x86/jpeg2000dsp: add ff_ict_float_{fma3,fma4}

[ffmpeg] / libavcodec / x86 / jpeg2000dsp_init.c

diff --git a/libavcodec/x86/jpeg2000dsp_init.c b/libavcodec/x86/jpeg2000dsp_init.c
index baa81383eac20b580dd2cd7a739fe05ccce8875c..7310a1d0e16fff01c3ad5466f0c76342046e6189 100644 (file)
--- a/libavcodec/x86/jpeg2000dsp_init.c
+++ b/libavcodec/x86/jpeg2000dsp_init.c
@@ -26,6 +26,8 @@
 
 void ff_ict_float_sse(void *src0, void *src1, void *src2, int csize);
 void ff_ict_float_avx(void *src0, void *src1, void *src2, int csize);
+void ff_ict_float_fma3(void *src0, void *src1, void *src2, int csize);
+void ff_ict_float_fma4(void *src0, void *src1, void *src2, int csize);
 void ff_rct_int_sse2 (void *src0, void *src1, void *src2, int csize);
 void ff_rct_int_avx2 (void *src0, void *src1, void *src2, int csize);
 
@@ -44,6 +46,14 @@ av_cold void ff_jpeg2000dsp_init_x86(Jpeg2000DSPContext *c)
         c->mct_decode[FF_DWT97] = ff_ict_float_avx;
     }
 
+    if (EXTERNAL_FMA4(cpu_flags)) {
+        c->mct_decode[FF_DWT97] = ff_ict_float_fma4;
+    }
+
+    if (EXTERNAL_FMA3_FAST(cpu_flags)) {
+        c->mct_decode[FF_DWT97] = ff_ict_float_fma3;
+    }
+
     if (EXTERNAL_AVX2_FAST(cpu_flags)) {
         c->mct_decode[FF_DWT53] = ff_rct_int_avx2;
     }