Merge branch 'WIP.x86/asm' into x86/urgent, because the topic is ready

Signed-off-by: Ingo Molnar <mingo@kernel.org>

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 @@
 
 /* adapting coeffs using the traditional stochastic descent (N)LMS algorithm */
 
-#ifdef __bfin__
-static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
-{
-	int i;
-	int offset1;
-	int offset2;
-	int factor;
-	int exp;
-	int16_t *phist;
-	int n;
-
-	if (shift > 0)
-		factor = clean << shift;
-	else
-		factor = clean >> -shift;
-
-	/* Update the FIR taps */
-
-	offset2 = ec->curr_pos;
-	offset1 = ec->taps - offset2;
-	phist = &ec->fir_state_bg.history[offset2];
-
-	/* st: and en: help us locate the assembler in echo.s */
-
-	/* asm("st:"); */
-	n = ec->taps;
-	for (i = 0; i < n; i++) {
-		exp = *phist++ * factor;
-		ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15);
-	}
-	/* asm("en:"); */
-
-	/* Note the asm for the inner loop above generated by Blackfin gcc
-	   4.1.1 is pretty good (note even parallel instructions used):
-
-	   R0 = W [P0++] (X);
-	   R0 *= R2;
-	   R0 = R0 + R3 (NS) ||
-	   R1 = W [P1] (X) ||
-	   nop;
-	   R0 >>>= 15;
-	   R0 = R0 + R1;
-	   W [P1++] = R0;
-
-	   A block based update algorithm would be much faster but the
-	   above can't be improved on much.  Every instruction saved in
-	   the loop above is 2 MIPs/ch!  The for loop above is where the
-	   Blackfin spends most of it's time - about 17 MIPs/ch measured
-	   with speedtest.c with 256 taps (32ms).  Write-back and
-	   Write-through cache gave about the same performance.
-	 */
-}
-
-/*
-   IDEAS for further optimisation of lms_adapt_bg():
-
-   1/ The rounding is quite costly.  Could we keep as 32 bit coeffs
-   then make filter pluck the MS 16-bits of the coeffs when filtering?
-   However this would lower potential optimisation of filter, as I
-   think the dual-MAC architecture requires packed 16 bit coeffs.
-
-   2/ Block based update would be more efficient, as per comments above,
-   could use dual MAC architecture.
-
-   3/ Look for same sample Blackfin LMS code, see if we can get dual-MAC
-   packing.
-
-   4/ Execute the whole e/c in a block of say 20ms rather than sample
-   by sample.  Processing a few samples every ms is inefficient.
-*/
-
-#else
 static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
 {
 	int i;
@@ -215,7 +143,6 @@ static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift)
 		ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15);
 	}
 }
-#endif
 
 static inline int top_bit(unsigned int bits)
 {