ref: 0bc1ecc2548b804d43f41c9c98541e40eb48509f
parent: a7c1ebf6bc2d2b770eed5c2398a73065ecc7ca4d
author: Jonathan Lennox <[email protected]>
date: Tue Aug 4 11:47:55 EDT 2015
Create OPUS_FAST_INT64 macro, to abstract conditions where opus_int64 should be used. This patch adds a macro abstracting the condition under which the silk math macros use opus_int64-based calculations rather than opus_int32. No substantive change, but will make it easier to adjust if additional such platforms are found in the future.
--- a/silk/macros.h
+++ b/silk/macros.h
@@ -43,10 +43,13 @@
#define opus_unlikely(x) (!!(x))
#endif
+/* Set this if opus_int64 is a native type of the CPU. */
+#define OPUS_FAST_INT64 (defined(__x86_64__) || defined(__LP64__) || defined(_WIN64))
+
/* This is an OPUS_INLINE header file for general platform. */
/* (a32 * (opus_int32)((opus_int16)(b32))) >> 16 output have to be 32bit int */
-#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64)
+#if OPUS_FAST_INT64
#define silk_SMULWB(a32, b32) (((a32) * (opus_int64)((opus_int16)(b32))) >> 16)
#else
#define silk_SMULWB(a32, b32) ((((a32) >> 16) * (opus_int32)((opus_int16)(b32))) + ((((a32) & 0x0000FFFF) * (opus_int32)((opus_int16)(b32))) >> 16))
@@ -53,7 +56,7 @@
#endif
/* a32 + (b32 * (opus_int32)((opus_int16)(c32))) >> 16 output have to be 32bit int */
-#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64)
+#if OPUS_FAST_INT64
#define silk_SMLAWB(a32, b32, c32) ((a32) + (((b32) * (opus_int64)((opus_int16)(c32))) >> 16))
#else
#define silk_SMLAWB(a32, b32, c32) ((a32) + ((((b32) >> 16) * (opus_int32)((opus_int16)(c32))) + ((((b32) & 0x0000FFFF) * (opus_int32)((opus_int16)(c32))) >> 16)))
@@ -63,7 +66,7 @@
#define silk_SMULWT(a32, b32) (((a32) >> 16) * ((b32) >> 16) + ((((a32) & 0x0000FFFF) * ((b32) >> 16)) >> 16))
/* a32 + (b32 * (c32 >> 16)) >> 16 */
-#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64)
+#if OPUS_FAST_INT64
#define silk_SMLAWT(a32, b32, c32) ((a32) + (((b32) * ((opus_int64)(c32) >> 16)) >> 16))
#else
#define silk_SMLAWT(a32, b32, c32) ((a32) + (((b32) >> 16) * ((c32) >> 16)) + ((((b32) & 0x0000FFFF) * ((c32) >> 16)) >> 16))
@@ -85,7 +88,7 @@
#define silk_SMLAL(a64, b32, c32) (silk_ADD64((a64), ((opus_int64)(b32) * (opus_int64)(c32))))
/* (a32 * b32) >> 16 */
-#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64)
+#if OPUS_FAST_INT64
#define silk_SMULWW(a32, b32) (((opus_int64)(a32) * (b32)) >> 16)
#else
#define silk_SMULWW(a32, b32) silk_MLA(silk_SMULWB((a32), (b32)), (a32), silk_RSHIFT_ROUND((b32), 16))
@@ -92,7 +95,7 @@
#endif
/* a32 + ((b32 * c32) >> 16) */
-#if defined(__x86_64__) || defined(__LP64__) || defined(_WIN64)
+#if OPUS_FAST_INT64
#define silk_SMLAWW(a32, b32, c32) ((a32) + (((opus_int64)(b32) * (c32)) >> 16))
#else
#define silk_SMLAWW(a32, b32, c32) silk_MLA(silk_SMLAWB((a32), (b32), (c32)), (b32), silk_RSHIFT_ROUND((c32), 16))