[FFmpeg-devel] [PATCH 6/6] avcodec/x86: allow 8-bit simple_idct to use slightly different coefficients

[James Darnley]

This makes it exact to the old MMX one, as reported by libavcodec/tests/dct.
---
 libavcodec/x86/proresdsp.asm              | 18 +++++++++--------
 libavcodec/x86/simple_idct10.asm          | 33 ++++++++++++++++++++++---------
 libavcodec/x86/simple_idct10_template.asm | 19 ++++++++++++++++++
 3 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/libavcodec/x86/proresdsp.asm b/libavcodec/x86/proresdsp.asm
index 3be0ff7757..65c9fad51c 100644
--- a/libavcodec/x86/proresdsp.asm
+++ b/libavcodec/x86/proresdsp.asm
@@ -33,14 +33,14 @@ cextern pw_1
 cextern pw_4
 cextern pw_1019
 ; Below are defined in simple_idct10.asm built from selecting idctdsp
-cextern w4_plus_w2
-cextern w4_min_w2
-cextern w4_plus_w6
-cextern w4_min_w6
-cextern w1_plus_w3
-cextern w3_min_w1
-cextern w7_plus_w3
-cextern w3_min_w7
+cextern w4_plus_w2_hi
+cextern w4_min_w2_hi
+cextern w4_plus_w6_hi
+cextern w4_min_w6_hi
+cextern w1_plus_w3_hi
+cextern w3_min_w1_hi
+cextern w7_plus_w3_hi
+cextern w3_min_w7_hi
 cextern w1_plus_w5
 cextern w5_min_w1
 cextern w5_plus_w7
@@ -50,6 +50,8 @@ cextern w7_min_w5
 
 SECTION .text
 
+define_constants _hi
+
 %macro idct_fn 0
 cglobal prores_idct_put_10, 4, 4, 15, pixels, lsize, block, qmat
     IDCT_FN    pw_1, 15, pw_88, 18, "put", pw_4, pw_1019, r3
diff --git a/libavcodec/x86/simple_idct10.asm b/libavcodec/x86/simple_idct10.asm
index 29e18fe6a6..5ec1e6b23d 100644
--- a/libavcodec/x86/simple_idct10.asm
+++ b/libavcodec/x86/simple_idct10.asm
@@ -48,24 +48,34 @@ times 4 dw %2, %3
 %define W2sh2 21407 ; W2 = 85627 = 21407<<2 - 1
 %define W3sh2 19265 ; W3 = 77062 = 19265<<2 + 2
 %define W4sh2 16384 ; W4 = 65535 = 16384<<2 - 1
+%define W3sh2_lo 19266
+%define W4sh2_lo 16383
 %define W5sh2 12873 ; W5 = 51491 = 12873<<2 - 1
 %define W6sh2  8867 ; W6 = 35468 =  8867<<2
 %define W7sh2  4520 ; W7 = 18081 =  4520<<2 + 1
 
-pw_round_20_div_w4: times 8 dw ((1 << (20 - 1)) / W4sh2)
+pw_round_20_div_w4: times 8 dw ((1 << (20 - 1)) / W4sh2_lo)
 
-CONST_DEC  w4_plus_w2,   W4sh2, +W2sh2
-CONST_DEC  w4_min_w2,    W4sh2, -W2sh2
-CONST_DEC  w4_plus_w6,   W4sh2, +W6sh2
-CONST_DEC  w4_min_w6,    W4sh2, -W6sh2
-CONST_DEC  w1_plus_w3,   W1sh2, +W3sh2
-CONST_DEC  w3_min_w1,    W3sh2, -W1sh2
-CONST_DEC  w7_plus_w3,   W7sh2, +W3sh2
-CONST_DEC  w3_min_w7,    W3sh2, -W7sh2
+CONST_DEC  w4_plus_w2_hi,   W4sh2, +W2sh2
+CONST_DEC  w4_min_w2_hi,    W4sh2, -W2sh2
+CONST_DEC  w4_plus_w6_hi,   W4sh2, +W6sh2
+CONST_DEC  w4_min_w6_hi,    W4sh2, -W6sh2
+CONST_DEC  w1_plus_w3_hi,   W1sh2, +W3sh2
+CONST_DEC  w3_min_w1_hi,    W3sh2, -W1sh2
+CONST_DEC  w7_plus_w3_hi,   W7sh2, +W3sh2
+CONST_DEC  w3_min_w7_hi,    W3sh2, -W7sh2
 CONST_DEC  w1_plus_w5,   W1sh2, +W5sh2
 CONST_DEC  w5_min_w1,    W5sh2, -W1sh2
 CONST_DEC  w5_plus_w7,   W5sh2, +W7sh2
 CONST_DEC  w7_min_w5,    W7sh2, -W5sh2
+CONST_DEC  w4_plus_w2_lo,   W4sh2_lo, +W2sh2
+CONST_DEC  w4_min_w2_lo,    W4sh2_lo, -W2sh2
+CONST_DEC  w4_plus_w6_lo,   W4sh2_lo, +W6sh2
+CONST_DEC  w4_min_w6_lo,    W4sh2_lo, -W6sh2
+CONST_DEC  w1_plus_w3_lo,   W1sh2,    +W3sh2_lo
+CONST_DEC  w3_min_w1_lo,    W3sh2_lo, -W1sh2
+CONST_DEC  w7_plus_w3_lo,   W7sh2,    +W3sh2_lo
+CONST_DEC  w3_min_w7_lo,    W3sh2_lo, -W7sh2
 
 %include "libavcodec/x86/simple_idct10_template.asm"
 
@@ -108,6 +118,9 @@ SECTION .text
     [base], [base + stride], [base + 2*stride], [base + stride3]
 
 %macro idct_fn 0
+
+define_constants _lo
+
 cglobal simple_idct8, 1, 1, 16, block
     IDCT_FN    "", 11, pw_round_20_div_w4, 20, "store"
 RET
@@ -160,6 +173,8 @@ cglobal simple_idct8_add, 3, 4, 16, pixels, lsize, block
     STORE_HI_LO PASS8ROWS(pixelsq, r3, lsizeq, r2), m8, m1, m4, m9
 RET
 
+define_constants _hi
+
 cglobal simple_idct10, 1, 1, 16, block
     IDCT_FN    "", 12, "", 19, "store"
     RET
diff --git a/libavcodec/x86/simple_idct10_template.asm b/libavcodec/x86/simple_idct10_template.asm
index 8367011dfd..d8ea0bcc6b 100644
--- a/libavcodec/x86/simple_idct10_template.asm
+++ b/libavcodec/x86/simple_idct10_template.asm
@@ -26,6 +26,25 @@
 
 %if ARCH_X86_64
 
+%macro define_constants 1
+    %undef w4_plus_w2
+    %undef w4_min_w2
+    %undef w4_plus_w6
+    %undef w4_min_w6
+    %undef w1_plus_w3
+    %undef w3_min_w1
+    %undef w7_plus_w3
+    %undef w3_min_w7
+    %define w4_plus_w2 w4_plus_w2%1
+    %define w4_min_w2  w4_min_w2%1
+    %define w4_plus_w6 w4_plus_w6%1
+    %define w4_min_w6  w4_min_w6%1
+    %define w1_plus_w3 w1_plus_w3%1
+    %define w3_min_w1  w3_min_w1%1
+    %define w7_plus_w3 w7_plus_w3%1
+    %define w3_min_w7  w3_min_w7%1
+%endmacro
+
 ; interleave data while maintaining source
 ; %1=type, %2=dstlo, %3=dsthi, %4=src, %5=interleave
 %macro SBUTTERFLY3 5
-- 
2.13.0