aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/misc/echo/echo.c
diff options
context:
space:
mode:
authorAaron Wu <aaron.wu@analog.com>2018-03-15 06:50:11 -0400
committerArnd Bergmann <arnd@arndb.de>2018-03-26 09:56:37 -0400
commitdabad54949930844d237af4b55c14eaff829c888 (patch)
treeb6926e97e750e913bed9851cea058a63d670064d /drivers/misc/echo/echo.c
parent64f5fdd951d5e1558d355aefbe661739eef0c8e4 (diff)
misc: Remove Blackfin DSP echo support
Remove Blackfin DSP echo support Signed-off-by: Aaron Wu <aaron.wu@analog.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Diffstat (limited to 'drivers/misc/echo/echo.c')
-rw-r--r--drivers/misc/echo/echo.c73
1 files changed, 0 insertions, 73 deletions
diff --git a/drivers/misc/echo/echo.c b/drivers/misc/echo/echo.c
index 9597e9523cac..8a5adc0d2e88 100644
--- a/drivers/misc/echo/echo.c
+++ b/drivers/misc/echo/echo.c
@@ -115,78 +115,6 @@
115 115
116/* adapting coeffs using the traditional stochastic descent (N)LMS algorithm */ 116/* adapting coeffs using the traditional stochastic descent (N)LMS algorithm */
117 117
118#ifdef __bfin__
119static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
120{
121 int i;
122 int offset1;
123 int offset2;
124 int factor;
125 int exp;
126 int16_t *phist;
127 int n;
128
129 if (shift > 0)
130 factor = clean << shift;
131 else
132 factor = clean >> -shift;
133
134 /* Update the FIR taps */
135
136 offset2 = ec->curr_pos;
137 offset1 = ec->taps - offset2;
138 phist = &ec->fir_state_bg.history[offset2];
139
140 /* st: and en: help us locate the assembler in echo.s */
141
142 /* asm("st:"); */
143 n = ec->taps;
144 for (i = 0; i < n; i++) {
145 exp = *phist++ * factor;
146 ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15);
147 }
148 /* asm("en:"); */
149
150 /* Note the asm for the inner loop above generated by Blackfin gcc
151 4.1.1 is pretty good (note even parallel instructions used):
152
153 R0 = W [P0++] (X);
154 R0 *= R2;
155 R0 = R0 + R3 (NS) ||
156 R1 = W [P1] (X) ||
157 nop;
158 R0 >>>= 15;
159 R0 = R0 + R1;
160 W [P1++] = R0;
161
162 A block based update algorithm would be much faster but the
163 above can't be improved on much. Every instruction saved in
164 the loop above is 2 MIPs/ch! The for loop above is where the
165 Blackfin spends most of it's time - about 17 MIPs/ch measured
166 with speedtest.c with 256 taps (32ms). Write-back and
167 Write-through cache gave about the same performance.
168 */
169}
170
171/*
172 IDEAS for further optimisation of lms_adapt_bg():
173
174 1/ The rounding is quite costly. Could we keep as 32 bit coeffs
175 then make filter pluck the MS 16-bits of the coeffs when filtering?
176 However this would lower potential optimisation of filter, as I
177 think the dual-MAC architecture requires packed 16 bit coeffs.
178
179 2/ Block based update would be more efficient, as per comments above,
180 could use dual MAC architecture.
181
182 3/ Look for same sample Blackfin LMS code, see if we can get dual-MAC
183 packing.
184
185 4/ Execute the whole e/c in a block of say 20ms rather than sample
186 by sample. Processing a few samples every ms is inefficient.
187*/
188
189#else
190static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift) 118static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
191{ 119{
192 int i; 120 int i;
@@ -215,7 +143,6 @@ static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
215 ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15); 143 ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15);
216 } 144 }
217} 145}
218#endif
219 146
220static inline int top_bit(unsigned int bits) 147static inline int top_bit(unsigned int bits)
221{ 148{