Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Mario *LigH* Rohkrämer
See also: http://forum.doom9.org/showthread.php?p=1677018#post1677018 ff. Probably some needle in the hay task for Min Chen, the ASM expert? -- Fun and success! Mario *LigH* Rohkrämer mailto:cont...@ligh.de ___ x265-devel mailing list

Re: [x265] [PATCH] vbv: log frame-average QPs for VBV; even when AQ is disabled

2014-04-11 Thread Aarthi Priya Thirumalai
hello, reminder : this bug-fix is still pending. can we have this patch pushed in to fix the bug, if there is no problems with it? On Tue, Apr 8, 2014 at 8:33 PM, aar...@multicorewareinc.com wrote: # HG changeset patch # User Aarthi Thirumalai # Date 1396969086 -19800 # Tue Apr 08

Re: [x265] [PATCH] vbv: log frame-average QPs for VBV; even when AQ is disabled

2014-04-11 Thread Deepthi Nandakumar
Sure. On Fri, Apr 11, 2014 at 11:41 AM, Aarthi Priya Thirumalai aar...@multicorewareinc.com wrote: hello, reminder : this bug-fix is still pending. can we have this patch pushed in to fix the bug, if there is no problems with it? On Tue, Apr 8, 2014 at 8:33 PM,

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Nabajit Deka
Hi, It will be really helpful if you can provide the call stack log. On Fri, Apr 11, 2014 at 11:39 AM, Mario *LigH* Rohkrämer cont...@ligh.dewrote: See also: http://forum.doom9.org/showthread.php?p=1677018#post1677018 ff. Probably some needle in the hay task for Min Chen, the ASM expert?

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Nabajit Deka
We dont have a system (having support upto SSSE3) to reproduce the issue at our end . So the call stack will be helpful. On Fri, Apr 11, 2014 at 1:49 PM, Nabajit Deka naba...@multicorewareinc.comwrote: Hi, It will be really helpful if you can provide the call stack log. On Fri, Apr 11,

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Mario *LigH* Rohkrämer
If you can give us call stack, we can solve it soon. I did not have this issue, I report it on behalf of 'D3C0D3R': See also: http://forum.doom9.org/showthread.php?p=1677018#post1677018 ff. I may ask him to provide the call stack. But if he asks how to do that, please tell me too how he

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread chen
Thank you! For simplest way, capture windows crash window (show crash address) and his exe file, we can find more information in it. At 2014-04-11 16:35:08,Mario *LigH* Rohkrämer cont...@ligh.de wrote: If you can give us call stack, we can solve it soon. I did not have this issue, I report it

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Mario *LigH* Rohkrämer
Am 11.04.2014, 10:28 Uhr, schrieb Nabajit Deka naba...@multicorewareinc.com: We dont have a system (having support upto SSSE3) to reproduce the issue at our end . So the call stack will be helpful. I wonder if it may be possible to provoke this SSSE3-only crash by using a better CPU and

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread chen
--asm disable asm code, can't help to detect problem point At 2014-04-11 16:55:20,Mario *LigH* Rohkrämer cont...@ligh.de wrote: Am 11.04.2014, 10:28 Uhr, schrieb Nabajit Deka naba...@multicorewareinc.com: We dont have a system (having support upto SSSE3) to reproduce the issue at our end .

Re: [x265] [PATCH] fix build error on VS2008 + WinXP

2014-04-11 Thread Steve Borho
On Thu, Apr 10, 2014 at 9:36 PM, chen chenm...@163.com wrote: At 2014-04-11 02:03:29,Steve Borho st...@borho.org wrote: On Thu, Apr 10, 2014 at 4:38 AM, Min Chen chenm...@163.com wrote: # HG changeset patch # User Min Chen chenm...@163.com # Date 1397122677 -28800 # Node ID

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread Steve Borho
On Fri, Apr 11, 2014 at 4:04 AM, chen chenm...@163.com wrote: --asm disable asm code, can't help to detect problem point Do any of the virtual PC tools allow you to specify the SIMD architecture level? It would be really handy to be able to: valgrind --cpu=ssse3 ./test/Testbench Then we could

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread chen
I often use QEMU At 2014-04-12 03:30:46,Steve Borho st...@borho.org wrote: On Fri, Apr 11, 2014 at 4:04 AM, chen chenm...@163.com wrote: --asm disable asm code, can't help to detect problem point Do any of the virtual PC tools allow you to specify the SIMD architecture level? It would be

Re: [x265] ASM crash in r6682 on E5200: Probably SSE4 vs. SSSE3 instructions

2014-04-11 Thread chen
a little more: your code is right, but when someone defined HAVE_ALIGNED_STACK and pass unalignment stack pointer into your code, mova will make crash. At 2014-04-12 05:45:15,chen chenm...@163.com wrote: @Nabajit, could you check dct8.asm, your r5 is unalignment, but use mova. At 2014-04-12

[x265] [PATCH] fix build error on VS2008 + WinXP

2014-04-11 Thread Min Chen
# HG changeset patch # User Min Chen chenm...@163.com # Date 1397256800 -28800 # Node ID 065e6599bab74c34e26ad67a9b9f6ed41516856d # Parent 850ebca2f7c88536753941736e447de475fe746f fix build error on VS2008 + WinXP diff -r 850ebca2f7c8 -r 065e6599bab7 source/common/winxp.h ---

Re: [x265] [PATCH] fix build error on VS2008 + WinXP

2014-04-11 Thread Steve Borho
On Fri, Apr 11, 2014 at 5:53 PM, Min Chen chenm...@163.com wrote: # HG changeset patch # User Min Chen chenm...@163.com # Date 1397256800 -28800 # Node ID 065e6599bab74c34e26ad67a9b9f6ed41516856d # Parent 850ebca2f7c88536753941736e447de475fe746f fix build error on VS2008 + WinXP modified