avcodec/x86/vp3dsp: Remove remnants of MMX

Forgotten in eefec06634.

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Reviewed-by: Lynne <dev@lynne.ee>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>

libavcodec/exr.c

@@ -196,9 +196,9 @@ typedef struct EXRContext {
     enum AVColorTransferCharacteristic apply_trc_type;
     float gamma;
     uint16_t gamma_table[65536];
-    Float2HalfTables f2h_tables;
 #endif
 
+    Float2HalfTables f2h_tables;
     Half2FloatTables h2f_tables;
 } EXRContext;
 
@@ -2300,9 +2300,9 @@ static av_cold int decode_init(AVCodecContext *avctx)
     union av_intfloat32 t;
     float one_gamma = 1.0f / s->gamma;
     av_csp_trc_function trc_func = NULL;
-    ff_init_float2half_tables(&s->f2h_tables);
 #endif
 
+    ff_init_float2half_tables(&s->f2h_tables);
     ff_init_half2float_tables(&s->h2f_tables);
 
     s->avctx              = avctx;

libavcodec/x86/hevc/add_res.asm

@@ -27,9 +27,9 @@ cextern pw_1023
 %define max_pixels_10 pw_1023
 
 ; the add_res macros and functions were largely inspired by h264_idct.asm from the x264 project
-%macro ADD_RES_MMX_4_8 0
+%macro ADD_RES_MMX_4_8 1
-    mova              m0, [r1]
+    mova              m0, [r1+%1]
-    mova              m2, [r1+8]
+    mova              m2, [r1+%1+8]
 
     movd              m1, [r0]
     movd              m3, [r0+r2]
@@ -50,31 +50,26 @@ INIT_MMX mmxext
 ; void ff_hevc_add_residual_4_8_mmxext(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
 cglobal hevc_add_residual_4_8, 3, 3, 6
     pxor              m4, m4
-    ADD_RES_MMX_4_8
+    ADD_RES_MMX_4_8    0
-    add               r1, 16
     lea               r0, [r0+r2*2]
-    ADD_RES_MMX_4_8
+    ADD_RES_MMX_4_8   16
     RET
 
-%macro ADD_RES_SSE_8_8 0
+%macro ADD_RES_SSE_8_8 1
     movq              m0, [r0]
     movq              m1, [r0+r2]
     punpcklbw         m0, m4
     punpcklbw         m1, m4
-    mova              m2, [r1]
+    paddsw            m0, [r1+%1]
-    mova              m3, [r1+16]
+    paddsw            m1, [r1+%1+16]
-    paddsw            m0, m2
-    paddsw            m1, m3
     packuswb          m0, m1
 
     movq              m2, [r0+r2*2]
     movq              m3, [r0+r3]
     punpcklbw         m2, m4
     punpcklbw         m3, m4
-    mova              m6, [r1+32]
+    paddsw            m2, [r1+%1+32]
-    mova              m7, [r1+48]
+    paddsw            m3, [r1+%1+48]
-    paddsw            m2, m6
-    paddsw            m3, m7
     packuswb          m2, m3
 
     movq            [r0], m0
@@ -88,27 +83,33 @@ cglobal hevc_add_residual_4_8, 3, 3, 6
     mova              m2, m1
     punpcklbw         m1, m0
     punpckhbw         m2, m0
+%if cpuflag(avx2)
     mova             xm5, [r1+%1]
     mova             xm6, [r1+%1+16]
-%if cpuflag(avx2)
     vinserti128       m5, m5, [r1+%1+32], 1
     vinserti128       m6, m6, [r1+%1+48], 1
-%endif
     paddsw            m1, m5
     paddsw            m2, m6
+%else
+    paddsw            m1, [r1+%1]
+    paddsw            m2, [r1+%1+16]
+%endif
 
     mova              m3, [%3]
     mova              m4, m3
     punpcklbw         m3, m0
     punpckhbw         m4, m0
+%if cpuflag(avx2)
     mova             xm5, [r1+%1+mmsize*2]
     mova             xm6, [r1+%1+mmsize*2+16]
-%if cpuflag(avx2)
     vinserti128       m5, m5, [r1+%1+96], 1
     vinserti128       m6, m6, [r1+%1+112], 1
-%endif
     paddsw            m3, m5
     paddsw            m4, m6
+%else
+    paddsw            m3, [r1+%1+mmsize*2]
+    paddsw            m4, [r1+%1+mmsize*2+16]
+%endif
 
     packuswb          m1, m2
     packuswb          m3, m4
@@ -117,19 +118,18 @@ cglobal hevc_add_residual_4_8, 3, 3, 6
 %endmacro
 
 
-%macro TRANSFORM_ADD_8 0
+INIT_XMM sse2
 ; void ff_hevc_add_residual_8_8_<opt>(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
-cglobal hevc_add_residual_8_8, 3, 4, 8
+cglobal hevc_add_residual_8_8, 3, 4, 5
     pxor              m4, m4
     lea               r3, [r2*3]
-    ADD_RES_SSE_8_8
+    ADD_RES_SSE_8_8    0
-    add               r1, 64
     lea               r0, [r0+r2*4]
-    ADD_RES_SSE_8_8
+    ADD_RES_SSE_8_8   64
     RET
 
 ; void ff_hevc_add_residual_16_8_<opt>(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
-cglobal hevc_add_residual_16_8, 3, 5, 7
+cglobal hevc_add_residual_16_8, 3, 5, 5
     pxor                m0, m0
     lea                 r3, [r2*3]
     mov                r4d, 4
@@ -143,7 +143,7 @@ cglobal hevc_add_residual_16_8, 3, 5, 7
     RET
 
 ; void ff_hevc_add_residual_32_8_<opt>(uint8_t *dst, const int16_t *res, ptrdiff_t stride)
-cglobal hevc_add_residual_32_8, 3, 5, 7
+cglobal hevc_add_residual_32_8, 3, 5, 5
     pxor                m0, m0
     mov                r4d, 16
 .loop:
@@ -154,12 +154,7 @@ cglobal hevc_add_residual_32_8, 3, 5, 7
     dec                r4d
     jg .loop
     RET
-%endmacro
 
-INIT_XMM sse2
-TRANSFORM_ADD_8
-INIT_XMM avx
-TRANSFORM_ADD_8
 
 %if HAVE_AVX2_EXTERNAL
 INIT_YMM avx2
@@ -295,9 +290,8 @@ cglobal hevc_add_residual_4_10, 3, 3, 6
     pxor              m2, m2
     mova              m3, [max_pixels_10]
     ADD_RES_MMX_4_10  r0, r2, r1
-    add               r1, 16
     lea               r0, [r0+2*r2]
-    ADD_RES_MMX_4_10  r0, r2, r1
+    ADD_RES_MMX_4_10  r0, r2, r1+16
     RET
 
 INIT_XMM sse2
@@ -308,8 +302,7 @@ cglobal hevc_add_residual_8_10, 3, 4, 6
 
     ADD_RES_SSE_8_10  r0, r2, r3, r1
     lea               r0, [r0+r2*4]
-    add               r1, 64
+    ADD_RES_SSE_8_10  r0, r2, r3, r1+64
-    ADD_RES_SSE_8_10  r0, r2, r3, r1
     RET
 
 cglobal hevc_add_residual_16_10, 3, 5, 6

libavcodec/x86/hevc/dsp.h

@@ -172,10 +172,6 @@ void ff_hevc_add_residual_8_8_sse2(uint8_t *dst, const int16_t *res, ptrdiff_t s
 void ff_hevc_add_residual_16_8_sse2(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
 void ff_hevc_add_residual_32_8_sse2(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
 
-void ff_hevc_add_residual_8_8_avx(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
-void ff_hevc_add_residual_16_8_avx(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
-void ff_hevc_add_residual_32_8_avx(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
-
 void ff_hevc_add_residual_32_8_avx2(uint8_t *dst, const int16_t *res, ptrdiff_t stride);
 
 void ff_hevc_add_residual_4_10_mmxext(uint8_t *dst, const int16_t *res, ptrdiff_t stride);

libavcodec/x86/hevc/dsp_init.c

@@ -877,10 +877,6 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
 
             c->idct[0] = ff_hevc_idct_4x4_8_avx;
             c->idct[1] = ff_hevc_idct_8x8_8_avx;
-
-            c->add_residual[1] = ff_hevc_add_residual_8_8_avx;
-            c->add_residual[2] = ff_hevc_add_residual_16_8_avx;
-            c->add_residual[3] = ff_hevc_add_residual_32_8_avx;
         }
         if (EXTERNAL_AVX2(cpu_flags)) {
             c->sao_band_filter[0] = ff_hevc_sao_band_filter_8_8_avx2;

libavcodec/x86/vp3dsp.asm

@@ -520,7 +520,6 @@ cglobal put_vp_no_rnd_pixels8_l2, 5, 6, 0, dst, src1, src2, stride, h, stride3
 %endmacro
 
 %macro VP3_IDCT 1
-%if mmsize == 16
 %define I(x) [%1+16*x]
 %define O(x) [%1+16*x]
 %define C(x) [vp3_idct_data+16*(x-1)]
@@ -538,37 +537,6 @@ cglobal put_vp_no_rnd_pixels8_l2, 5, 6, 0, dst, src1, src2, stride, h, stride3
 %define ADD(x)   paddsw x, [pw_8]
         VP3_1D_IDCT_SSE2
         PUT_BLOCK 0, 1, 2, 3, 4, 5, 6, 7
-%else ; mmsize == 8
-    ; eax = quantized input
-    ; ebx = dequantizer matrix
-    ; ecx = IDCT constants
-    ;  M(I) = ecx + MaskOffset(0) + I * 8
-    ;  C(I) = ecx + CosineOffset(32) + (I-1) * 8
-    ; edx = output
-    ; r0..r7 = mm0..mm7
-%define OC_8 [pw_8]
-%define C(x) [vp3_idct_data+16*(x-1)]
-
-    ; at this point, function has completed dequantization + dezigzag +
-    ; partial transposition; now do the idct itself
-%define I(x) [%1+16*x]
-%define J(x) [%1+16*x]
-    RowIDCT
-    Transpose
-
-%define I(x) [%1+16*x+8]
-%define J(x) [%1+16*x+8]
-    RowIDCT
-    Transpose
-
-%define I(x) [%1+16* x]
-%define J(x) [%1+16*(x-4)+8]
-    ColumnIDCT
-
-%define I(x) [%1+16* x   +64]
-%define J(x) [%1+16*(x-4)+72]
-    ColumnIDCT
-%endif ; mmsize == 16/8
 %endmacro
 
 %macro vp3_idct_funcs 0