<div style="line-height:1.7;color:#000000;font-size:14px;font-family:arial"><div>Thank your report</div>
<div>PACKUSDW is SSE4.1 instruction, we will fix it soon.</div>
<div><br>At 2014-04-21 22:44:35,"dn c" <dncodr@gmail.com> wrote:<br>>Hi. Fisrt of all thanks for quick fix unaligned read.<br>>But I found one more crash, now its 10(16-bit ) x64-build. Correct me<br>>if i wrong, but only supported for high bit depth is 64-bit builds. So<br>>this time in SSE2 branch SSE4.1 instruction PACKUSDW.<br>>Here some log, stacktrace and disasm info.<br>><br>>yuv [info]: 320x240 fps 20000/1000 i420 frames 0 - 30 of 31<br>>[New Thread 1460.0x738]<br>>x265 [info]: HEVC encoder version +-<br>>x265 [info]: build info [Windows][GCC 4.8.2][64 bit] 16bpp<br>>x265 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 Cache64<br>>[New Thread 1460.0x2c8]<br>>[New Thread 1460.0xb8]<br>>x265 [info]: WPP streams / pool / frames : 4 / 2 / 1<br>>x265 [info]: Main10 profile, Level-2 (Main tier)<br>>x265 [info]: Internal bit depth : 10<br>>x265 [info]: CU size : 64<br>>x265 [info]: Max RQT depth inter / intra : 1 / 1<br>>x265 [info]: ME / range / subpel / merge : hex / 57 / 2 / 2<br>>x265 [info]: Keyframe min / max / scenecut : 20 / 250 / 40<br>>x265 [info]: Lookahead / bframes / badapt : 20 / 4 / 2<br>>x265 [info]: b-pyramid / weightp / weightb / refs: 1 / 1 / 0 / 3<br>>x265 [info]: Rate Control / AQ-Strength / CUTree : CRF-20.0 / 1.0 / 1<br>>x265 [info]: tools: rect amp rd=3 lft sao-lcu sign-hide<br>>[New Thread 1460.0x1ec]<br>>x265 [debug]: POC:0 I QP 38.40(25) 397752 bits [SSIM: 19.806dB]<br>>x265 [full]: poc: 4 weights: [L0:R0 Y{29/32+9}U{58/64-1}V{61/64+6}]<br>>x265 [debug]: POC:4 P QP 38.25(25) 360088 bits [SSIM: 15.483dB] [L0 0 ]<br>>=========================<br>>Program received signal SIGILL, Illegal instruction.<br>>[Switching to Thread 1460.0x2c8]<br>>0x0000000000525f20 in x265_interp_4tap_vert_sp_4x2_sse2 ()<br>><br>>#0 0x0000000000525f20 in x265_interp_4tap_vert_sp_4x2_sse2 ()<br>>#1 0x00000000005b82dc in<br>>x265::TComPrediction::xPredInterUni(x265::TComDataCU*,unsigned int,<br>>int, int, int, x265::TComYuv*, bool, bool) ()<br>>#2 0x00000000005b9c30 in<br>>x265::TComPrediction::xPredInterBi(x265::TComDataCU*,unsigned int,<br>>int, int, x265::TComYuv*, bool, bool) ()<br>>#3 0x00000000005ba108 in<br>>x265::TComPrediction::motionCompensation(x265::TComDataCU*,<br>>x265::TComYuv*, int, int, bool, bool) ()<br>>#4 0x00000000005c47e8 in<br>>x265::TEncCu::xCompressInterCU(x265::TComDataCU*&, x265::TComDataCU*&,<br>>x265::TComDataCU*&, unsigned int, unsigned int, unsigned char)<br>>()<br>>=========================<br>> 0x0000000000525f0e <+126>: paddd %xmm4,%xmm0<br>> 0x0000000000525f12 <+130>: paddd %xmm4,%xmm1<br>> 0x0000000000525f16 <+134>: psrad $0xa,%xmm0<br>> 0x0000000000525f1b <+139>: psrad $0xa,%xmm1<br>>=> 0x0000000000525f20 <+144>: packusdw %xmm1,%xmm0<br>> 0x0000000000525f25 <+149>: pmaxsw %xmm6,%xmm0<br>> 0x0000000000525f29 <+153>: pminsw %xmm5,%xmm0<br>> 0x0000000000525f2d <+157>: movq %xmm0,(%r8)<br>> 0x0000000000525f32 <+162>: movhps %xmm0,(%r8,%r9,1)<br>> 0x0000000000525f37 <+167>: movaps 0x8(%rsp),%xmm6<br>> 0x0000000000525f3c <+172>: retq<br>>_______________________________________________<br>>x265-devel mailing list<br>>x265-devel@videolan.org<br>>https://mailman.videolan.org/listinfo/x265-devel<br></div></div>