http://www.miikahweb.com/feed.php MiikaHweb - Blender Commits By Lockal http://www.miikahweb.com/ MiikaHweb - Blender Commits By Lockal fi Thu, 27 Feb 20 04:51:58 +0000 MiikaHweb RSS contact at miikahweb.com <![CDATA[[88acb3c] master: Fix T44707: cycles border render regression]]> http://www.miikahweb.com/en/blender/git-logs/commit/88acb3c599b31d37375c325c47cc9264ad700720 88acb3c
Branches : master
Author : Sv. Lockal (lockal)
Committed By : Campbell Barton (campbellbarton)
----------------------------------------
Fix T44707: cycles border render regression

----------------------------------------
1 Path Changed]]>
Mon, 18 May 2015 01:37:19 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/88acb3c599b31d37375c325c47cc9264ad700720Sv. Lockal
<![CDATA[[c7bccb3] master: Cycles: check for F16C support with __cpuid, as we do for BMI...]]> http://www.miikahweb.com/en/blender/git-logs/commit/c7bccb30bf03a0ac4d6d135f94658c93be7b7b0f c7bccb3
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: check for F16C support with __cpuid, as we do for BMI and BMI2

----------------------------------------
1 Path Changed]]>
Mon, 11 May 2015 15:49:36 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c7bccb30bf03a0ac4d6d135f94658c93be7b7b0fSv. Lockal
<![CDATA[[d55868c] master: Cycles: And yet another compilation fix after half-float commit...]]> http://www.miikahweb.com/en/blender/git-logs/commit/d55868c3b2004cba008e21f5607dc08076594451 d55868c
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: And yet another compilation fix after half-float commit for clang.

Suggested by Brecht, tested with gcc > 4.4 and Clang

----------------------------------------
1 Path Changed]]>
Sun, 10 May 2015 19:32:32 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/d55868c3b2004cba008e21f5607dc08076594451Sv. Lockal
<![CDATA[[3ec1684] master: Cycles: fix compilation on 32-bit Windows for half-floats]]> http://www.miikahweb.com/en/blender/git-logs/commit/3ec168465d31c90cc75b5ea70de492dbeb4ac992 3ec1684
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: fix compilation on 32-bit Windows for half-floats

Reported by IRC user HG1.

----------------------------------------
1 Path Changed]]>
Sun, 10 May 2015 19:06:43 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/3ec168465d31c90cc75b5ea70de492dbeb4ac992Sv. Lockal
<![CDATA[[8db2a9a] master: Cycles: Add -mf16c for previous commit for Scons]]> http://www.miikahweb.com/en/blender/git-logs/commit/8db2a9a352c62d4a1ad3ba39dd3cf0b4a8f9ae6f 8db2a9a
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: Add -mf16c for previous commit for Scons

Thanks to Dingto for noticing!

----------------------------------------
1 Path Changed]]>
Sun, 10 May 2015 17:51:04 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/8db2a9a352c62d4a1ad3ba39dd3cf0b4a8f9ae6fSv. Lockal
<![CDATA[[2ec221a] master: Cycles: Use native float->half conversion instructions for...]]> http://www.miikahweb.com/en/blender/git-logs/commit/2ec221aa281d8c8e8e52d59f9364b5dd373a752c 2ec221a
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: Use native float->half conversion instructions for Haswell CPUs.

This makes OCIO viewport color correction a little bit faster (about -0.5s for 100 samples)
Also set max half float value to 65504.0 to conform with IEEE 754.

----------------------------------------
2 Paths Changed]]>
Sun, 10 May 2015 16:35:51 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/2ec221aa281d8c8e8e52d59f9364b5dd373a752cSv. Lockal
<![CDATA[[7201f6d] master: Cycles: Use curve approximation for blackbody instead of lookup...]]> http://www.miikahweb.com/en/blender/git-logs/commit/7201f6d14c0161ad9a0d4143d1c5caf872e0d93e 7201f6d
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: Use curve approximation for blackbody instead of lookup table

Now we calculate color in range 800..12000 using an approximation a/x+bx+c for R and G and ((at + b)t + c)t + d) for B.
Max absolute error for RGB for non-lut function is less than 0.0001, which is enough to get the same 8 bit/channel color as for OSL with a noticeable performance difference.
However there is a slight visible difference between previous non-OSL implementation because of lookup table interpolation and offset-by-one mistake.
The previous implementation gave black color outside of soft range (t > 12000), now it gives the same color as for 12000.

Also blackbody node without input connected is being converted to value input at shader compile time.

Reviewers: dingto, sergey

Reviewed By: dingto

Subscribers: nutel, brecht, juicyfruit

Differential Revision: https://developer.blender.org/D1280

----------------------------------------
13 Paths Changed]]>
Tue, 05 May 2015 06:11:54 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/7201f6d14c0161ad9a0d4143d1c5caf872e0d93eSv. Lockal
<![CDATA[[c32ded3] master: Cycles: add better specializations for SSE shuffle function...]]> http://www.miikahweb.com/en/blender/git-logs/commit/c32ded36548b26c5722803556e2b502d3dbbba8a c32ded3
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: add better specializations for SSE shuffle function and few more wrappers.

----------------------------------------
3 Paths Changed]]>
Sat, 07 Mar 2015 17:25:21 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c32ded36548b26c5722803556e2b502d3dbbba8aSv. Lockal
<![CDATA[[c8fb488] master: Fix T41066: An actual fix for curve intersection on FMA-enabled...]]> http://www.miikahweb.com/en/blender/git-logs/commit/c8fb488b087f91ba58ac16e4e76050b660122417 c8fb488
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Fix T41066: An actual fix for curve intersection on FMA-enabled CPUs

----------------------------------------
2 Paths Changed]]>
Sat, 07 Mar 2015 16:20:34 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c8fb488b087f91ba58ac16e4e76050b660122417Sv. Lockal
<![CDATA[[7ad9b13] blender-v2.72-release: Use native float math functions for MSVC12]]> http://www.miikahweb.com/en/blender/git-logs/commit/7ad9b13b54d18026a9d0aa09bfb31ed70e5e934d 7ad9b13
Branches : blender-v2.72-release
Author : Sv. Lockal (lockal)
Committed By : Sergey Sharybin (sergey)
----------------------------------------
Use native float math functions for MSVC12

`double` surrogates are slow (e.g. pow is 2x slower than powf), and MSVC12
supports fp-math functions from C99.

----------------------------------------
1 Path Changed]]>
Fri, 03 Oct 2014 13:09:28 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/7ad9b13b54d18026a9d0aa09bfb31ed70e5e934dSv. Lockal
<![CDATA[[5ecbd5c] master: Use native float math functions for MSVC12]]> http://www.miikahweb.com/en/blender/git-logs/commit/5ecbd5c87144c0f36089ba91e37d5768fc766315 5ecbd5c
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Use native float math functions for MSVC12

`double` surrogates are slow (e.g. pow is 2x slower than powf), and MSVC12
supports fp-math functions from C99.

----------------------------------------
1 Path Changed]]>
Tue, 30 Sep 2014 09:39:03 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/5ecbd5c87144c0f36089ba91e37d5768fc766315Sv. Lockal
<![CDATA[[ab32a18] master: Cycles: SSE optimization for Voronoi cells texture]]> http://www.miikahweb.com/en/blender/git-logs/commit/ab32a1807dd153723d26a7d53895ed071233dafc ab32a18
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: SSE optimization for Voronoi cells texture

Gives 5-6% speedup for Caterpillar_PatazStudio.blend.

Reviewed By: brecht, dingto

Differential Revision: https://developer.blender.org/D419

----------------------------------------
5 Paths Changed]]>
Thu, 03 Apr 2014 19:35:10 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/ab32a1807dd153723d26a7d53895ed071233dafcSv. Lockal
<![CDATA[[c019ae5] master: I18N: add missing lines]]> http://www.miikahweb.com/en/blender/git-logs/commit/c019ae5ea3a8eb49010de76c14a359c4729bbcf0 c019ae5
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
I18N: add missing lines

Reviewed By: mont29

Differential Revision: https://developer.blender.org/D328

----------------------------------------
7 Paths Changed]]>
Thu, 03 Apr 2014 18:49:27 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c019ae5ea3a8eb49010de76c14a359c4729bbcf0Sv. Lockal
<![CDATA[[e7c2578] master: Cycles: avoid 1.0f/(1.0f/x) divisions, which msvc (only) can...]]> http://www.miikahweb.com/en/blender/git-logs/commit/e7c2578576380288befcd77e88edd8ae508ed01a e7c2578
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: avoid 1.0f/(1.0f/x) divisions, which msvc (only) can't optimize.

This makes bmw scene in msvc 12 builds 6% faster.
It also gives a minor speedup for SSE hair in all compilers.

----------------------------------------
6 Paths Changed]]>
Thu, 03 Apr 2014 18:08:53 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/e7c2578576380288befcd77e88edd8ae508ed01aSv. Lockal
<![CDATA[[c682fe4] master: Cycles: fix 3-5% performance regression in msvc builds caused...]]> http://www.miikahweb.com/en/blender/git-logs/commit/c682fe49f482b21eed4a25dcb366e65676af5905 c682fe4
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: fix 3-5% performance regression in msvc builds caused by a typo in stackchecking flags.

----------------------------------------
2 Paths Changed]]>
Mon, 31 Mar 2014 17:44:02 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c682fe49f482b21eed4a25dcb366e65676af5905Sv. Lockal
<![CDATA[[7397ef8] master: UI: Fix more double ":" in UI labels]]> http://www.miikahweb.com/en/blender/git-logs/commit/7397ef8666270d11025ff347ab95f23bed7e04db 7397ef8
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
UI: Fix more double ":" in UI labels

----------------------------------------
3 Paths Changed]]>
Thu, 27 Mar 2014 03:15:08 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/7397ef8666270d11025ff347ab95f23bed7e04dbSv. Lockal
<![CDATA[[c45c472] master: Cycles: SSE optimization for line segments/ribbons hair]]> http://www.miikahweb.com/en/blender/git-logs/commit/c45c472e1b373c5125955056bcf3dd9b5edb8d18 c45c472
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: SSE optimization for line segments/ribbons hair

Gives ~11% speedup for hair.blend, ~10% for koro_final.blend

Also extract few common subexpressions in hair calculation.

Reviewed By: brecht

Differential Revision: https://developer.blender.org/D318

----------------------------------------
2 Paths Changed]]>
Sat, 22 Mar 2014 20:45:59 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/c45c472e1b373c5125955056bcf3dd9b5edb8d18Sv. Lockal
<![CDATA[[6045de2] master: Cycles: remove ccl_align macro for GPU as unused and unsupported...]]> http://www.miikahweb.com/en/blender/git-logs/commit/6045de2bf5a13066d10148ae558071f474aaf6ee 6045de2
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: remove ccl_align macro for GPU as unused and unsupported in OpenCL

----------------------------------------
1 Path Changed]]>
Sun, 02 Mar 2014 08:44:52 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/6045de2bf5a13066d10148ae558071f474aaf6eeSv. Lockal
<![CDATA[[5031ca0] master: Cycles: compile fix after rB7808360c5f (own mistake)]]> http://www.miikahweb.com/en/blender/git-logs/commit/5031ca05aab9d3659ebdc5a95b20d5d713222ccd 5031ca0
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: compile fix after rB7808360c5f (own mistake)

----------------------------------------
1 Path Changed]]>
Thu, 27 Feb 2014 13:29:35 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/5031ca05aab9d3659ebdc5a95b20d5d713222ccdSv. Lockal
<![CDATA[[7808360] master: Cycles: fix crash in SSE hair and half-floats on x86+vc2008]]> http://www.miikahweb.com/en/blender/git-logs/commit/7808360c5f35c5a6371c3627758a70db431955a2 7808360
Branches : master
Author : Sv. Lockal (lockal)
----------------------------------------
Cycles: fix crash in SSE hair and half-floats on x86+vc2008

MSVC 2008 ignores alignement attribute when assigning from unaligned
float4 vector, returned from other function. Now Cycles uses unaligned
loads instead of casts for win32 in x86 mode.

----------------------------------------
8 Paths Changed]]>
Thu, 27 Feb 2014 11:01:20 +0000 http://www.miikahweb.com/en/blender/git-logs/commit/7808360c5f35c5a6371c3627758a70db431955a2Sv. Lockal