| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | r600g: fix hang on RV740 by using DX_RASTERIZATION_KILL instead of SX_MISC | Marek Olšák | 2014-04-25 | 1 | -2/+2 |
| * | r600g: fix flushing on RV670, RS780, RS880 again | Marek Olšák | 2014-04-25 | 1 | -0/+9 |
| * | r600g,radeonsi: don't skip the context flush if a fence should be returned | Marek Olšák | 2014-04-18 | 1 | -1/+1 |
| * | r600g,radeonsi: share some of gfx flush code | Marek Olšák | 2014-04-16 | 1 | -41/+3 |
| * | r600g: merge r600_flush with r600_context_flush | Marek Olšák | 2014-04-16 | 1 | -2/+29 |
| * | gallium/radeon: create and return a fence in the flush function | Marek Olšák | 2014-04-16 | 1 | -4/+5 |
| * | r600g: use more appropriate names for async DMA functions | Marek Olšák | 2014-03-20 | 1 | -6/+6 |
| * | r600g: deobfuscate async DMA code | Marek Olšák | 2014-03-20 | 1 | -7/+6 |
| * | r600g: don't flush the gfx IB explicitly before doing DMA | Marek Olšák | 2014-03-20 | 1 | -3/+0 |
| * | radeon: Move r600_need_dma_space to common code | Niels Ole Salscheider | 2014-03-20 | 1 | -11/+1 |
| * | r600g, radeonsi: fix primitives-generated query with disabled streamout | Marek Olšák | 2014-03-11 | 1 | -1/+1 |
| * | r600g,radeonsi: set priorities for relocations | Marek Olšák | 2014-03-11 | 1 | -4/+8 |
| * | r600g,radeonsi: Consolidate logic for short-circuiting flushes | Michel Dänzer | 2014-02-18 | 1 | -1/+1 |
| * | r600g: add support for multiple viewports. | Dave Airlie | 2014-02-11 | 1 | -3/+6 |
| * | r600g: initial support for geometry shaders on evergreen (v2) | Vadim Girlin | 2014-02-05 | 1 | -0/+6 |
| * | r600g,radeonsi: consolidate variables for CS tracing | Marek Olšák | 2014-01-28 | 1 | -3/+3 |
| * | r600g: move queries to drivers/radeon | Marek Olšák | 2014-01-28 | 1 | -92/+9 |
| * | r600g/compute: Emit DEALLOC_STATE on cayman after dispatching a compute shader. | Tom Stellard | 2014-01-27 | 1 | -3/+1 |
| * | r600g,radeonsi: fix initialized buffer range tracking for DMA, add comments | Marek Olšák | 2013-12-12 | 1 | -6/+12 |
| * | r600g,radeonsi: share flags has_cp_dma and has_streamout | Marek Olšák | 2013-12-12 | 1 | -1/+1 |
| * | r600g/compute: Add a work-around for flushing issues on Cayman | Tom Stellard | 2013-11-21 | 1 | -1/+3 |
| * | r600g,radeonsi: use fences provided by the winsys | Marek Olšák | 2013-10-25 | 1 | -32/+1 |
| * | Revert "r600g: only flush the caches that need to be flushed during CP DMA op... | Marek Olšák | 2013-10-06 | 1 | -120/+14 |
| * | r600g: move the low-level buffer functions for multiple rings to drivers/radeon | Marek Olšák | 2013-09-29 | 1 | -2/+2 |
| * | r600g,radeonsi: consolidate transfer, cmask, and fmask structures | Marek Olšák | 2013-09-29 | 1 | -2/+2 |
| * | r600g: fix texture buffer object cache flushing | Marek Olšák | 2013-09-25 | 1 | -1/+4 |
| * | r600g: fix constant buffer cache flushing | Marek Olšák | 2013-09-25 | 1 | -1/+5 |
| * | r600g: add support for separately allocated CMASKs | Grigori Goronzy | 2013-09-20 | 1 | -4/+14 |
| * | r600g: move streamout state to drivers/radeon | Marek Olšák | 2013-08-31 | 1 | -262/+101 |
| * | r600g: use WAIT_3D_IDLE before using CP DMA | Marek Olšák | 2013-07-18 | 1 | -0/+1 |
| * | r600g: don't use the CB/DB CP COHER logic on r6xx | Alex Deucher | 2013-07-12 | 1 | -2/+10 |
| * | r600g: improve the mechanism for recognizing an empty CS | Marek Olšák | 2013-07-08 | 1 | -3/+2 |
| * | r600g: only flush the caches that need to be flushed during CP DMA operations | Marek Olšák | 2013-07-08 | 1 | -16/+110 |
| * | r600g: split INVAL_READ_CACHES into vertex, tex, and const cache flags | Marek Olšák | 2013-07-08 | 1 | -7/+23 |
| * | r600g: adjust flush flags (v3) | Alex Deucher | 2013-07-08 | 1 | -4/+30 |
| * | r600g: don't emit surface_sync after FLUSH_AND_INV_EVENT | Alex Deucher | 2013-05-03 | 1 | -26/+0 |
| * | r600g: Don't set the dest cache bits on surface sync for R600_CONTEXT_FLUSH_A... | Tom Stellard | 2013-05-02 | 1 | -15/+13 |
| * | winsys/radeon: consolidate tracing into winsys v2 | Jerome Glisse | 2013-04-25 | 1 | -35/+1 |
| * | r600g: remove r600_hw_context_priv.h, move the stuff to r600_pipe.h | Marek Olšák | 2013-03-11 | 1 | -1/+1 |
| * | r600g: remove deprecated state management code | Marek Olšák | 2013-03-11 | 1 | -377/+0 |
| * | r600g: atomize pixel shader | Marek Olšák | 2013-03-11 | 1 | -49/+1 |
| * | r600g: atomize vertex shader | Marek Olšák | 2013-03-11 | 1 | -16/+1 |
| * | r600g: don't require dword alignment with CP DMA for buffer transfers | Marek Olšák | 2013-03-01 | 1 | -6/+1 |
| * | r600g: always map uninitialized buffer range as unsynchronized | Marek Olšák | 2013-03-01 | 1 | -0/+6 |
| * | r600g: cleanup deprecated register tables | Marek Olšák | 2013-03-01 | 1 | -3/+0 |
| * | r600g: unify vgt states | Marek Olšák | 2013-03-01 | 1 | -1/+0 |
| * | r600g: flush and invalidate htile cache when appropriate | Marek Olšák | 2013-03-01 | 1 | -0/+8 |
| * | r600g: atomize streamout enabling | Marek Olšák | 2013-03-01 | 1 | -46/+23 |
| * | r600g: add missing emit_flush for R600_CONTEXT_FLUSH_AND_INV case | Alex Deucher | 2013-02-26 | 1 | -0/+1 |
| * | r600g: synchronize streamout buffers on r6xx too (v3) | Alex Deucher | 2013-02-26 | 1 | -1/+1 |
