summaryrefslogtreecommitdiff
path: root/src/i965_render.c
AgeCommit message (Expand)Author
2008-09-12Only BO map render state if kernel mode setting is activeJesse Barnes
2008-08-14Map/unmap render state only when bo is availableJesse Barnes
2008-08-12Map gen4 render state buffer before initializingJesse Barnes
2008-08-06Revert "Switch to using a buffer object for the vertex buffer"Jesse Barnes
2008-08-05Merge branch 'drm-gem' of ssh://git.freedesktop.org/git/xorg/driver/xf86-vide...Jesse Barnes
2008-07-31Eliminate unnecessary flush from i965_compositeCarl Worth
2008-07-31Switch to using a buffer object for the vertex bufferCarl Worth
2008-07-23shut up gcc warningZhenyu Wang
2008-07-12Use up to 256 separate vertex buffersCarl Worth
2008-07-12Allow for multiple vertex buffers (though only use one for now)Carl Worth
2008-07-12Move VERTEX_BUFFERS setup from prepare_composite to compositeCarl Worth
2008-07-03Fix official name for GM45 chipsetZhenyu Wang
2008-06-17Add support for Intel 4 series chipsets.Zhenyu Wang
2008-05-08Fix i965 render getting dest format errorZhenyu Wang
2008-04-17Make the binding table and surface state be arrays to reduce syncing.Eric Anholt
2008-04-14Abstract surface setup into a separate function.Eric Anholt
2008-04-14Move the vertex buffer to the state structure as well.Eric Anholt
2008-04-14Move the binding table for 965 to the state structure.Eric Anholt
2008-04-14Move the 965 static variables local to the function they're used in.Eric Anholt
2008-04-14Make the VS unit state static for 965 render.Eric Anholt
2008-04-14Rename some variables in i965_render.c for clarity.Eric Anholt
2008-04-14Associate one sf_state object with each sf_kernelCarl Worth
2008-04-13Move wm_scratch first to meet alignment requirementsKeith Packard
2008-04-11Fix the offset to sampler default color, and a compiler warning.Eric Anholt
2008-04-11Enumerate all possible wm_state objectsCarl Worth
2008-04-11Enumerate all possible src,mask sampler state pairsCarl Worth
2008-04-10Enumerate all possible cc_state objectsCarl Worth
2008-04-10Revert "Compute pixel values directly into data port"Keith Packard
2008-04-10Compute pixel values directly into data portKeith Packard
2008-04-10Statically allocate the sampler default color, which we never change.Eric Anholt
2008-04-10Add copyright information for recent editors of this file.Eric Anholt
2008-04-10Keep static copies of the 965 render programs in video memory.Eric Anholt
2008-04-01Remove extra flushingKeith Packard
2008-04-01Add projective versions of the PS kernelsKeith Packard
2008-04-01Shrink WM thread to 32 registers and 1024 scratch space.Keith Packard
2008-03-31Fix composite with mask using new compositing thread codeKeith Packard
2008-03-31Back to new shaders, fix urb read lengthKeith Packard
2008-03-31Use m4 to clean up gen4 asm progs. Start adding projective transform support.Keith Packard
2008-03-30Reimplement wm program for nomask case to handle affine transformsKeith Packard
2008-03-21Transformed coord computed using floats. Don't move bilinear composite dst.Keith Packard
2008-03-188xx/9xx can handle textures to 2kx2k. 965 can do 8kx8kKeith Packard
2008-03-14Change OUT_RING and similar calls to OUT_BATCH for batchbuffer mergeEric Anholt
2008-03-11Remove i830+ driver's use of CARD*/INT* types for great justice.Eric Anholt
2008-03-11Silence warnings about possible uninitialize use of dst_format.Kristian Høgsberg
2008-01-09Update PIPELINE_SELECT instruction and surface state format for new chipsetZhenyu Wang
2007-08-10Tiling fixes for 965Jesse Barnes
2007-08-09i965: increase composite vertex buffer size and alignment to be safeDave Airlie
2007-08-09i965: fix memcpy of the sf_kernel when a mask is neededDave Airlie
2007-08-08Allow 965 composite acceleration to A8 destinations.Carl Worth
2007-06-27EXA: fallback mask transform on i965Wang Zhenyu