minor-optimization.patch

diff --git a/src/liblzma/rangecoder/range_encoder.h b/src/liblzma/rangecoder/range_encoder.h
index d794eab..aa52424 100644
--- a/src/liblzma/rangecoder/range_encoder.h
+++ b/src/liblzma/rangecoder/range_encoder.h
@@ -128,6 +128,7 @@ rc_direct(lzma_range_encoder *rc,
 static inline void
 rc_flush(lzma_range_encoder *rc)
 {
+	_Pragma("GCC unroll 5")
 	for (size_t i = 0; i < 5; ++i)
 		rc->symbols[rc->count++] = RC_FLUSH;
 }
@@ -140,7 +141,7 @@ rc_shift_low(lzma_range_encoder *rc,
 	if ((uint32_t)(rc->low) < (uint32_t)(0xFF000000)
 			|| (uint32_t)(rc->low >> 32) != 0) {
 		do {
-			if (*out_pos == out_size)
+			if (__builtin_expect((*out_pos == out_size), 0))
 				return true;
 
 			out[*out_pos] = rc->cache + (uint8_t)(rc->low >> 32);
@@ -187,7 +188,6 @@ rc_shift_low_dummy(uint64_t *low, uint64_t *cache_size, uint8_t *cache,
 	return false;
 }
 
-
 static inline bool
 rc_encode(lzma_range_encoder *rc,
 		uint8_t *out, size_t *out_pos, size_t out_size)
@@ -279,7 +279,7 @@ rc_encode_dummy(const lzma_range_encoder *rc, uint64_t out_limit)
 
 	while (true) {
 		// Normalize
-		if (range < RC_TOP_VALUE) {
+		if (__builtin_expect((range < RC_TOP_VALUE), 0)) {
 			if (rc_shift_low_dummy(&low, &cache_size, &cache,
 					&out_pos, out_limit))
 				return true;
@@ -331,6 +331,7 @@ rc_encode_dummy(const lzma_range_encoder *rc, uint64_t out_limit)
 	// Flush the last bytes. This isn't in rc->symbols[] so we do
 	// it after the above loop to take into account the size of
 	// the flushing that will be done at the end of the stream.
+	_Pragma("GCC unroll 5")
 	for (pos = 0; pos < 5; ++pos) {
 		if (rc_shift_low_dummy(&low, &cache_size,
 				&cache, &out_pos, out_limit))