Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | radeonsi: decompress DCC in set_sampler_view instead of create_sampler_view (v2) | Marek Olšák | 2017-03-31 | 3 | -6/+16 |
| | | | | | | v2: don't add a new decompress helper function Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi: decompress DCC in set_framebuffer_state instead of create_surface (v2) | Marek Olšák | 2017-03-31 | 3 | -6/+49 |
| | | | | | | | | for threaded gallium, which can't use pipe_context in create_surface v2: don't add a new decompress helper function Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | tgsi: fix printing of 64-bit integer immediates | Nicolai Hähnle | 2017-03-31 | 3 | -5/+11 |
| | | | | Reviewed-by: Marek Olšák <[email protected]> | ||||
* | radeonsi: implement ARB_shader_group_vote | Nicolai Hähnle | 2017-03-31 | 2 | -1/+85 |
| | | | | Reviewed-by: Marek Olšák <[email protected]> | ||||
* | radeonsi: enable ARB_shader_clock | Nicolai Hähnle | 2017-03-31 | 1 | -1/+1 |
| | | | | | Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> | ||||
* | radeonsi: emit TGSI_OPCODE_CLOCK | Nicolai Hähnle | 2017-03-31 | 1 | -0/+21 |
| | | | | | Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> | ||||
* | tgsi: add CLOCK opcode | Ilia Mirkin | 2017-03-31 | 3 | -2/+16 |
| | | | | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> | ||||
* | gallium: add PIPE_CAP_TGSI CLOCK | Nicolai Hähnle | 2017-03-31 | 17 | -0/+17 |
| | | | | | Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> | ||||
* | r300: Fix indenting in r300_get_param() | Lyude | 2017-03-30 | 1 | -3/+3 |
| | | | | | | Signed-off-by: Lyude <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]> | ||||
* | vc4: Fix indenting in vc4_screen_get_param() | Lyude | 2017-03-30 | 1 | -3/+3 |
| | | | | | | Signed-off-by: Lyude <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]> | ||||
* | ddebug: implement clear_texture | Marek Olšák | 2017-03-30 | 2 | -0/+34 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi: fix an unused-variable warning in a release build | Marek Olšák | 2017-03-30 | 1 | -3/+1 |
| | |||||
* | vdpau: fix a maybe-uninitialized warning | Marek Olšák | 2017-03-30 | 1 | -1/+1 |
| | |||||
* | softpipe: fix a maybe-uninitialized warning | Marek Olšák | 2017-03-30 | 1 | -1/+1 |
| | | | | | | /home/marek/dev/mesa-main/src/gallium/drivers/softpipe/sp_compute.c:178: warning: 'grid_size' may be used uninitialized in this function [-Wmaybe-uninitialized] | ||||
* | gallivm: fix a maybe-uninitialized warning | Marek Olšák | 2017-03-30 | 1 | -1/+1 |
| | | | | | | | /home/marek/dev/mesa-main/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c:3598: warning: 'level' may be used uninitialized in this function [-Wmaybe-uninitialized] out1 = lp_build_cmp(&leveli_bld, PIPE_FUNC_GREATER, level, last_level); ^ | ||||
* | gallium/radeon: s/dcc_disable/disable_dcc/ | Marek Olšák | 2017-03-30 | 4 | -9/+9 |
| | | | | | | Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> | ||||
* | radeonsi: handle incompatible DCC formats in resource_copy_region | Marek Olšák | 2017-03-30 | 1 | -0/+5 |
| | | | | | | | Required because of later commits. Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> | ||||
* | radeonsi: remove a workaround for inexact *8_SNORM blits | Marek Olšák | 2017-03-30 | 1 | -3/+1 |
| | | | | | | | | All tests pass on Fiji now. This prevents DCC disablement due to incompatible DCC formats due to the fallback. Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> | ||||
* | gallium/radeon: add and use a new helper vi_dcc_enabled | Marek Olšák | 2017-03-30 | 5 | -14/+16 |
| | | | | | | Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> | ||||
* | gallium/radeon: formalize that r600_query_hw_add_result doesn't need a context | Marek Olšák | 2017-03-30 | 3 | -8/+9 |
| | | | | | | Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> | ||||
* | radeonsi: don't make a copy of pipe_index_buffer in draw_vbo | Marek Olšák | 2017-03-30 | 1 | -32/+27 |
| | | | | | | Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> | ||||
* | gallium/util: use const in u_index_modify helpers | Marek Olšák | 2017-03-30 | 2 | -6/+6 |
| | | | | | | Reviewed-by: Nicolai Hähnle <[email protected]> Tested-by: Edmondo Tommasina <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> | ||||
* | winsys/amdgpu: remove AMDGPU_INFO_NUM_EVICTIONS | Samuel Pitoiset | 2017-03-30 | 1 | -4/+0 |
| | | | | | | | | This is now exposed with libdrm_amdgpu 2.4.76. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeon/uvd: set correct vega10 db pitch alignment | Boyuan Zhang | 2017-03-30 | 1 | -4/+12 |
| | | | | | | | | Create new function to get correct alignment based on Asics, and change the corresponding decode message buffer and dpb buffer size calculations Signed-off-by: Boyuan Zhang <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | radeon/vce: add vce support for firmware 53.19.4 | Leo Liu | 2017-03-30 | 1 | -0/+6 |
| | | | | | | | v2: squashed with other similar commits Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | radeon/vce: adapt gfx9 surface to vce | Leo Liu | 2017-03-30 | 2 | -15/+51 |
| | | | | | | Signed-off-by: Leo Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | winsys/surface: add height pitch for gfx9 | Leo Liu | 2017-03-30 | 2 | -0/+2 |
| | | | | | Signed-off-by: Leo Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> | ||||
* | radeon/uvd: clear message buffer when reuse | Leo Liu | 2017-03-30 | 1 | -1/+2 |
| | | | | | | | | As required by firmware Signed-off-by: Leo Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | radeon/uvd: adapt gfx9 surface to uvd | Leo Liu | 2017-03-30 | 6 | -56/+106 |
| | | | | | | Signed-off-by: Leo Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | radeon/uvd: add uvd soc15 register | Leo Liu | 2017-03-30 | 2 | -4/+27 |
| | | | | | | Signed-off-by: Leo Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> | ||||
* | radeonsi/gfx9: disable features that don't work | Marek Olšák | 2017-03-30 | 4 | -5/+15 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: only allow GL 3.1 | Marek Olšák | 2017-03-30 | 1 | -0/+5 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: add linear address computations for texture transfers | Marek Olšák | 2017-03-30 | 1 | -20/+53 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: don't generate LS and ES states | Marek Olšák | 2017-03-30 | 1 | -24/+46 |
| | | | | | | these shaders don't exist on GFX9 Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: SPI_SHADER_USER_DATA changes | Marek Olšák | 2017-03-30 | 1 | -11/+34 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | winsys/amdgpu: set/get BO tiling flags for GFX9 | Marek Olšák | 2017-03-30 | 1 | -2/+4 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: handle pitch and offset overrides for texture_from_handle | Marek Olšák | 2017-03-30 | 1 | -11/+18 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: set/validate GFX9 BO metadata | Marek Olšák | 2017-03-30 | 2 | -1/+24 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: add radeon_surf.gfx9.surf_offset | Marek Olšák | 2017-03-30 | 5 | -1/+7 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: don't write mipmap level offsets to BO metadata | Marek Olšák | 2017-03-30 | 1 | -3/+6 |
| | | | | | | GFX9 doesn't have (usable) mipmap offsets. Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: flush CB & DB caches with an EOP TS event | Marek Olšák | 2017-03-30 | 1 | -23/+84 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: use ACQUIRE_MEM | Marek Olšák | 2017-03-30 | 1 | -6/+17 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: only use CE RAM for most-used descriptors | Marek Olšák | 2017-03-30 | 2 | -5/+23 |
| | | | | | | because the CE RAM size decreased to 4 KB. Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: emit FLUSH_DFSM where required | Marek Olšák | 2017-03-30 | 2 | -0/+18 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: emit BREAK_BATCH in emit_framebuffer_state | Marek Olšák | 2017-03-30 | 1 | -0/+5 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: fix MIP0_WIDTH & MIP0_HEIGHT for compressed texture blits | Marek Olšák | 2017-03-30 | 6 | -10/+26 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: fix textureSize/imageSize for 1D textures | Marek Olšák | 2017-03-30 | 1 | -25/+32 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: add a workaround for 1D depth textures | Marek Olšák | 2017-03-30 | 4 | -30/+86 |
| | | | | | | The same workaround is used by Vulkan. Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: enable clamping for Z UNORM formats promoted to Z32F | Marek Olšák | 2017-03-30 | 1 | -1/+11 |
| | | | | | | so that shaders don't have to do it. Reviewed-by: Nicolai Hähnle <[email protected]> | ||||
* | radeonsi/gfx9: image descriptor changes in mutable fields | Marek Olšák | 2017-03-30 | 3 | -23/+73 |
| | | | | Reviewed-by: Nicolai Hähnle <[email protected]> |