Context Navigation

+0
← Previous Change
Ticket Comment History
Next Change →

Changes between Initial Version and Version 1 of Ticket #1844, comment 4

Timestamp:: 10/25/2012 05:44:20 PM (7 months ago)
Author:: thegeek
Comment:

Legend:

: Unmodified
: Added
: Removed
: Modified

Ticket #1844, comment 4

-                      initial
+                      v1
 Replying to [comment:3 cehoyos]:
 > Please add the missing parts of the gdb session (disassembly, register dump), see https://ffmpeg.org/bugreports.html - consider using a static build (although it does not really matter).
+Ok.
+Ok, this is the static build with slightly different build settings, which seems to produce the crash in the sse2 version of the function:
+{{{
+  configuration: --cross-prefix=/home/swingcatalyst/mxe/build-ffmpeg/../../mxe/mxe-multitarget-static/usr/bin/x86_64-static-mingw32- --enable-cross-compile --arch=x86_64 --target-os=mingw32 --prefix=/home/swingcatalyst/mxe/build-ffmpeg/install/ffmpeg-1.0-x86_64-static-install --disable-shared --disable-postproc --disable-pthreads --enable-runtime-cpudetect --enable-bzlib --enable-libfreetype --enable-libmp3lame --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-zlib --disable-stripping
+}}}
+{{{
+(gdb) bt
+#0  0x0000000000add1ec in ff_mix_2_1_a_int16_sse2 ()
+#1  0x00000000085ef0a0 in ?? ()
+#2  0x0000000000000000 in ?? ()
+(gdb) disass $pc-32,$pc+32
+Dump of assembler code from 0xadd1cc to 0xadd20c:
+x0000000000add1cc <ff_mix_2_1_a_int16_sse2+44>:     test   $0xf,%r8
+x0000000000add1d3 <ff_mix_2_1_a_int16_sse2+51>:     jne    0xadd0bf <mix_2_1_int16_u_int_sse2>
+x0000000000add1d9 <ff_mix_2_1_a_int16_sse2+57>:     test   $0xf,%rcx
+x0000000000add1e0 <ff_mix_2_1_a_int16_sse2+64>:     jne    0xadd0bf <mix_2_1_int16_u_int_sse2>
+x0000000000add1e6 <ff_mix_2_1_a_int16_sse2+70>:     movd   (%r9,%r10,4),%xmm4
+=> 0x0000000000add1ec <ff_mix_2_1_a_int16_sse2+76>:     movd   (%r9,%r11,4),%xmm6
+x0000000000add1f2 <ff_mix_2_1_a_int16_sse2+82>:     pshuflw $0x0,%xmm4,%xmm5
+x0000000000add1f7 <ff_mix_2_1_a_int16_sse2+87>:     punpcklqdq %xmm5,%xmm5
+x0000000000add1fb <ff_mix_2_1_a_int16_sse2+91>:     pshuflw $0x0,%xmm6,%xmm6
+x0000000000add200 <ff_mix_2_1_a_int16_sse2+96>:     punpcklqdq %xmm6,%xmm6
+x0000000000add204 <ff_mix_2_1_a_int16_sse2+100>:    psllq  $0x20,%xmm4
+x0000000000add209 <ff_mix_2_1_a_int16_sse2+105>:    psrlq  $0x30,%xmm4
+End of assembler dump.
+(gdb) info all-registers
+rax            0x2000   8192
+rbx            0x5b267a0        95578016
+rcx            0xc2dc0a0        204325024
+rdx            0xc2bbfe0        204193760
+rsi            0x5b26970        95578480
+rdi            0x5b267a0        95578016
+rbp            0x0      0x0
+rsp            0x23dc98 0x23dc98
+r8             0xc2c3fe0        204226528
+r9             0x7604f80        123752320
+r10            0x0      0
+r11            0xea6400000001   257715217629185
+r12            0x23de10 2350608
+r13            0x1      1
+r14            0x0      0
+r15            0x1      1
+rip            0xadd1ec 0xadd1ec <ff_mix_2_1_a_int16_sse2+76>
+eflags         0x10246  [ PF ZF IF RF ]
+cs             0x33     51
+ss             0x2b     43
+ds             0x0      0
+es             0x0      0
+fs             0x0      0
+gs             0x0      0
+st0            -nan(0xbebebebebebebebe) (raw 0xffffbebebebebebebebe)
+st1            -nan(0xbebebebebebebebe) (raw 0xffffbebebebebebebebe)
+st2            -nan(0x31b7323331362f33) (raw 0xffff31b7323331362f33)
+st3            -nan(0x3100b700320033)   (raw 0xffff003100b700320033)
+st4            9        (raw 0x40029000000000000000)
+st5            1        (raw 0x3fff8000000000000000)
+st6            2818.3829312644548       (raw 0x400ab026207c88973351)
+st7            3.4500000000000002       (raw 0x4000dcccccccccccd000)
+fctrl          0x420037f        69206911
+fstat          0x420    1056
+ftag           0x0      0
+fiseg          0x33     51
+fioff          0xd252a0 13783712
+foseg          0x2b     43
+fooff          0x23e0a0 2351264
+fop            0x0      0
+xmm0           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000}, v16_int8 = {0xea, 0xff, 0xd5, 0xff, 0xd3, 0xff, 0xdd, 0xff, 0xd5, 0xff,
+xce, 0xff, 0xd8, 0xff, 0xdf, 0xff}, v8_int16 = {0xffea, 0xffd5, 0xffd3, 0xffdd, 0xffd5, 0xffce, 0xffd8, 0xffdf}, v4_int32 = {0xffd5ffea, 0xffddffd3, 0xffceffd5,
+xffdfffd8}, v2_int64 = {0xffddffd3ffd5ffea, 0xffdfffd8ffceffd5}, uint128 = 0xffdfffd8ffceffd5ffddffd3ffd5ffea}
+xmm1           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000}, v16_int8 = {0xea, 0xff, 0xd5, 0xff, 0xd3, 0xff, 0xdd, 0xff, 0xd5, 0xff,
+xce, 0xff, 0xd8, 0xff, 0xdf, 0xff}, v8_int16 = {0xffea, 0xffd5, 0xffd3, 0xffdd, 0xffd5, 0xffce, 0xffd8, 0xffdf}, v4_int32 = {0xffd5ffea, 0xffddffd3, 0xffceffd5,
+xffdfffd8}, v2_int64 = {0xffddffd3ffd5ffea, 0xffdfffd8ffceffd5}, uint128 = 0xffdfffd8ffceffd5ffddffd3ffd5ffea}
+xmm2           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000}, v16_int8 = {0xd5, 0xff, 0xce, 0xff, 0xd8, 0xff, 0xdf, 0xff, 0xd5, 0xff,
+xce, 0xff, 0xd8, 0xff, 0xdf, 0xff}, v8_int16 = {0xffd5, 0xffce, 0xffd8, 0xffdf, 0xffd5, 0xffce, 0xffd8, 0xffdf}, v4_int32 = {0xffceffd5, 0xffdfffd8, 0xffceffd5,
+xffdfffd8}, v2_int64 = {0xffdfffd8ffceffd5, 0xffdfffd8ffceffd5}, uint128 = 0xffdfffd8ffceffd5ffdfffd8ffceffd5}
+xmm3           {v4_float = {0xffffffaf, 0xffffffcd, 0xffffffdb, 0xfffffff3}, v2_double = {0xffffffc2c6667abb, 0xffffffffff8726c5}, v16_int8 = {0xf6, 0x8d, 0xa2, 0xc2, 0xcc,
+x9c, 0x4e, 0xc2, 0x3f, 0x3b, 0x15, 0xc2, 0x4e, 0x36, 0x5e, 0xc1}, v8_int16 = {0x8df6, 0xc2a2, 0x9ccc, 0xc24e, 0x3b3f, 0xc215, 0x364e, 0xc15e}, v4_int32 = {0xc2a28df6,
+xc24e9ccc, 0xc2153b3f, 0xc15e364e}, v2_int64 = {0xc24e9cccc2a28df6, 0xc15e364ec2153b3f}, uint128 = 0xc15e364ec2153b3fc24e9cccc2a28df6}
+xmm4           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0, 0x40, 0xf, 0x0 <repeats 13 times>}, v8_int16 = {0x4000, 0xf, 0x0, 0x0, 0x0, 0x0, 0x0,
+x0}, v4_int32 = {0xf4000, 0x0, 0x0, 0x0}, v2_int64 = {0xf4000, 0x0}, uint128 = 0x000000000000000000000000000f4000}
+xmm5           {v4_float = {0xffffffd0, 0xffffffdb, 0xffffffe9, 0xfffffff3}, v2_double = {0xfffffffab1300f70, 0xffffffffff8726c5}, v16_int8 = {0x85, 0x27, 0x41, 0xc2, 0x3f,
+x3b, 0x15, 0xc2, 0x45, 0x95, 0xb9, 0xc1, 0x4e, 0x36, 0x5e, 0xc1}, v8_int16 = {0x2785, 0xc241, 0x3b3f, 0xc215, 0x9545, 0xc1b9, 0x364e, 0xc15e}, v4_int32 = {0xc2412785,
+xc2153b3f, 0xc1b99545, 0xc15e364e}, v2_int64 = {0xc2153b3fc2412785, 0xc15e364ec1b99545}, uint128 = 0xc15e364ec1b99545c2153b3fc2412785}
+xmm6           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm7           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm8           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0, 0x0, 0x0, 0x80, 0x0 <repeats 12 times>}, v8_int16 = {0x0, 0x8000, 0x0, 0x0, 0x0, 0x0,
+x0, 0x0}, v4_int32 = {0x80000000, 0x0, 0x0, 0x0}, v2_int64 = {0x80000000, 0x0}, uint128 = 0x00000000000000000000000080000000}
+xmm9           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm10          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm11          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm12          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm13          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm14          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+xmm15          {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0 <repeats 16 times>}, v8_int16 = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0}, v4_int32 = {
+x0, 0x0, 0x0, 0x0}, v2_int64 = {0x0, 0x0}, uint128 = 0x00000000000000000000000000000000}
+mxcsr          0x1fa0   [ PE IM DM ZM OM UM PM ]
+(gdb)
+}}}
+>
 > Do you know if the Zeranoe build actually contains the AVX-optimized function ff_mix_2_1_a_float_avx?
 I just checked and it does. I've also seen this crash with the sse2 version of the function.
+I just checked and it does (both sse and avx versions).
 I'm currently investigating something curious I've discovered. It seems my crosschain compilex libvpx with pthreads, but I use w32threads in ffmpeg. Will using both thread libraries be OK?