[FFmpeg-cvslog] x86/flacdsp: add a SSE2 version of wasted32

[James Almer]

ffmpeg | branch: master | James Almer <jamrial at gmail.com> | Sun May 12 11:53:44 2024 -0300| [0664cbd732fd9d95037d9110b64fb2a32360de2c] | committer: James Almer

x86/flacdsp: add a SSE2 version of wasted32

flac_wasted_32_c: 851.3
flac_wasted_32_sse2: 41.3

Signed-off-by: James Almer <jamrial at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=0664cbd732fd9d95037d9110b64fb2a32360de2c
---

 libavcodec/x86/flacdsp.asm    | 24 ++++++++++++++++++++++++
 libavcodec/x86/flacdsp_init.c |  3 +++
 2 files changed, 27 insertions(+)

diff --git a/libavcodec/x86/flacdsp.asm b/libavcodec/x86/flacdsp.asm
index f38eb7db76..21b2439bc0 100644
--- a/libavcodec/x86/flacdsp.asm
+++ b/libavcodec/x86/flacdsp.asm
@@ -89,6 +89,30 @@ LPC_32 sse4, 32, psrlq
 LPC_32 xop,  32, psrlq
 %endif
 
+INIT_XMM sse2
+cglobal flac_wasted_32, 3,3,5, decoded, wasted, len
+    shl   lend, 2
+    add   decodedq, lenq
+    neg   lenq
+    movd  m4, wastedd
+ALIGN 16
+.loop:
+    mova  m0, [decodedq+lenq+mmsize*0]
+    mova  m1, [decodedq+lenq+mmsize*1]
+    mova  m2, [decodedq+lenq+mmsize*2]
+    mova  m3, [decodedq+lenq+mmsize*3]
+    pslld m0, m4
+    pslld m1, m4
+    pslld m2, m4
+    pslld m3, m4
+    mova  [decodedq+lenq+mmsize*0], m0
+    mova  [decodedq+lenq+mmsize*1], m1
+    mova  [decodedq+lenq+mmsize*2], m2
+    mova  [decodedq+lenq+mmsize*3], m3
+    add lenq, mmsize * 4
+    jl .loop
+    RET
+
 ;----------------------------------------------------------------------------------
 ;void ff_flac_decorrelate_[lrm]s_16_sse2(uint8_t **out, int32_t **in, int channels,
 ;                                                   int len, int shift);
diff --git a/libavcodec/x86/flacdsp_init.c b/libavcodec/x86/flacdsp_init.c
index dee4bf88fc..67aa118760 100644
--- a/libavcodec/x86/flacdsp_init.c
+++ b/libavcodec/x86/flacdsp_init.c
@@ -30,6 +30,8 @@ void ff_flac_lpc_32_sse4(int32_t *samples, const int coeffs[32], int order,
 void ff_flac_lpc_32_xop(int32_t *samples, const int coeffs[32], int order,
                         int qlevel, int len);
 
+void ff_flac_wasted_32_sse2(int32_t *decoded, int wasted, int len);
+
 #define DECORRELATE_FUNCS(fmt, opt)                                                      \
 void ff_flac_decorrelate_ls_##fmt##_##opt(uint8_t **out, int32_t **in, int channels,     \
                                           int len, int shift);                           \
@@ -63,6 +65,7 @@ av_cold void ff_flacdsp_init_x86(FLACDSPContext *c, enum AVSampleFormat fmt, int
     int cpu_flags = av_get_cpu_flags();
 
     if (EXTERNAL_SSE2(cpu_flags)) {
+        c->wasted32 = ff_flac_wasted_32_sse2;
         if (fmt == AV_SAMPLE_FMT_S16) {
             c->decorrelate[1] = ff_flac_decorrelate_ls_16_sse2;
             c->decorrelate[2] = ff_flac_decorrelate_rs_16_sse2;