, dummyprobs[bitno++]);
 		if( data != dummydata[i] )
 		{
 			fprintf( stderr, "Disagree at %d (%08x != %08x)\n", i, data, dummydata[i] );

vpxcoding.h

@@ -44,7 +44,23 @@ extern "C" {
 #define VPXCODING_IMPLEMENTATION
 #endif
 
-
+#ifdef VPXCODING_NOTABLE
+VPXCODING_DECORATOR uint8_t vpx_norm( uint8_t n )
+{
+	return __builtin_clz(n) & 7;
+#if 0
+	// Implementation for systems w/o clz.
+	if( n == 0 ) return 0; // I don't think this is needed
+	int i = 7;
+	if( n >= 16 ) { i -= 4; n >>= 4; }
+	if( n >= 8 ) { i -= 3; n >>= 3; }
+	if( n >= 4 ) { i -= 2; n >>= 2; }
+	if( n >= 2 ) { i -= 1; n >>= 1; }
+	return i;
+#endif
+}
+#define VPXCODING_VPXNORM(x) vpx_norm(x)
+#else
 static const uint8_t vpx_norm[256] = {
 	0, 7, 6, 6, 5, 5, 5, 5, 4, 4, 4, 4, 4, 4, 4, 4,
 	3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
@@ -64,6 +80,8 @@ static const uint8_t vpx_norm[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
 };
 
+#define VPXCODING_VPXNORM( x ) vpx_norm[x]
+#endif
 #ifdef VPXCODING_READER
 
 // This is meant to be a large, positive constant that can still be
@@ -262,7 +280,7 @@ VPXCODING_DECORATOR int vpx_read(vpx_reader *r, int prob) {
 	}
 
 	{
-		const unsigned char shift = vpx_norm[(unsigned char)range];
+		const unsigned char shift = VPXCODING_VPXNORM((unsigned char)range);
 		range <<= shift;
 		value <<= shift;
 		count -= shift;
@@ -367,7 +385,7 @@ VPXCODING_DECORATOR VPX_NO_UNSIGNED_SHIFT_CHECK void vpx_write(vpx_writer *br,
 		range = br->range - split;
 	}
 
-	shift = vpx_norm[range];
+	shift = VPXCODING_VPXNORM(range);
 
 	range <<= shift;
 	count += shift;