[D3C0D3R]

Ok. I compile x265 with CMAKE_BUILD_TYPE = Debug.
And run this:

gdb --args x265_debug --crf 20  --input ffmpeg_g.exe --input-depth 8 --input-res 320x240 --fps 20 --preset=medium --asm=0x014007F --ssim --log=4 --output 1_1.265

Then type "run" in gdb console:

Program received signal SIGSEGV, Segmentation fault.
[Switching to Thread 2916.0xf28]
0x00533950 in x265_patial_butterfly_inverse_internal_pass2_ssse3 ()
(gdb) bt
#0  0x00533950 in x265_patial_butterfly_inverse_internal_pass2_ssse3 ()
#1  0x00533b6e in x265_idct8_ssse3 ()
#2  0x0441f339 in ?? ()
Backtrace stopped: previous frame inner to this frame (corrupt stack?)
(gdb) disass $pc-32,$pc+32
Dump of assembler code from 0x533930 to 0x533970:
   0x00533930 <x265_patial_butterfly_inverse_internal_pass1_ssse3+368>: jb     0x533916 <x265_patial_butterfly_inverse_internal_pass1_ssse3+342>
   0x00533932 <x265_patial_butterfly_inverse_internal_pass1_ssse3+370>: pop    %es
   0x00533933 <x265_patial_butterfly_inverse_internal_pass1_ssse3+371>: psubd  %xmm5,%xmm1
   0x00533937 <x265_patial_butterfly_inverse_internal_pass1_ssse3+375>: psrad  $0x7,%xmm1
   0x0053393c <x265_patial_butterfly_inverse_internal_pass1_ssse3+380>: packssdw %xmm1,%xmm4
   0x00533940 <x265_patial_butterfly_inverse_internal_pass1_ssse3+384>: movq   %xmm4,0x30(%edi)
   0x00533945 <x265_patial_butterfly_inverse_internal_pass1_ssse3+389>: movhps %xmm4,0x40(%edi)
   0x00533949 <x265_patial_butterfly_inverse_internal_pass1_ssse3+393>: ret
   0x0053394a <x265_patial_butterfly_inverse_internal_pass1_ssse3+394>: nopw   0x0(%eax,%eax,1)
=> 0x00533950 <x265_patial_butterfly_inverse_internal_pass2_ssse3+0>:   movdqa (%edi),%xmm0
   0x00533954 <x265_patial_butterfly_inverse_internal_pass2_ssse3+4>:   movdqa %xmm0,%xmm4
   0x00533958 <x265_patial_butterfly_inverse_internal_pass2_ssse3+8>:   pshufb 0x6a7950,%xmm4
   0x00533961 <x265_patial_butterfly_inverse_internal_pass2_ssse3+17>:  pmaddwd 0x6a7960,%xmm4
   0x00533969 <x265_patial_butterfly_inverse_internal_pass2_ssse3+25>:  phsubd %xmm4,%xmm5
   0x0053396e <x265_patial_butterfly_inverse_internal_pass2_ssse3+30>:  pshufd $0x4e,%xmm4,%xmm4
End of assembler dump.

eax            0xc55b90 12934032
ecx            0x163d900        23320832
edx            0x10     16
ebx            0x30     48
esp            0x10bf8c8        0x10bf8c8
ebp            0x623990 0x623990 <_ZSt16__convert_from_vRKPiPciPKcz+6437264>
esi            0x623970 6437232
edi            0x10bf8cc        17561804
eip            0x4e63f0 0x4e63f0 <x265_patial_butterfly_inverse_internal_pass2_ssse3>
eflags         0x10216  [ PF AF IF RF ]
cs             0x1b     27
ss             0x23     35
ds             0x23     35
es             0x23     35
fs             0x3b     59
gs             0x0      0

xmm0           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x31, 0xf5, 0xff, 0xff,
    0x4c, 0x8, 0x0, 0x0, 0xb1, 0x3, 0x0, 0x0, 0xd7, 0x6, 0x0, 0x0}, v8_int16 = {0xf531, 0xffff, 0x84c, 0x0,
    0x3b1, 0x0, 0x6d7, 0x0}, v4_int32 = {0xfffff531, 0x84c, 0x3b1, 0x6d7}, v2_int64 = {0x84cfffff531,
    0x6d7000003b1}, uint128 = 0x000006d7000003b10000084cfffff531}
xmm1           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x8000000000000000}, v16_int8 = {0xd1, 0x4,
    0x0, 0x0, 0xea, 0x0, 0x0, 0x0, 0x22, 0x4, 0x0, 0x0, 0xe5, 0xf6, 0xff, 0xff}, v8_int16 = {0x4d1, 0x0, 0xea,
    0x0, 0x422, 0x0, 0xf6e5, 0xffff}, v4_int32 = {0x4d1, 0xea, 0x422, 0xfffff6e5}, v2_int64 = {0xea000004d1,
    0xfffff6e500000422}, uint128 = 0xfffff6e500000422000000ea000004d1}
xmm2           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000},
  v16_int8 = {0x80, 0x4, 0x80, 0x4, 0x80, 0xfb, 0x40, 0xf9, 0xc0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x80, 0xfb},
  v8_int16 = {0x480, 0x480, 0xfb80, 0xf940, 0xfdc0, 0x0, 0x0, 0xfb80}, v4_int32 = {0x4800480, 0xf940fb80,
    0xfdc0, 0xfb800000}, v2_int64 = {0xf940fb8004800480, 0xfb8000000000fdc0},
  uint128 = 0xfb8000000000fdc0f940fb8004800480}
xmm3           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x0}, v16_int8 = {0xa7, 0xf8,
    0xff, 0xff, 0xaf, 0xff, 0xff, 0xff, 0x74, 0xfe, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0}, v8_int16 = {0xf8a7, 0xffff,
    0xffaf, 0xffff, 0xfe74, 0xffff, 0x0, 0x0}, v4_int32 = {0xfffff8a7, 0xffffffaf, 0xfffffe74, 0x0}, v2_int64 = {
    0xffffffaffffff8a7, 0xfffffe74}, uint128 = 0x00000000fffffe74ffffffaffffff8a7}
xmm4           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000},
  v16_int8 = {0xdb, 0x6, 0x41, 0x4, 0x39, 0xfc, 0x1, 0xf9, 0xd1, 0x4, 0xea, 0x0, 0x22, 0x4, 0xe5, 0xf6},
  v8_int16 = {0x6db, 0x441, 0xfc39, 0xf901, 0x4d1, 0xea, 0x422, 0xf6e5}, v4_int32 = {0x44106db, 0xf901fc39,
    0xea04d1, 0xf6e50422}, v2_int64 = {0xf901fc39044106db, 0xf6e5042200ea04d1},
  uint128 = 0xf6e5042200ea04d1f901fc39044106db}
xmm5           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x80, 0x82, 0x0, 0x0, 0xc0,
    0xd5, 0x0, 0x0, 0xc0, 0x5, 0xfe, 0xff, 0x0, 0x87, 0x0, 0x0}, v8_int16 = {0x8280, 0x0, 0xd5c0, 0x0, 0x5c0,
    0xfffe, 0x8700, 0x0}, v4_int32 = {0x8280, 0xd5c0, 0xfffe05c0, 0x8700}, v2_int64 = {0xd5c000008280,
    0x8700fffe05c0}, uint128 = 0x00008700fffe05c00000d5c000008280}
xmm6           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x0, 0x0}, v16_int8 = {0x0, 0x8, 0x0, 0x0, 0x0,
    0x8, 0x0, 0x0, 0x0, 0x8, 0x0, 0x0, 0x0, 0x8, 0x0, 0x0}, v8_int16 = {0x800, 0x0, 0x800, 0x0, 0x800, 0x0,
    0x800, 0x0}, v4_int32 = {0x800, 0x800, 0x800, 0x800}, v2_int64 = {0x80000000800, 0x80000000800},
  uint128 = 0x00000800000008000000080000000800}
xmm7           {v4_float = {0x0, 0x0, 0x0, 0x0}, v2_double = {0x8000000000000000, 0x8000000000000000},
  v16_int8 = {0x5e, 0xfe, 0x62, 0xf5, 0x27, 0xfc, 0x7e, 0xff, 0xf7, 0xf5, 0xf3, 0x9, 0x0, 0xf6, 0x9d, 0xfe},
  v8_int16 = {0xfe5e, 0xf562, 0xfc27, 0xff7e, 0xf5f7, 0x9f3, 0xf600, 0xfe9d}, v4_int32 = {0xf562fe5e,
    0xff7efc27, 0x9f3f5f7, 0xfe9df600}, v2_int64 = {0xff7efc27f562fe5e, 0xfe9df60009f3f5f7},
  uint128 = 0xfe9df60009f3f5f7ff7efc27f562fe5e}