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

	Commit message (Expand)	Author	Age	Files	Lines
*	various: Fix missing DumpModule with recent LLVM.	Bas Nieuwenhuizen	2017-01-29	1	-3/+3
*	radeonsi: don't declare LDS in TES	Marek Olšák	2017-01-23	1	-2/+1
*	radeonsi: for the tess barrier, only use emit_waitcnt on SI and LLVM 3.9+	Marek Olšák	2017-01-17	1	-2/+5
*	radeonsi: implement GL_FIXED vertex format	Marek Olšák	2017-01-16	1	-2/+12
*	radeonsi: implement 32-bit SNORM/UNORM/SSCALED/USCALED vertex formats	Marek Olšák	2017-01-16	1	-1/+51
*	radeonsi: make fix_fetch 64-bit	Marek Olšák	2017-01-16	1	-2/+2
*	radeonsi: replace si_shader_context::soa by bld_base	Samuel Pitoiset	2017-01-13	1	-58/+54
*	radeonsi: replace ctx->soa.outputs by ctx->outputs	Samuel Pitoiset	2017-01-13	1	-11/+9
*	radeonsi: move si_shader_context::soa::addr to si_shader_context	Samuel Pitoiset	2017-01-13	1	-2/+2
*	radeonsi: allocate the array of immediates dynamically	Samuel Pitoiset	2017-01-13	1	-8/+8
*	amd/common: unify cube map coordinate handling between radeonsi and radv	Nicolai Hähnle	2017-01-13	1	-1/+5
*	radeonsi: num_records is in units of stride for swizzled buffers even on VI	Nicolai Hähnle	2017-01-12	1	-2/+0
*	radeonsi: cleanly communicate whether si_shader_dump should check R600_DEBUG	Marek Olšák	2017-01-09	1	-9/+11
*	radeonsi: unduplicate VS color export code	Marek Olšák	2017-01-06	1	-9/+2
*	radeonsi: clean up more HAVE_LLVM #ifdefs	Marek Olšák	2017-01-06	1	-8/+11
*	radeonsi: shrink each vertex stream to the actually required size	Nicolai Hähnle	2016-12-12	1	-10/+18
*	radeonsi: use a single descriptor for the GSVS ring	Nicolai Hähnle	2016-12-12	1	-8/+65
*	radeonsi: pack GS output components for each vertex stream contiguously	Nicolai Hähnle	2016-12-12	1	-3/+8
*	radeonsi: do not write non-existent components through the GSVS ring	Nicolai Hähnle	2016-12-12	1	-2/+4
*	radeonsi: only write values belonging to the stream when emitting GS vertex	Nicolai Hähnle	2016-12-12	1	-0/+3
*	radeonsi: generate an explicit switch instruction over vertex streams	Nicolai Hähnle	2016-12-12	1	-8/+13
*	radeonsi: fetch only outputs of current vertex stream from the GSVS ring	Nicolai Hähnle	2016-12-12	1	-16/+25
*	radeonsi: only export from GS copy shader for vertex stream 0	Nicolai Hähnle	2016-12-12	1	-12/+19
*	radeonsi: do not export VS outputs from vertex streams != 0	Nicolai Hähnle	2016-12-12	1	-0/+6
*	radeonsi: pull iteration over vertex streams into GS copy shader logic	Nicolai Hähnle	2016-12-12	1	-25/+37
*	radeonsi: group streamout writes by vertex stream	Nicolai Hähnle	2016-12-12	1	-10/+22
*	radeonsi: load the streamout buf descriptors closer to their use	Nicolai Hähnle	2016-12-12	1	-14/+11
*	radeonsi: extract writing of a single streamout output	Nicolai Hähnle	2016-12-12	1	-39/+52
*	radeonsi: separate the call to si_llvm_emit_streamout from exports	Nicolai Hähnle	2016-12-12	1	-4/+4
*	radeonsi: plumb the output vertex_stream through to si_shader_output_values	Nicolai Hähnle	2016-12-12	1	-1/+9
*	radeonsi: rename members of si_shader_output_values	Nicolai Hähnle	2016-12-12	1	-8/+8
*	radeonsi: fix an off-by-one error in the bounds check for max_vertices	Nicolai Hähnle	2016-12-12	1	-1/+1
*	radeonsi: do not kill GS with memory writes	Nicolai Hähnle	2016-12-12	1	-8/+22
*	radeonsi: Fix typo: "llvm.fs.interp" => "llvm.SI.fs.interp"	Michel Dänzer	2016-12-08	1	-1/+1
*	radeonsi: wait for outstanding LDS instructions in memory barriers if needed	Marek Olšák	2016-12-07	1	-1/+17
*	radeonsi: wait for outstanding memory instructions in TCS barriers	Marek Olšák	2016-12-07	1	-1/+5
*	radeonsi: allow specifying simm16 of emit_waitcnt at call sites	Marek Olšák	2016-12-07	1	-5/+7
*	radeonsi: take LDS into account for compute shader occupancy stats	Marek Olšák	2016-12-07	1	-11/+18
*	radeonsi: fix isolines tess factor writes to control ring	Nicolai Hähnle	2016-12-07	1	-4/+12
*	radeonsi: Use amdgcn intrinsics for fs interpolation	Tom Stellard	2016-12-07	1	-54/+142
*	radeonsi: don't apply the Z export bug workaround to Hainan	Marek Olšák	2016-12-01	1	-2/+3
*	radeonsi: apply a TC L1 write corruption workaround for SI	Marek Olšák	2016-12-01	1	-11/+23
*	radeonsi: apply a multi-wave workgroup SPI bug workaround to affected CIK chips	Marek Olšák	2016-12-01	1	-2/+22
*	radeonsi: consolidate max-work-group-size computation	Marek Olšák	2016-12-01	1	-24/+19
*	radeonsi: don't fetch 8 dwords for samplerBuffer and imageBuffer	Marek Olšák	2016-11-29	1	-51/+43
*	radeonsi: count and report temp arrays in scratch separately	Marek Olšák	2016-11-29	1	-4/+39
*	radeonsi: don't try to eliminate trivial VS outputs for PS and CS	Marek Olšák	2016-11-29	1	-1/+4
*	radeonsi: print new opt flags in si_dump_shader_key	Marek Olšák	2016-11-23	1	-0/+9
*	radeonsi: eliminate VS outputs that aren't used by PS at runtime	Marek Olšák	2016-11-21	1	-1/+25
*	radeonsi: record information about all written and read varyings	Marek Olšák	2016-11-21	1	-0/+22