[Bluez-devel] SBC optimizations

["Cidorvan Leite" <cidorvan@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 190 bytes --]

Hi!

I replaced the 64bits multiplies by 32bits and fixed the volume, now
the encode and decode are >10% faster.
Unfortunately, I couldn't keep the same volume for decode with 4 subbands...

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: sbc.patch --]
[-- Type: text/x-patch; name=sbc.patch, Size: 4342 bytes --]

Index: sbc.c
===================================================================
RCS file: /cvsroot/bluez/utils/sbc/sbc.c,v
retrieving revision 1.61
diff -u -p -r1.61 sbc.c
--- sbc.c	19 Feb 2008 19:47:25 -0000	1.61
+++ sbc.c	21 Feb 2008 22:08:56 -0000
@@ -551,7 +551,7 @@ static inline void sbc_synthesize_four(s
 				struct sbc_frame *frame, int ch, int blk)
 {
 	int i, j, k, idx;
-	sbc_extended_t res;
+	sbc_fixed_t res;
 
 	for (i = 0; i < 8; i++) {
 		/* Shifting */
@@ -592,7 +592,7 @@ static inline void sbc_synthesize_eight(
 				struct sbc_frame *frame, int ch, int blk)
 {
 	int i, j, k, idx;
-	sbc_extended_t res;
+	sbc_fixed_t res;
 
 	for (i = 0; i < 16; i++) {
 		/* Shifting */
@@ -667,8 +667,7 @@ static void sbc_encoder_init(struct sbc_
 
 static inline void _sbc_analyze_four(const int32_t *in, int32_t *out)
 {
-	sbc_fixed_t t[8];
-	sbc_extended_t s[5];
+	sbc_fixed_t t[8], s[5];
 
 	t[0] = SCALE4_STAGE1( /* Q8 */
 		MULA(_sbc_proto_4[0], in[8] - in[32], /* Q18 */
@@ -752,8 +751,7 @@ static inline void sbc_analyze_four(stru
 
 static inline void _sbc_analyze_eight(const int32_t *in, int32_t *out)
 {
-	sbc_fixed_t t[8];
-	sbc_extended_t s[8];
+	sbc_fixed_t t[8], s[8];
 
 	t[0] = SCALE8_STAGE1( /* Q10 */
 		MULA(_sbc_proto_8[0], (in[16] - in[64]), /* Q18 = Q18 * Q0 */
Index: sbc_math.h
===================================================================
RCS file: /cvsroot/bluez/utils/sbc/sbc_math.h,v
retrieving revision 1.17
diff -u -p -r1.17 sbc_math.h
--- sbc_math.h	15 Feb 2008 18:06:32 -0000	1.17
+++ sbc_math.h	21 Feb 2008 22:08:56 -0000
@@ -28,49 +28,45 @@
    always be correct and every compiler *should* generate optimal code */
 #define ASR(val, bits) ((-2 >> 1 == -1) ? \
 		 ((int32_t)(val)) >> (bits) : ((int32_t) (val)) / (1 << (bits)))
-#define ASR_64(val, bits) ((-2 >> 1 == -1) ? \
-		 ((long long)(val)) >> (bits) : ((long long) (val)) / (1 << (bits)))
 
 #define SCALE_PROTO4_TBL	15
 #define SCALE_ANA4_TBL		16
-#define SCALE_PROTO8_TBL	15
-#define SCALE_ANA8_TBL		16
-#define SCALE_SPROTO4_TBL	16
-#define SCALE_SPROTO8_TBL	16
-#define SCALE_NPROTO4_TBL	10
-#define SCALE_NPROTO8_TBL	12
-#define SCALE_SAMPLES		14
+#define SCALE_PROTO8_TBL	16
+#define SCALE_ANA8_TBL		17
+#define SCALE_SPROTO4_TBL	15
+#define SCALE_SPROTO8_TBL	14
+#define SCALE_NPROTO4_TBL	13
+#define SCALE_NPROTO8_TBL	11
 #define SCALE4_STAGE1_BITS	16
-#define SCALE4_STAGE2_BITS	16
-#define SCALE4_STAGED1_BITS	14
-#define SCALE4_STAGED2_BITS	14
-#define SCALE8_STAGE1_BITS	16
-#define SCALE8_STAGE2_BITS	16
-#define SCALE8_STAGED1_BITS	14
-#define SCALE8_STAGED2_BITS	14
+#define SCALE4_STAGE2_BITS	15
+#define SCALE4_STAGED1_BITS	12
+#define SCALE4_STAGED2_BITS	16
+#define SCALE8_STAGE1_BITS	15
+#define SCALE8_STAGE2_BITS	15
+#define SCALE8_STAGED1_BITS	15
+#define SCALE8_STAGED2_BITS	16
 
 typedef int32_t sbc_fixed_t;
-typedef long long sbc_extended_t;
 
-#define SCALE4_STAGE1(src)  ASR_64(src, SCALE4_STAGE1_BITS)
-#define SCALE4_STAGE2(src)  ASR_64(src, SCALE4_STAGE2_BITS)
-#define SCALE4_STAGED1(src) ASR_64(src, SCALE4_STAGED1_BITS)
-#define SCALE4_STAGED2(src) ASR_64(src, SCALE4_STAGED2_BITS)
-#define SCALE8_STAGE1(src)  ASR_64(src, SCALE8_STAGE1_BITS)
-#define SCALE8_STAGE2(src)  ASR_64(src, SCALE8_STAGE2_BITS)
-#define SCALE8_STAGED1(src) ASR_64(src, SCALE8_STAGED1_BITS)
-#define SCALE8_STAGED2(src) ASR_64(src, SCALE8_STAGED2_BITS)
+#define SCALE4_STAGE1(src)  ASR(src, SCALE4_STAGE1_BITS)
+#define SCALE4_STAGE2(src)  ASR(src, SCALE4_STAGE2_BITS)
+#define SCALE4_STAGED1(src) ASR(src, SCALE4_STAGED1_BITS)
+#define SCALE4_STAGED2(src) ASR(src, SCALE4_STAGED2_BITS)
+#define SCALE8_STAGE1(src)  ASR(src, SCALE8_STAGE1_BITS)
+#define SCALE8_STAGE2(src)  ASR(src, SCALE8_STAGE2_BITS)
+#define SCALE8_STAGED1(src) ASR(src, SCALE8_STAGED1_BITS)
+#define SCALE8_STAGED2(src) ASR(src, SCALE8_STAGED2_BITS)
 
 #define SBC_FIXED_0(val) { val = 0; }
-#define MUL(a, b)        ((sbc_extended_t)(a) * (b))
+#define MUL(a, b)        ((a) * (b))
 #ifdef __arm__
 #define MULA(a, b, res) ({				\
-		long long tmp = res;			\
+		int tmp = res;			\
 		__asm__(				\
-			"smlal %Q0, %R0, %2, %3"	\
+			"mla %0, %2, %3, %0"		\
 			: "=&r" (tmp)			\
 			: "0" (tmp), "r" (a), "r" (b));	\
 		tmp; })
 #else
-#define MULA(a, b, res)  ((sbc_extended_t)(a) * (b) + (res))
+#define MULA(a, b, res)  ((a) * (b) + (res))
 #endif

[-- Attachment #3: Type: text/plain, Size: 228 bytes --]

-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/

[-- Attachment #4: Type: text/plain, Size: 164 bytes --]

_______________________________________________
Bluez-devel mailing list
Bluez-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/bluez-devel