- 2812622 radv/aco: enable VK_EXT_shader_demote_to_helper_invocation by Daniel Schürmann · 5 years ago
- e01b522 radv: enable clustered reductions by Daniel Schürmann · 5 years ago
- a70a998 radv/aco: Setup alternate path in RADV to support the experimental ACO compiler by Daniel Schürmann · 5 years ago
- 93c8ebf aco: Initial commit of independent AMD compiler by Daniel Schürmann · 5 years ago
- 99cbec0 egl: check for NULL value like eglGetSyncAttribKHR does by Tapani Pälli · 5 years ago
- a16975e iris: Rework iris_update_draw_parameters to be more efficient by Kenneth Graunke · 5 years ago
- 6841f11 iris: Use state_refs for draw parameters. by Kenneth Graunke · 5 years ago
- ddd314f util/disk_cache: make use of the total job size limiting feature by Timothy Arceri · 5 years ago
- 8968850 util/u_queue: track job size and limit the size of queue growth by Timothy Arceri · 5 years ago
- a2ee29c util/disk_cache: bump thread count assigned to disk cache queue by Timothy Arceri · 5 years ago
- 8e614c7 intel/fs: fix SHADER_OPCODE_CLUSTER_BROADCAST for SIMD32 by Paulo Zanoni · 5 years ago
- c99df52 intel/fs: the maximum supported stride width is 16 by Paulo Zanoni · 5 years ago
- cebf447 intel/fs: roll the loop with the <0,1,0> additions in emit_scan() by Paulo Zanoni · 5 years ago
- d9ddf50 intel/fs: make scan/reduce work with SIMD32 when it fits 2 registers by Paulo Zanoni · 5 years ago
- 7f07046 freedreno/regs: A couple of tess updates by Kristian H. Kristensen · 5 years ago
- a2031a1 freedreno/regs: Fix CP_DRAW_INDX_OFFSET command by Kristian H. Kristensen · 5 years ago
- 2251a43 freedreno/a6xx: Write multiple regs for SP_VS_OUT_REG and SP_VS_VPC_DST_REG by Kristian H. Kristensen · 5 years ago
- cc4fe81 freedreno/a6xx: Turn on vectorize_io by Kristian H. Kristensen · 5 years ago
- 1cb9534 freedreno/a6xx: Share shader state constructor and destructor by Kristian H. Kristensen · 5 years ago
- be38480 freedreno/a6xx: Track location of gl_Position out as we link it by Kristian H. Kristensen · 5 years ago
- d38e0a6 spirv: Add missing break for capability handling by Caio Marcelo de Oliveira Filho · 5 years ago
- 3da8a8a iris: Avoid uploading SURFACE_STATE descriptors for UBOs if possible by Kenneth Graunke · 5 years ago
- 0e4a75f intel/compiler: Record whether any pull constant loads occur by Kenneth Graunke · 5 years ago
- dd83ef0 iris: Track per-stage bind history, reduce work accordingly by Kenneth Graunke · 5 years ago
- 1e7daaa iris: Don't flag IRIS_DIRTY_BINDINGS for constant usage history by Kenneth Graunke · 5 years ago
- e7db357 iris: Explicitly emit 3DSTATE_BTP_XS on Gen9 with DIRTY_CONSTANTS_XS by Kenneth Graunke · 5 years ago
- caa0aeb iris: Flag IRIS_DIRTY_BINDINGS_XS on constant buffer rebinds by Kenneth Graunke · 5 years ago
- 4b7e795 radv: Add DFSM support. by Bas Nieuwenhuizen · 5 years ago
- 0fa2740 radv: Disable dfsm by default even on Raven. by Bas Nieuwenhuizen · 5 years ago
- f2dffb3 radv: Only break batch on framebuffer change with dfsm. by Bas Nieuwenhuizen · 5 years ago
- 57e0bb8 nir/opt_if: Fix undef handling in opt_split_alu_of_phi() by Connor Abbott · 5 years ago
- a1de301 gl: drop incorrect pkg-config file for glvnd by Eric Engestrom · 5 years ago
- d9760f8 nir/opcodes: Clear variable names confusion by Andres Gomez · 5 years ago
- b3f7168 radv: never kill a NGG GS shader by Rhys Perry · 5 years ago
- 99c186f radv/gfx10: fix VK_KHR_pipeline_executable_properties with NGG GS by Samuel Pitoiset · 5 years ago
- fe7aa27 radeonsi: include drm_fourcc.h to fix the build by Marek Olšák · 5 years ago
- 00e2981 radeonsi: implement pipe_screen::resource_get_param by Marek Olšák · 5 years ago
- d307aa5 gallium: extend resource_get_param to be as capable as resource_get_handle by Marek Olšák · 5 years ago
- aae35fb ac: move ac_get_num_physical_vgprs into radeon_info by Marek Olšák · 5 years ago
- 0692ae3 ac: move ac_get_num_physical_sgprs into radeon_info by Marek Olšák · 5 years ago
- ca43006 ac: move ac_get_max_wave64_per_simd into radeon_info by Marek Olšák · 5 years ago
- deab3a2 ac: move num_sdp_interfaces into radeon_info by Marek Olšák · 5 years ago
- 2c62b46 ac: move PBB MAX_ALLOC_COUNT into radeon_info by Marek Olšák · 5 years ago
- 05da025 etnaviv: fix two-sided stencil by Jonathan Marek · 5 years ago
- 6882000 radv: fix loading 64-bit GS inputs by Samuel Pitoiset · 5 years ago
- 7999e10 tu: Set up glsl types. by Bas Nieuwenhuizen · 5 years ago
- 46b7512 radv: fix writing depth/stencil clear values to image by Samuel Pitoiset · 5 years ago
- 8a9b81a i965: support AYUV/XYUV for external import only by Haihao Xiang · 5 years ago
- 1e483a8 panfrost: Allocate tiler and scratchpad BOs per-batch by Boris Brezillon · 5 years ago
- 0eec73a panfrost: Add FBO BOs to batch->bos earlier by Boris Brezillon · 5 years ago
- 5a4d095 panfrost: Add the panfrost_batch_create_bo() helper by Boris Brezillon · 5 years ago
- 9af4aea panfrost: Don't return imported/exported BOs to the cache by Boris Brezillon · 5 years ago
- 90b8934 panfrost: Add panfrost_bo_{alloc,free}() by Boris Brezillon · 5 years ago
- cb71ae5 panfrost: Stop using panfrost_bo_release() outside of pan_bo.c by Boris Brezillon · 5 years ago
- e15ab93 panfrost: Stop passing screen around for BO operations by Boris Brezillon · 5 years ago
- 10ce751 panfrost: Don't check if BO is mmaped before calling panfrost_bo_mmap() by Boris Brezillon · 5 years ago
- a06e08d panfrost: Stop exposing panfrost_bo_cache_{fetch,put}() by Boris Brezillon · 5 years ago
- 154cb72 panfrost: Move the BO API to its own header by Boris Brezillon · 5 years ago
- 34efaaf panfrost: s/PAN_ALLOCATE_/PAN_BO_/ by Boris Brezillon · 5 years ago
- 29d0e5c panfrost: Move panfrost_bo_{reference,unreference}() to pan_bo.c by Boris Brezillon · 5 years ago
- 0500c9e panfrost: Get rid of pan_drm.c by Boris Brezillon · 5 years ago
- 1e47c3e panfrost: Stop passing has_draws to panfrost_drm_submit_vs_fs_batch() by Boris Brezillon · 5 years ago
- 07085fe panfrost: Kill a useless memset(0) in panfrost_create_context() by Boris Brezillon · 5 years ago
- 4eac1b2 panfrost: Add polygon_list to the batch BO set at allocation time by Boris Brezillon · 5 years ago
- c16fb1f panfrost: Add missing panfrost_batch_add_bo() calls by Boris Brezillon · 5 years ago
- a94d028 panfrost: Use the correct type for the bo_handle array by Boris Brezillon · 5 years ago
- 2b771b8 panfrost: Stop exposing internal panfrost_*_batch() functions by Boris Brezillon · 5 years ago
- 8d5f905 etnaviv: disable ARB_shadow by Christian Gmeiner · 5 years ago
- dcc0e23 Revert "gallium: remove PIPE_CAP_TEXTURE_SHADOW_MAP" by Christian Gmeiner · 5 years ago
- 417d602 virgl: Remove wrong EAGAIN handling for drmIoctl by Lepton Wu · 5 years ago
- f8c44e4 iris: Skip allocating a null surface when there are 0 color regions. by Kenneth Graunke · 5 years ago
- f76a724 intel/compiler: Set "Null Render Target" ex_desc bit on Gen11 by Kenneth Graunke · 5 years ago
- f5dd6df anv: enable VK_KHR_shader_float_controls and SPV_KHR_float_controls by Samuel Iglesias Gonsálvez · 6 years ago
- 9b07020 i965/fs: add support for shader float control to remove_extra_rounding_modes() by Samuel Iglesias Gonsálvez · 6 years ago
- 9bd88d1 i965/fs: set rounding mode when emitting nir_op_f2f32 or nir_op_f2f16 by Samuel Iglesias Gonsálvez · 6 years ago
- ba1e25e i965/fs: set rounding mode when emitting fadd, fmul and ffma instructions by Samuel Iglesias Gonsálvez · 6 years ago
- 9da56ff i965/fs: add emit_shader_float_controls_execution_mode() and aux functions by Samuel Iglesias Gonsálvez · 6 years ago
- 8a6507b i965/fs/generator: add new opcode to set float controls modes in control register by Samuel Iglesias Gonsálvez · 5 years ago
- 28da955 i965/fs/generator: refactor rounding mode helper in preparation for float controls by Samuel Iglesias Gonsálvez · 5 years ago
- cdace5b i965/fs/nir: add nir_op_unpack_half_2x16_split_*_flush_to_zero by Samuel Iglesias Gonsálvez · 6 years ago
- 3c474f8 intel/nir: do not apply the fsin and fcos trig workarounds for consts by Samuel Iglesias Gonsálvez · 6 years ago
- dba4d0a nir: fix fmin/fmax support for doubles by Samuel Iglesias Gonsálvez · 6 years ago
- 2abc629 nir: fix denorm flush-to-zero in sqrt's lowering at nir_lower_double_ops by Samuel Iglesias Gonsálvez · 6 years ago
- 1e0e3ed nir: fix denorms in unpack_half_1x16() by Samuel Iglesias Gonsálvez · 6 years ago
- f097247 nir/algebraic: disable inexact optimizations depending on float controls execution mode by Samuel Iglesias Gonsálvez · 6 years ago
- 3f782cd nir/algebraic: mark float optimizations returning one parameter as inexact by Andres Gomez · 6 years ago
- 5e22f3e nir/constant_expressions: mind rounding mode converting from float to float16 destinations by Samuel Iglesias Gonsálvez · 6 years ago
- ef681cf nir/opcodes: make sure f2f16_rtz and f2f16_rtne behavior is not overriden by the float controls execution mode by Samuel Iglesias Gonsálvez · 6 years ago
- 7580707 nir: mind rounding mode on fadd, fsub, fmul and fma opcodes by Samuel Iglesias Gonsálvez · 6 years ago
- 0ac07c7 nir: add support for round to zero rounding mode to nir_op_f2f32 by Samuel Iglesias Gonsálvez · 6 years ago
- 5308333 util: add fp64 -> fp32 conversion support for RTNE and RTZ rounding modes by Samuel Iglesias Gonsálvez · 6 years ago
- 733ede8 util: add float to float16 conversions with RTZ and RTNE by Samuel Iglesias Gonsálvez · 6 years ago
- 153c714 util: add softfloat functions to operate with doubles and floats by Samuel Iglesias Gonsálvez · 6 years ago
- f7d73db nir: add support for flushing to zero denorm constants by Samuel Iglesias Gonsálvez · 6 years ago
- 45668a8 nir: add auxiliary functions to detect if a mode is enabled by Samuel Iglesias Gonsálvez · 6 years ago
- 84781e1 spirv/nir: keep track of SPV_KHR_float_controls execution modes by Samuel Iglesias Gonsálvez · 6 years ago
- 420ad0a spirv: check support for SPV_KHR_float_controls capabilities by Samuel Iglesias Gonsálvez · 6 years ago
- 320c36e gallium/xlib: Fix glXMakeCurrent(dpy, None, None, ctx) by Adam Jackson · 5 years ago
- a693f98 gallium/xlib: Remove MakeCurrent_PrevContext by Adam Jackson · 5 years ago
- db8be35 gallium/xlib: Remove drawable caching from the MakeCurrent path by Adam Jackson · 5 years ago