mesa.git - Unnamed repository; edit this file 'description' to name the repository.

	Commit message (Collapse)	Author	Age	Files	Lines
*	xlib: Complete llvmpipe integration.	José Fonseca	2009-08-29	4	-3/+12
\|
*	llvmpipe: SoA blending.	José Fonseca	2009-08-29	6	-145/+635
\| \| \| \|	Throughput seems to be 4x higher.
*	util: Fix blend factor dumping.	José Fonseca	2009-08-29	1	-0/+2
\|
*	llvmpipe: Update blending test.	José Fonseca	2009-08-29	1	-15/+8
\|
*	llvmpipe: Handle more conversions.	José Fonseca	2009-08-29	3	-73/+100
\| \| \| \|	Not all successfully yet though..
*	llvmpipe: Use full set of sse4 min/max intrinsics.	José Fonseca	2009-08-29	1	-2/+20
\|
*	llvmpipe: Fix one const generation for some signed integers.	José Fonseca	2009-08-29	1	-1/+7
\|
*	llvmpipe: Allow floating types without sign.	José Fonseca	2009-08-29	2	-2/+3
\| \| \| \|	With the meaning that all values are assumed to be positive.
*	llvmpipe: Centralize lp_build_context initialization.	José Fonseca	2009-08-29	3	-5/+20
\|
*	llvmpipe: Normalize the cycles with the number of channel.	José Fonseca	2009-08-29	2	-7/+5
\| \| \| \|	So that we have a comparable number for different formats.
*	llvmpipe: Handle ubyte -> float conversion too.	José Fonseca	2009-08-29	3	-30/+196
\|
*	llvmpipe: Make lp_const_offset visible.	José Fonseca	2009-08-29	2	-1/+5
\|
*	llvmpipe: Only get the preprocessor flags from llvm-config.	José Fonseca	2009-08-29	1	-1/+1
\| \| \| \|	Otherwise we get -O2 optimization flag, preventing proper debugging.
*	llvmpipe: Bootstrap type conversions.	José Fonseca	2009-08-29	4	-0/+642
\|
*	llvmpipe: Use same type for reference vectors.	José Fonseca	2009-08-29	3	-9/+12
\|
*	llvmpipe: Fix floating point const scale factor.	José Fonseca	2009-08-29	1	-1/+3
\|
*	llvmpipe: Factor out shared test code into a separate module.	José Fonseca	2009-08-29	5	-184/+598
\|
*	llvmpipe: Cleanup constant helpers.	José Fonseca	2009-08-29	5	-40/+141
\|
*	llvmpipe: Move intrinsic helpers to a separate module.	José Fonseca	2009-08-29	4	-42/+145
\|
*	llvmpipe: Collect richer blend data.	José Fonseca	2009-08-29	1	-1/+10
\|
*	llvmpipe: Some notes about PSHUF.	José Fonseca	2009-08-29	1	-4/+7
\|
*	llvmpipe: Optimize blend swizzles by using bitmasks instead of shuffles for ↵	José Fonseca	2009-08-29	6	-55/+416
\| \| \| \|	ubytes.
*	llvmpipe: Write data to a tsv file for posterior analysis.	José Fonseca	2009-08-29	1	-99/+170
\|
*	llvmpipe: Move p_build_context to lp_bld_type.h	José Fonseca	2009-08-29	2	-26/+27
\| \| \| \|	As it will be shared with more modules.
*	util: New file dedicated to dump state in human/machine readable format.	José Fonseca	2009-08-29	4	-0/+225
\|
*	llvmpipe: Don't use llvm.readcyclecounter.	José Fonseca	2009-08-29	1	-27/+24
\| \| \| \| \|	LLVM during optimization reorders the rdtsc instructions next to each other, which makes it pretty useless.
*	llvmpipe: Separate constant building.	José Fonseca	2009-08-29	6	-135/+226
\|
*	llvmpipe: Move type support functions into a separate file.	José Fonseca	2009-08-29	7	-204/+278
\|
*	llvmpipe: Measure the number of cycles taken for blending.	José Fonseca	2009-08-29	1	-20/+90
\|
*	llvmpipe: Minor comments / debug mnemonics.	José Fonseca	2009-08-29	1	-0/+11
\|
*	llvmpipe: Optimize away min/max with equal operands.	José Fonseca	2009-08-29	1	-0/+14
\|
*	llvmpipe: Improve generated 8bit blending code.	José Fonseca	2009-08-29	1	-0/+29
\|
*	llvmpipe: Get blending of normalized 8bit unsigned integers working.	José Fonseca	2009-08-29	2	-115/+347
\|
*	llvmpipe: Specialize arithmetic operations.	José Fonseca	2009-08-29	4	-244/+420
\|
*	llvmpipe: Introduce a custom typing system.	José Fonseca	2009-08-29	5	-42/+228
\| \| \| \| \|	Straightforward representation of floating-point/fixed-point/integer, normalized/scaled, signed/unsigned SIMD vector types.
*	llvmpipe: Avoid C99-isms.	José Fonseca	2009-08-29	2	-23/+21
\|
*	llvmpipe: Factor out intrisic calling code into a reusable function.	José Fonseca	2009-08-29	1	-40/+31
\|
*	llvmpipe: Cleanup test programs.	José Fonseca	2009-08-29	3	-63/+83
\|
*	llvmpipe: Blending.	José Fonseca	2009-08-29	5	-2/+965
\| \| \| \|	The code
*	llvmpipe: Arithmetic helpers.	José Fonseca	2009-08-29	4	-0/+420
\|
*	llvmpipe: fastpath for interpolated z16 less depthtesting	Keith Whitwell	2009-08-29	1	-4/+139
\| \| \| \| \| \| \|	Because this is interpolated (ie. early) depth, we can build in an assumption about the quads emitted by triangle setup, ie that they are actually linear spans. Interpolate z over those spans in z16 format to save on math & conversion.
*	llvmpipe: cope with nr_cbufs == 0	Keith Whitwell	2009-08-29	1	-3/+13
\| \| \| \|	Disable blend code when no color buffer
*	llvmpipe: Translate logicops.	José Fonseca	2009-08-29	4	-0/+115
\|
*	llvmpipe: Separate pixel packing/unpacking from loading/storing.	José Fonseca	2009-08-29	8	-44/+185
\|
*	xlib: Integrate with llvmpipe.	José Fonseca	2009-08-29	1	-0/+513
\| \| \| \|	Actually, the makefile/sconscript changes were already commit by mistake.
*	llvmpipe: Adjust for pixel layout changes.	José Fonseca	2009-08-29	3	-2/+4
\|
*	util: Make pixel format layout more meaningful.	José Fonseca	2009-08-29	3	-109/+114
\| \| \| \| \|	Namelly, explicitly distinguish formats coded by arithmetic manipulation, from formats layed out in array.
*	util: Don't commit u_format_table.c	José Fonseca	2009-08-29	2	-1925/+1
\| \| \| \|	At least not until stabilizes, to reduce noise.
*	llvmpipe: Fix typo in copyright.	José Fonseca	2009-08-29	5	-5/+5
\|
*	llvmpipe: Add test cases for pixels.	José Fonseca	2009-08-29	1	-42/+95
\| \| \| \|	Actually some of this test cases need more testing...