[FFmpeg-devel] [PATCH] ac3dsp: remove 3dnow version of float_to_fixed24

[Daniel Verkamp]

This implementation is only used in a very narrow set of circumstances:
it is not bitexact, and there is an SSE implementation, so the 3DNow
version would only get used on K6-II/K6-III/early (pre-XP) Athlon CPUs.
It is completely dead code in x86-64 builds.

Signed-off-by: Daniel Verkamp <daniel at drv.nu>
---
 libavcodec/x86/ac3dsp.asm    | 29 -----------------------------
 libavcodec/x86/ac3dsp_init.c |  6 ------
 2 files changed, 35 deletions(-)

diff --git a/libavcodec/x86/ac3dsp.asm b/libavcodec/x86/ac3dsp.asm
index 675ade3..dbb5dab 100644
--- a/libavcodec/x86/ac3dsp.asm
+++ b/libavcodec/x86/ac3dsp.asm
@@ -212,35 +212,6 @@ AC3_SHIFT r, 32, psrad
 ; void ff_float_to_fixed24(int32_t *dst, const float *src, unsigned int len)
 ;-----------------------------------------------------------------------------
 
-; The 3DNow! version is not bit-identical because pf2id uses truncation rather
-; than round-to-nearest.
-INIT_MMX 3dnow
-cglobal float_to_fixed24, 3, 3, 0, dst, src, len
-    movq   m0, [pf_1_24]
-.loop:
-    movq   m1, [srcq   ]
-    movq   m2, [srcq+8 ]
-    movq   m3, [srcq+16]
-    movq   m4, [srcq+24]
-    pfmul  m1, m0
-    pfmul  m2, m0
-    pfmul  m3, m0
-    pfmul  m4, m0
-    pf2id  m1, m1
-    pf2id  m2, m2
-    pf2id  m3, m3
-    pf2id  m4, m4
-    movq  [dstq   ], m1
-    movq  [dstq+8 ], m2
-    movq  [dstq+16], m3
-    movq  [dstq+24], m4
-    add  srcq, 32
-    add  dstq, 32
-    sub  lend, 8
-    ja .loop
-    femms
-    RET
-
 INIT_XMM sse
 cglobal float_to_fixed24, 3, 3, 3, dst, src, len
     movaps     m0, [pf_1_24]
diff --git a/libavcodec/x86/ac3dsp_init.c b/libavcodec/x86/ac3dsp_init.c
index eea2736..f229f34 100644
--- a/libavcodec/x86/ac3dsp_init.c
+++ b/libavcodec/x86/ac3dsp_init.c
@@ -41,7 +41,6 @@ void ff_ac3_lshift_int16_sse2(int16_t *src, unsigned int len, unsigned int shift
 void ff_ac3_rshift_int32_mmx (int32_t *src, unsigned int len, unsigned int shift);
 void ff_ac3_rshift_int32_sse2(int32_t *src, unsigned int len, unsigned int shift);
 
-void ff_float_to_fixed24_3dnow(int32_t *dst, const float *src, unsigned int len);
 void ff_float_to_fixed24_sse  (int32_t *dst, const float *src, unsigned int len);
 void ff_float_to_fixed24_sse2 (int32_t *dst, const float *src, unsigned int len);
 
@@ -206,11 +205,6 @@ av_cold void ff_ac3dsp_init_x86(AC3DSPContext *c, int bit_exact)
         c->ac3_lshift_int16 = ff_ac3_lshift_int16_mmx;
         c->ac3_rshift_int32 = ff_ac3_rshift_int32_mmx;
     }
-    if (EXTERNAL_AMD3DNOW(cpu_flags)) {
-        if (!bit_exact) {
-            c->float_to_fixed24 = ff_float_to_fixed24_3dnow;
-        }
-    }
     if (EXTERNAL_MMXEXT(cpu_flags)) {
         c->ac3_exponent_min = ff_ac3_exponent_min_mmxext;
         c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_mmxext;
-- 
2.4.10