opus - Nov 2015 - [Fast Int64 2/4] Add OPUS_FAST_INT64 flavors of celt/fixed_generic.h macros.

---
 celt/arch.h   | 5 +++++
 silk/macros.h | 4 +---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/celt/arch.h b/celt/arch.h
index 9f74ddd..670527b 100644
--- a/celt/arch.h
+++ b/celt/arch.h
@@ -78,6 +78,11 @@ static OPUS_INLINE void _celt_fatal(const char *str, const
char *file, int line)
 #define UADD32(a,b) ((a)+(b))
 #define USUB32(a,b) ((a)-(b))
 
+/* Set this if opus_int64 is a native type of the CPU. */
+/* Assume that all LP64 architectures have fast 64-bit types; also x86_64
(which can be ILP32 for x32)
+   and Win64 (which is LLP64). */
+#define OPUS_FAST_INT64 (defined(__LP64__) || defined(__x86_64__) ||
defined(_WIN64))
+
 #define PRINT_MIPS(file)
 
 #ifdef FIXED_POINT
diff --git a/silk/macros.h b/silk/macros.h
index bc30303..1ba614a 100644
--- a/silk/macros.h
+++ b/silk/macros.h
@@ -34,6 +34,7 @@ POSSIBILITY OF SUCH DAMAGE.
 
 #include "opus_types.h"
 #include "opus_defines.h"
+#include "arch.h"
 
 #if OPUS_GNUC_PREREQ(3, 0)
 #define opus_likely(x)       (__builtin_expect(!!(x), 1))
@@ -43,9 +44,6 @@ POSSIBILITY OF SUCH DAMAGE.
 #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 */
-- 
2.4.9 (Apple Git-60)

---
 celt/fixed_generic.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/celt/fixed_generic.h b/celt/fixed_generic.h
index ac67d37..1cfd6d6 100644
--- a/celt/fixed_generic.h
+++ b/celt/fixed_generic.h
@@ -37,16 +37,32 @@
 #define MULT16_16SU(a,b)
((opus_val32)(opus_val16)(a)*(opus_val32)(opus_uint16)(b))
 
 /** 16x32 multiplication, followed by a 16-bit shift right. Results fits in 32
bits */
+#if OPUS_FAST_INT64
+#define MULT16_32_Q16(a,b)
((opus_val32)SHR((opus_int64)((opus_val16)(a))*(b),16))
+#else
 #define MULT16_32_Q16(a,b) ADD32(MULT16_16((a),SHR((b),16)),
SHR(MULT16_16SU((a),((b)&0x0000ffff)),16))
+#endif
 
 /** 16x32 multiplication, followed by a 16-bit shift right (round-to-nearest).
Results fits in 32 bits */
+#if OPUS_FAST_INT64
+#define MULT16_32_P16(a,b)
((opus_val32)PSHR((opus_int64)((opus_val16)(a))*(b),16))
+#else
 #define MULT16_32_P16(a,b) ADD32(MULT16_16((a),SHR((b),16)),
PSHR(MULT16_16SU((a),((b)&0x0000ffff)),16))
+#endif
 
 /** 16x32 multiplication, followed by a 15-bit shift right. Results fits in 32
bits */
+#if OPUS_FAST_INT64
+#define MULT16_32_Q15(a,b)
((opus_val32)SHR((opus_int64)((opus_val16)(a))*(b),15))
+#else
 #define MULT16_32_Q15(a,b) ADD32(SHL(MULT16_16((a),SHR((b),16)),1),
SHR(MULT16_16SU((a),((b)&0x0000ffff)),15))
+#endif
 
 /** 32x32 multiplication, followed by a 31-bit shift right. Results fits in 32
bits */
+#if OPUS_FAST_INT64
+#define MULT32_32_Q31(a,b)
((opus_val32)SHR((opus_int64)(a)*(opus_int64)(b),31))
+#else
 #define MULT32_32_Q31(a,b)
ADD32(ADD32(SHL(MULT16_16(SHR((a),16),SHR((b),16)),1),
SHR(MULT16_16SU(SHR((a),16),((b)&0x0000ffff)),15)),
SHR(MULT16_16SU(SHR((b),16),((a)&0x0000ffff)),15))
+#endif
 
 /** Compile-time conversion of float constant to 16-bit value */
 #define QCONST16(x,bits) ((opus_val16)(.5+(x)*(((opus_val32)1)<<(bits))))
-- 
2.4.9 (Apple Git-60)

---
 silk/macros.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/silk/macros.h b/silk/macros.h
index 1ba614a..e1e05b9 100644
--- a/silk/macros.h
+++ b/silk/macros.h
@@ -48,14 +48,14 @@ POSSIBILITY OF SUCH DAMAGE.
 
 /* (a32 * (opus_int32)((opus_int16)(b32))) >> 16 output have to be 32bit
int */
 #if OPUS_FAST_INT64
-#define silk_SMULWB(a32, b32)            (((a32) *
(opus_int64)((opus_int16)(b32))) >> 16)
+#define silk_SMULWB(a32, b32)            ((opus_int32)(((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))
 #endif
 
 /* a32 + (b32 * (opus_int32)((opus_int16)(c32))) >> 16 output have to be
32bit int */
 #if OPUS_FAST_INT64
-#define silk_SMLAWB(a32, b32, c32)       ((a32) + (((b32) *
(opus_int64)((opus_int16)(c32))) >> 16))
+#define silk_SMLAWB(a32, b32, c32)       ((opus_int32)((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)))
 #endif
@@ -65,7 +65,7 @@ POSSIBILITY OF SUCH DAMAGE.
 
 /* a32 + (b32 * (c32 >> 16)) >> 16 */
 #if OPUS_FAST_INT64
-#define silk_SMLAWT(a32, b32, c32)       ((a32) + (((b32) * ((opus_int64)(c32)
>> 16)) >> 16))
+#define silk_SMLAWT(a32, b32, c32)       ((opus_int32)((a32) + (((b32) *
((opus_int64)(c32) >> 16)) >> 16)))
 #else
 #define silk_SMLAWT(a32, b32, c32)       ((a32) + (((b32) >> 16) * ((c32)
>> 16)) + ((((b32) & 0x0000FFFF) * ((c32) >> 16)) >> 16))
 #endif
@@ -87,14 +87,14 @@ POSSIBILITY OF SUCH DAMAGE.
 
 /* (a32 * b32) >> 16 */
 #if OPUS_FAST_INT64
-#define silk_SMULWW(a32, b32)            (((opus_int64)(a32) * (b32)) >>
16)
+#define silk_SMULWW(a32, b32)            ((opus_int32)(((opus_int64)(a32) *
(b32)) >> 16))
 #else
 #define silk_SMULWW(a32, b32)            silk_MLA(silk_SMULWB((a32), (b32)),
(a32), silk_RSHIFT_ROUND((b32), 16))
 #endif
 
 /* a32 + ((b32 * c32) >> 16) */
 #if OPUS_FAST_INT64
-#define silk_SMLAWW(a32, b32, c32)       ((a32) + (((opus_int64)(b32) * (c32))
>> 16))
+#define silk_SMLAWW(a32, b32, c32)       ((opus_int32)((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))
 #endif
-- 
2.4.9 (Apple Git-60)

---
 silk/macros.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/silk/macros.h b/silk/macros.h
index e1e05b9..7cefedc 100644
--- a/silk/macros.h
+++ b/silk/macros.h
@@ -61,7 +61,11 @@ POSSIBILITY OF SUCH DAMAGE.
 #endif
 
 /* (a32 * (b32 >> 16)) >> 16 */
+#if OPUS_FAST_INT64
+#define silk_SMULWT(a32, b32)            ((opus_int32)(((a32) *
(opus_int64)((b32) >> 16)) >> 16))
+#else
 #define silk_SMULWT(a32, b32)            (((a32) >> 16) * ((b32) >>
16) + ((((a32) & 0x0000FFFF) * ((b32) >> 16)) >> 16))
+#endif
 
 /* a32 + (b32 * (c32 >> 16)) >> 16 */
 #if OPUS_FAST_INT64
-- 
2.4.9 (Apple Git-60)