Commit Graph
21 Commits
Author SHA1 Message Date
xsacha 5c725262ba Refactor all the SSSE3 functions in TextureDecoder so that the cpu_info check isn't looped over. Speeds up most textures dramatically (where it has previously slowed them).
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6784 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-08 09:08:36 +00:00
xsacha 394534814b New SSSE3 implementation for I4 texture decode. 14% speedup over the previous SSE4 implementation (so it was scrapped).
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6783 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-08 08:07:45 +00:00
xsacha 3cf8003a55 From my last commit: Fix build on Linux. Use SSSE3 instead of SSE3.
Remove some unused vars from the SSE2 CMPR.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6781 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-08 04:59:26 +00:00
xsacha f667c03d55 New SSSE3 implementation of RGB5A3. About 40% improvement (less cycles) on the plain C version and 17% on the SSE2 version.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6779 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-08 02:52:07 +00:00
xsacha 62b79028ef This needs to be in the right place to work for <sse4. Going to bed now :P.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6776 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 17:55:26 +00:00
xsacha 87bd4dd4b9 Probably want to store the result for sse4.
Makes I4 textures appear again for SSE4 codepath.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6775 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 17:52:53 +00:00
xsacha 5c1f30060e Fix a missing 'else' in last commit.
Remove more redundancy in CMPR (may make it faster - not tested).

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6774 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 17:30:48 +00:00
xsacha 9efa62b0ed Add SSSE3 implementation for RGBA8 texture decode. It is 25% faster (3/4 of the cycles) than the SSE2 version.
Remove a bit of redundancy in CMPR.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6773 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 17:17:26 +00:00
xsacha 9cb3340754 An extra 5-10% speedup for I4 texture decoding with SSE4.1 intrinsics.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6772 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 16:00:39 +00:00
xsacha dcbfd4ea4c SSSE3 implementation of IA8 texture decode. Roughly 50% faster than SSE2 version on my computer (SSSE3: 77%, SSE2: 57% vs reference C on Core2 Duo). About half as many cycles.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6770 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 14:55:05 +00:00
xsacha a6acc99a89 Last commit only requires SSSE3, not SSE4.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6769 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 13:54:18 +00:00
xsacha 53474403e2 An SSE4 implementation for I8 texture decode. Slightly faster than SSE2 version on my computer (SSE4: 60%, SSE2: 55% vs reference C on Core2 Duo).
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6768 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 13:40:32 +00:00
xsacha c02f56fca3 Use CPUDetect.h and bSSSE3 to fix "unknown machine instructions" on DX9 plugin.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6767 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 09:42:44 +00:00
xsacha c4477f68e1 ~93% speed improvement (over plain C++) in RGBA -> BGRA conversion for processors that support SSSE3 (Core or newer).
About 40% faster than the SSE2 implementation.

May not be required in future but good for reference.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6766 8ced0084-cf51-0410-be5f-012b33b47a6e
2011-01-07 07:54:04 +00:00
xsacha 963ece2017 Remove unnecessary casting bloat. Since AMD Stream 2.2 this is no longer a requirement.
Stream 2.2 is minimum requirement for OpenCL 1.1 and binary kernels as well (I hope to implement these soon).Remove unnecessary casting bloat. Since AMD Stream 2.2 this is no longer a requirement.

Sidenote: Stream 2.2/Catalyst 10.7b is minimum requirement for OpenCL 1.1 and binary kernels as well. I hope to implement these soon. 

For the latest ATI Drivers and SDK:
http://support.amd.com/us/kbarticles/Pages/OpenCL11ATICat107UpdateDriver.aspx

http://support.amd.com/us/kbarticles/Pages/OpenCL11ATICat107UpdateDriver.aspx

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@6102 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-08-16 15:48:46 +00:00
xsacha 434e6b1198 Small update to fix some cmpr alpha issues with games that use linear filtering. Apparently the colour values matter even though alpha = 0.
Also, remove redundant ANDs.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5787 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-25 19:31:26 +00:00
xsacha 2faae384b3 Changes:
- RGBA8 (DX9/OGL): 10x speed up on Radeon 5450, 2x speed up on other cards due to swizzle registers.
 - RGB565: 2-3x speed up on all hardware
 - Removed OpenCL compiler warnings (eg. redefine).
OpenCL is now optimally complete for DX9/OGL. The code is very fast on all supported hardware. No more updates are needed unless the spec changes or drivers improve. When I started, the OpenCL code was as slow or slower than CPU. Now, using the lowest end radeon that supports the code: a Radeon 45xx mobility, I experience a substantial 2-10x speedup over CPU. The benefits are more pronounced with modern hardware. A Radeon 5870 runs this code 20x faster than a 4550. Even ignoring speedups, the code benefits users by not using CPU for intermittent texture loads (unless GPU is your bottleneck). Instead, the CPU is able to do more important tasks.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5775 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-24 04:06:03 +00:00
xsacha 21fb4cb96c Add a toggle option for OpenCL in Config (in Advanced Settings). Default is off.
git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5768 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-22 13:17:01 +00:00
xsacha 1b670a9825 New OpenCL update for DX11
Changes:
 - IA4: 2x Speed up for all hardware and ATI glitch fixed (blocky text)
 - IA8: 2x Speed up for all hardware
 - New DX11 OCL Textures: I4, I8, IA4, IA8

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5766 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-22 06:09:21 +00:00
xsacha 92c98ac5fa A new update for OpenCL.h.
Changes:
 - Strict casting as required by NVidia. Now NVidia cards should work.
 - Fixed Alpha CMPR bug.

Please tell me if you find any bugs. Current known bug is the 'Press' texture in Paper Mario that is meant to flash rainbow colours appears black. Other than that, everything should work on every videocard.


git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5759 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-21 13:09:25 +00:00
xsacha 783390539d Hi! This is my first commit so be nice :)
New OpenCL updates:
 - OpenCL bug with ATI SDK (GPU or CPU) fixed.
 - IA4 texture loop unrolled. 12x speed up on 4xxx series.
 - Completed rewriting RGB5A3 texture decode. 20% faster.
 - Redundant code removed from CMPR and RGB5A3 (Alpha, shift).
 - Made use of optimised OpenCL functions (upsample, bitselect).
 - Cleaner code.

Tested and working with DX9 plugin. DX11 plugin will NOT work due to a recent commit affecting VideoCommon. You can use this file with an older DX11 plugin (~r5730), however.

git-svn-id: https://dolphin-emu.googlecode.com/svn/trunk@5753 8ced0084-cf51-0410-be5f-012b33b47a6e
2010-06-20 16:43:21 +00:00