| Commit message (Expand) | Author | Age | Files | Lines |
* | radv: add a compute shader implementation for buffer to image | Dave Airlie | 2016-12-18 | 3 | -6/+325 |
* | radv: Use correct pitch for views with different block size. | Bas Nieuwenhuizen | 2016-12-18 | 1 | -1/+4 |
* | radv: Store queue family in command buffers. | Dave Airlie | 2016-12-18 | 2 | -2/+35 |
* | radv: start fixing up queue allocate for multiple queues | Dave Airlie | 2016-12-18 | 2 | -15/+53 |
* | radv/winsys: start adding support for DMA/compute queue | Dave Airlie | 2016-12-18 | 1 | -5/+20 |
* | radv/winsys: Expose number of compute/dma rings. | Bas Nieuwenhuizen | 2016-12-18 | 2 | -2/+15 |
* | freedreno/a5xx: border color support | Rob Clark | 2016-12-18 | 1 | -3/+160 |
* | freedreno/a5xx: use MRT0 to import linear zs | Rob Clark | 2016-12-18 | 1 | -5/+20 |
* | freedreno: fdN_gmem_restore_format() is not gen specific | Rob Clark | 2016-12-18 | 8 | -50/+25 |
* | freedreno/a5xx: cargo-cult end-batch sequence more faithfully | Rob Clark | 2016-12-18 | 4 | -4/+39 |
* | freedreno/a5xx: misc fix | Rob Clark | 2016-12-18 | 1 | -1/+1 |
* | freedreno/a5xx: fix (at least some) vtx formats | Rob Clark | 2016-12-18 | 1 | -1/+1 |
* | freedreno/a5xx: more formats | Rob Clark | 2016-12-18 | 1 | -25/+25 |
* | freedreno/a5xx: fixup caps | Rob Clark | 2016-12-18 | 2 | -6/+11 |
* | freedreno/a5xx: fix random faults on first sysmem draw | Rob Clark | 2016-12-18 | 1 | -0/+3 |
* | freedreno: update generated headers | Rob Clark | 2016-12-18 | 6 | -17/+80 |
* | freedreno/a5xx: fix stride/size for mem->gmem blits | Rob Clark | 2016-12-18 | 1 | -5/+7 |
* | radv/winsys: consolidate request->fence code | Dave Airlie | 2016-12-17 | 1 | -22/+19 |
* | radv: handle fence allocation failing | Dave Airlie | 2016-12-17 | 1 | -1/+4 |
* | radv: Don't bail out on pipeline create failure. | Bas Nieuwenhuizen | 2016-12-17 | 1 | -21/+17 |
* | spirv/nir: add support for ImageGatherExtended | Ilia Mirkin | 2016-12-16 | 1 | -7/+69 |
* | anv: Fix uniform and storage buffer offset alignment limits. | Francisco Jerez | 2016-12-16 | 1 | -2/+2 |
* | nir: Remove nir_array from lower_locals_to_regs | Thomas Helland | 2016-12-16 | 1 | -9/+0 |
* | swr: Implement fence attached work queues for deferred deletion. | Bruce Cherniak | 2016-12-16 | 9 | -54/+255 |
* | nir: Turn imov/fmov of undef into undef | Timothy Arceri | 2016-12-16 | 1 | -6/+6 |
* | egl/x11: cleanup init code | Eric Engestrom | 2016-12-15 | 1 | -14/+10 |
* | nir/lower_tex: fix number of components in replace_gradient_with_lod() | Iago Toral Quiroga | 2016-12-15 | 1 | -1/+2 |
* | Revert "nir: Turn imov/fmov of undef into undef." | Timothy Arceri | 2016-12-15 | 1 | -3/+1 |
* | i965/vec4: Fix TCS output reads with non-zero component qualifiers. | Kenneth Graunke | 2016-12-14 | 1 | -5/+5 |
* | i965/disasm: Decode dataport constant cache control fields. | Francisco Jerez | 2016-12-14 | 1 | -0/+1 |
* | i965/fs: Remove the FS_OPCODE_SET_SIMD4X2_OFFSET virtual opcode. | Francisco Jerez | 2016-12-14 | 4 | -33/+0 |
* | i965/fs: Drop useless access mode override from pull constant generator code. | Francisco Jerez | 2016-12-14 | 1 | -2/+0 |
* | i965/fs: Fetch one cacheline of pull constants at a time. | Francisco Jerez | 2016-12-14 | 2 | -19/+18 |
* | i965/fs: Expose arbitrary pull constant load sizes to the IR. | Francisco Jerez | 2016-12-14 | 4 | -27/+26 |
* | i965: Factor out oword block read and write message control calculation. | Francisco Jerez | 2016-12-14 | 2 | -12/+8 |
* | i965/fs: Switch to the constant cache for uniform pull constants. | Francisco Jerez | 2016-12-14 | 4 | -91/+36 |
* | i965: Let the caller of brw_set_dp_write/read_message control the target cache. | Francisco Jerez | 2016-12-14 | 3 | -42/+43 |
* | i965/gen6+: Invalidate constant cache on brw_emit_mi_flush(). | Francisco Jerez | 2016-12-14 | 1 | -0/+1 |
* | genxml: Make Gen8 3DSTATE_DS SIMD8 enable work like Gen9+. | Kenneth Graunke | 2016-12-14 | 1 | -1/+4 |
* | genxml: Rename "DS Function Enable" to "Function Enable". | Kenneth Graunke | 2016-12-14 | 2 | -2/+2 |
* | anv: Reject VkMemoryAllocateInfo::allocationSize == 0 | Chad Versace | 2016-12-14 | 1 | -5/+2 |
* | egl: Fix crashes in eglCreate*Surface() | Chad Versace | 2016-12-14 | 1 | -2/+2 |
* | i965/miptree: Use intel_miptree_copy for maps | Jason Ekstrand | 2016-12-13 | 1 | -12/+8 |
* | i965/blit: Fix the src dimension sanity check in miptree_copy | Jason Ekstrand | 2016-12-13 | 1 | -2/+10 |
* | main: add INTEL_conservative_rasterization enum query support | Lionel Landwerlin | 2016-12-13 | 2 | -0/+8 |
* | glapi: add missing INTEL_conservative_rasterization | Lionel Landwerlin | 2016-12-13 | 1 | -0/+4 |
* | extensions: update INTEL_conservative_rasterization dependencies | Lionel Landwerlin | 2016-12-13 | 1 | -1/+1 |
* | main: don't error when enabling conservative rasterization on gles | Lionel Landwerlin | 2016-12-13 | 1 | -1/+1 |
* | main: use new driver flag for conservative rasterization state | Lionel Landwerlin | 2016-12-13 | 6 | -7/+19 |
* | nir/lower_tex: lower gradients on shadow cube maps if lower_txd_shadow is set | Iago Toral Quiroga | 2016-12-13 | 1 | -2/+4 |