On penrynn, from 255 to 174c. Unrolling yields no gain.
---
libavcodec/x86/sbrdsp.asm | 21 +++++++++++++++++++++
libavcodec/x86/sbrdsp_init.c | 2 ++
2 files changed, 23 insertions(+), 0 deletions(-)
diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm
index 11a6faf..2b90100 100644
--- a/libavcodec/x86/sbrdsp.asm
+++ b/libavcodec/x86/sbrdsp.asm
@@ -24,6 +24,8 @@
SECTION_RODATA
; mask equivalent for multiply by -1.0 1.0
ps_mask times 2 dd 1<<31, 0
+ps_mask2 times 2 dd 0, 1<<31
+ps_neg times 4 dd 1<<31
SECTION_TEXT
@@ -203,3 +205,22 @@ cglobal sbr_sum64x5, 1,2,4,z
cmp zq, r1q
jne .loop
REP_RET
+
+cglobal sbr_qmf_post_shuffle, 2,3,3,W,z
+ lea r2q, [zq + (64-4)*4]
+.loop:
+ mova m0, [r2q]
+ mova m1, [zq ]
+ xorps m0, [ps_neg]
+ shufps m0, m0, 0x1B
+ mova m2, m0
+ unpcklps m0, m1
+ unpckhps m2, m1
+ mova [Wq + 0], m0
+ mova [Wq + 16], m2
+ add Wq, 32
+ sub r2q, 16
+ add zq, 16
+ cmp zq, r2q
+ jl .loop
+ REP_RET
diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c
index 108a681..3f6dd97 100644
--- a/libavcodec/x86/sbrdsp_init.c
+++ b/libavcodec/x86/sbrdsp_init.c
@@ -31,6 +31,7 @@ void ff_sbr_hf_gen_sse(float (*X_high)[2], const float
(*X_low)[2],
const float alpha0[2], const float alpha1[2],
float bw, int start, int end);
void ff_sbr_sum64x5_sse(float *z);
+void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z);
void ff_sbrdsp_init_x86(SBRDSPContext *s)
{
@@ -41,5 +42,6 @@ void ff_sbrdsp_init_x86(SBRDSPContext *s)
s->hf_g_filt = ff_sbr_hf_g_filt_sse;
s->hf_gen = ff_sbr_hf_gen_sse;
s->sum64x5 = ff_sbr_sum64x5_sse;
+ s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse;
}
}
--
1.7.7.msysgit.0
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel