aboutsummaryrefslogtreecommitdiffstats
path: root/src
Commit message (Expand)AuthorAgeFilesLines
* gallium: rename PIPE_RESOURCE_FLAG_ST_PRIV to FRONTEND_PRIVMarek Olšák2020-05-132-3/+3
* gallium: change comments to remove 'state tracker'Marek Olšák2020-05-1395-183/+178
* gallium: rename 'state tracker' to 'frontend'Marek Olšák2020-05-13443-162/+348
* tu: Implement fallback linear staging blit for CopyImageConnor Abbott2020-05-131-24/+173
* tu: Add noubwc debug flag to disable UBWCConnor Abbott2020-05-133-1/+4
* tu: Add a "scratch bo" allocation mechanismConnor Abbott2020-05-132-0/+74
* aco: improve phi affinities with p_split_vectorRhys Perry2020-05-131-0/+19
* aco: consider affinities when creating v_mac_f32Rhys Perry2020-05-131-2/+8
* aco: mark phi definitions as last-seen phi operandsRhys Perry2020-05-131-14/+14
* aco: fix consecutively written vgprs from vmem instructionsRhys Perry2020-05-131-10/+26
* aco: simplify consecutive ordered vmem/lds writes optimizationRhys Perry2020-05-131-10/+2
* radv: add a LLVM version string workaround for SotTR and ACOSamuel Pitoiset2020-05-133-3/+36
* turnip: use the common code for generating extensions and dispatch tablesSamuel Pitoiset2020-05-132-204/+12
* anv: use the common code for generating extensions and dispatch tablesSamuel Pitoiset2020-05-132-335/+14
* radv: use the common code for generating extensions and dispatch tablesSamuel Pitoiset2020-05-132-348/+13
* vulkan: import common code for generating extensionsSamuel Pitoiset2020-05-132-0/+370
* radv: implement VK_EXT_private_dataSamuel Pitoiset2020-05-132-0/+52
* radv: use the base object struct typesSamuel Pitoiset2020-05-1312-7/+138
* radv: use the common base object type for VkDeviceSamuel Pitoiset2020-05-1312-90/+87
* etnaviv: Disable seamless cube map on GC880Marek Vasut2020-05-133-3/+10
* freedreno/a6xx: fix max-scissor optRob Clark2020-05-132-13/+10
* freedreno/ir3/sched: try to avoid syncsRob Clark2020-05-131-13/+99
* freedreno/ir3/sched: avoid scheduling outputsRob Clark2020-05-133-22/+101
* freedreno/ir3/postsched: try to avoid (sy) syncsRob Clark2020-05-131-2/+19
* freedreno/ir3/postsched: reset sfu_delay on syncRob Clark2020-05-132-4/+33
* freedreno/ir3: limit # of tex prefetch by shader sizeRob Clark2020-05-133-1/+40
* freedreno/ir3: fix indirect cb0 load_ubo loweringRob Clark2020-05-121-2/+2
* freedreno/ir3: don't allow negative const_offsetRob Clark2020-05-121-3/+14
* pan/mdg: Fix derivative swizzleAlyssa Rosenzweig2020-05-121-4/+2
* pan/mdg: Set types for derivativesAlyssa Rosenzweig2020-05-121-0/+2
* pan/mdg: Remove texture_op_countAlyssa Rosenzweig2020-05-124-15/+0
* pan/mdg: Use analysis to set .cont/.last flagsAlyssa Rosenzweig2020-05-121-10/+2
* pan/mdg: Use the helper invo analyze passesAlyssa Rosenzweig2020-05-121-0/+5
* pan/mdg: Analyze helper execution requirementsAlyssa Rosenzweig2020-05-125-8/+99
* pan/mdg: Analyze helper invocation terminationAlyssa Rosenzweig2020-05-125-0/+112
* pan/mdg: Explain helper invocations dataflow theoryAlyssa Rosenzweig2020-05-121-0/+63
* intel/compiler: fix alignment assert in nir_emit_intrinsicArcady Goldmints-Orlov2020-05-121-1/+1
* freedreno: Skip taking the lock for resource usage if it's already flagged.Eric Anholt2020-05-121-0/+5
* freedreno: Move the resource_read early out to an inline.Eric Anholt2020-05-123-15/+20
* freedreno: Add an early out for preparing to read a resource.Eric Anholt2020-05-121-0/+7
* freedreno: Split the fd_batch_resource_used by read vs write.Eric Anholt2020-05-125-47/+70
* freedreno: Add a nohw flag to skip submitting to the kernel.Eric Anholt2020-05-123-0/+5
* turnip: Execute ir3_nir_lower_gs pass againBrian Ho2020-05-122-2/+8
* freedreno/gmem: rework gmem layout algoRob Clark2020-05-121-29/+48
* freedreno/gmem: relax alignment on a6xxRob Clark2020-05-121-0/+2
* freedreno: add gmemtoolRob Clark2020-05-122-0/+163
* freedreno/gmem: add helper to dump GMEM layoutRob Clark2020-05-121-0/+53
* freedreno/gmem: add div_align() helperRob Clark2020-05-121-5/+11
* freedreno: initialize max_scissorRob Clark2020-05-121-0/+8
* freedreno/gmem: don't assume scissor opt when estimating # of binsRob Clark2020-05-121-6/+6