mesa/mesa - The Mesa 3D Graphics Library

Age	Commit message (Expand)	Author	Files	Lines
21 hours	r600g/sb: fix incorrect assert	Vadim Girlin	1	-1/+1
21 hours	r600g/sb: relax some restrictions for FETCH instructions	Vadim Girlin	1	-9/+8
21 hours	r600g/sb: relax register allocation for compute shaders	Vadim Girlin	2	-2/+16
26 hours	r600g/sb: fix gpr array handling for compute shaders	Vadim Girlin	1	-1/+1
26 hours	r600g/sb: fix buffer overflow in sb_ostream	Vadim Girlin	1	-1/+1
41 hours	r600g/compute: Use common transfer_{map,unmap} functions for global resources	Tom Stellard	1	-44/+24
41 hours	r600g/compute: Use common transfer_{map,unmap} functions for kernel inputs	Tom Stellard	1	-4/+11
4 days	radeonsi: increase array size for shader inputs and outputs	Marek Olšák	2	-2/+4
5 days	r600g/llvm: fix cubemap lod/bias	Vincent Lejeune	1	-0/+3
5 days	r600g/llvm: Fix texelFetchOffset-2D	Vincent Lejeune	1	-0/+6
5 days	r600g/llvm: Fix cubearray textureSize	Vincent Lejeune	3	-0/+17
5 days	r600g/llvm: Factorize code loading from const buffer.	Vincent Lejeune	1	-27/+24
9 days	r600g: fixup for MSAA texture support checking	Niels Ole Salscheider	1	-1/+1
10 days	r600g: cleanup MSAA texture support checking	Marek Olšák	7	-72/+21
10 days	r600g: rewrite FMASK allocation, fix FMASK texturing with 2 and 4 samples	Marek Olšák	8	-37/+43
11 days	r600g/sb: add missing cases for ARUBA chips	Vadim Girlin	2	-0/+2
11 days	r600g/sb: get rid of standard c++ streams	Vadim Girlin	24	-545/+592
11 days	r600g/sb: separate bytecode decoding and parsing	Vadim Girlin	6	-144/+163
2013-05-10	r600g: increase array size for shader inputs and outputs	Marek Olšák	2	-2/+4
2013-05-07	r600g/sb: optimize some cases for CNDxx instructions	Vadim Girlin	2	-5/+81
2013-05-07	r600g/sb: fix memory leaks	Vadim Girlin	2	-1/+7
2013-05-07	r600g/sb: fix kcache handling on r6xx	Vadim Girlin	1	-1/+5
2013-05-06	r600g/llvm: Parse config values in register / value pairs	Tom Stellard	2	-4/+31
2013-05-06	r600g/llvm: Don't feed LLVM output through r600_bytecode_build()	Tom Stellard	4	-395/+21
2013-05-06	r600g/llvm: Don't emit CALL_FS for vertex shaders	Tom Stellard	2	-8/+10
2013-05-06	r600g/llvm: Update radeon family mappings for LLVM backend	Tom Stellard	2	-4/+8
2013-05-04	r600g/llvm: Undefines unrequired texture coord values	Vincent Lejeune	1	-1/+28
2013-05-03	r600g: Correctly initialize the shader key, v2	Lauri Kasanen	1	-1/+2
2013-05-03	r600g: don't emit surface_sync after FLUSH_AND_INV_EVENT	Alex Deucher	1	-26/+0
2013-05-03	r600g/sb: zero-initialize bytecode structs	Vadim Girlin	2	-3/+6
2013-05-03	r600g/sb: fix constant propagation in gvn pass	Vadim Girlin	1	-1/+2
2013-05-03	r600g/sb: don't run unnecessary passes	Vadim Girlin	1	-3/+0
2013-05-03	r600g/sb: silence warnings with gcc 4.8	Vadim Girlin	2	-14/+15
2013-05-03	r600g/sb: fix handling of interference sets in post_scheduler	Vadim Girlin	2	-8/+8
2013-05-03	r600g/sb: fix allocation of indirectly addressed input arrays	Vadim Girlin	4	-10/+25
2013-05-03	r600g/sb: use hex instead of binary constants	Vadim Girlin	5	-15/+15
2013-05-03	r600g: use old shader disassembler by default	Vadim Girlin	4	-19/+18
2013-05-02	r600g: Don't set the dest cache bits on surface sync for R600_CONTEXT_FLUSH_A...	Tom Stellard	1	-15/+13
2013-05-02	r600g/compute: Fix build error in debug code	Tom Stellard	1	-1/+1
2013-04-30	r600g/sb: remove unused code	Vadim Girlin	2	-34/+0
2013-04-30	r600g/sb: collect shader statistics	Vadim Girlin	5	-8/+162
2013-04-30	r600g/sb: don't propagate dead values in GVN pass	Vadim Girlin	1	-0/+3
2013-04-30	r600g/sb: use simple heuristic to limit register pressure	Vadim Girlin	2	-3/+33
2013-04-30	r600g/sb: improve error checking in ra_coalesce pass	Vadim Girlin	2	-14/+27
2013-04-30	r600g/sb: use source bytecode in case of optimization errors	Vadim Girlin	5	-11/+25
2013-04-30	r600g: plug in optimizing backend	Vadim Girlin	8	-3/+155
2013-04-30	r600g/sb: initial commit of the optimizing shader backend	Vadim Girlin	35	-0/+17498
2013-04-30	r600g: use enum type for domains field in struct r600_resource	Vadim Girlin	1	-1/+1
2013-04-30	r600g: add new flags to isa instruction tables	Vadim Girlin	1	-116/+127
2013-04-30	r600g: always create reverse lookup isa tables	Vadim Girlin	1	-10/+2