[opus] [Aarch64 v2 12/18] Add OPUS_FAST_INT64 flavors of celt/fixed_generic.h macros.

[Jonathan Lennox]

---
 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)