[FFmpeg-devel] [PATCH 1/3] avcodec/x86/vvc/vvc_alf: fix integer overflow

[toqsxw at outlook.com]

From: Wu Jianhua <toqsxw at outlook.com>

Some tests fails with certain seeds

tests/checkasm/checkasm 2325607578 --test=vvc_alf
checkasm: using random seed 2325607578
AVX2:
    vvc_alf_filter_luma_120x20_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x24_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x28_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x32_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x36_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x40_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x44_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x48_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x52_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x56_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x60_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x64_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x68_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x72_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x76_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x80_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x84_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x88_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x92_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x96_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x100_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x104_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x108_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x112_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x116_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x120_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x124_12_avx2 (vvc_alf.c:104)
    vvc_alf_filter_luma_120x128_12_avx2 (vvc_alf.c:104)
  - vvc_alf.alf_filter   [FAILED]
  - vvc_alf.alf_classify [OK]
checkasm: 28 of 9216 tests have failed

Reported-by: James Almer <jamrial at gmail.com>
Signed-off-by: Wu Jianhua <toqsxw at outlook.com>
---
 libavcodec/x86/vvc/vvc_alf.asm | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/libavcodec/x86/vvc/vvc_alf.asm b/libavcodec/x86/vvc/vvc_alf.asm
index 71e821c27b..91f158bac9 100644
--- a/libavcodec/x86/vvc/vvc_alf.asm
+++ b/libavcodec/x86/vvc/vvc_alf.asm
@@ -278,7 +278,9 @@ SECTION .text
     psrad             m0, SHIFT + 3
     psrad             m1, SHIFT + 3
 %%shift_end:
+%if ps == 1
     packssdw          m0, m0, m1
+%endif
 %endmacro
 
 ; FILTER_VB(line)
@@ -356,7 +358,18 @@ SECTION .text
 
     FILTER_VB         xq
 
+    ; sum += curr
+%if ps == 1
     paddw             m0, m2
+%else
+    vpunpcklqdq      m11, m2, m2
+    vpunpckhqdq      m12, m2, m2
+    vpunpcklwd       m11, m11, m14
+    vpunpcklwd       m12, m12, m14
+    paddd             m0, m11
+    paddd             m1, m12
+    packssdw          m0, m0, m1
+%endif
 
     ; clip to pixel
     CLIPW             m0, m14, m15
-- 
2.44.0.windows.1