summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers
Commit message (Collapse)AuthorAgeFilesLines
* ilo: initialize dirty flags in ilo_init_states()Chia-I Wu2013-06-132-2/+2
| | | | | Now that we have a function to initialize states, initialize dirty flags there too.
* ilo: re-emit states that involve resourcesChia-I Wu2013-06-134-21/+23
| | | | | | | Even with hardware contexts, since we do not pin resources, we have to re-emit the states so that the resources are referenced (by cp->bo) and their offsets are updated in case they are moved. This also allows us to elimiate cp flush in is_bo_busy().
* ilo: fix for util_blitter_clear() changesChia-I Wu2013-06-131-4/+1
| | | | It has been broken since 17350ea979b883662573dac136cd9efb49938210.
* r600g: upsample and downsample MSAA resources for transfersMarek Olšák2013-06-131-79/+141
| | | | | | | | | | | We did downsample (=resolve) MSAA resources to make ReadPixels work with MSAA GLX visuals, which was enough for read-only color-only transfers. This commit makes write color transfers and depth-stencil transfers work in a similar manner. It does downsampling in transfer_map and upsampling in transfer_unmap. Reviewed-by: Brian Paul <[email protected]>
* gallium/u_blitter: make clearing independent of the colorbuffer formatMarek Olšák2013-06-133-6/+3
| | | | | | | There isn't any difference between 32_FLOAT and 32_*INT in vertex fetching. Both of them don't do any format conversion. Reviewed-by: Brian Paul <[email protected]>
* gallium/u_blitter: make clearing independent of the number of bound colorbuffersMarek Olšák2013-06-133-3/+2
| | | | | | We can use the fragment shader TGSI property WRITES_ALL_CBUFS. Reviewed-by: Brian Paul <[email protected]>
* util: new util_fill_box helperRoland Scheidegger2013-06-131-29/+25
| | | | | | | | | Use new util_fill_box helper for util_clear_render_target. (Also fix off-by-one map error.) v2: handle non-zero z correctly in new helper Reviewed-by: Jose Fonseca <[email protected]>
* ilo: update winsys interfaceChia-I Wu2013-06-121-7/+14
| | | | | | The motivation is to kill tiling and pitch in struct intel_bo. That requires us to make tiling and pitch not queryable, and be passed around as function parameters.
* ilo: get rid of function tables in winsysChia-I Wu2013-06-1214-90/+88
| | | | | We are moving toward making struct intel_bo alias drm_intel_bo. As a first step, we cannot have function tables.
* ilo: access bo size directlyChia-I Wu2013-06-121-2/+2
| | | | buf->bo_size is readily avaiable, no need to go via buf->bo->get_size().
* ilo: remove unnecessary tex_set_bo/buf_set_boChia-I Wu2013-06-121-42/+18
| | | | Merge the bodies to tex_create_bo/buf_create_bo respectively.
* nvc0: fix up video buffer alignment requirementsMaarten Lankhorst2013-06-081-5/+3
| | | | Signed-off-by: Maarten Lankhorst <[email protected]>
* freedreno: better scissor fixRob Clark2013-06-085-28/+43
| | | | | | Actually respect rasterizer state. Signed-off-by: Rob Clark <[email protected]>
* freedreno: gmem bypassRob Clark2013-06-087-30/+168
| | | | | | | | | | | | | The GPU (at least a3xx, but I think also a2xx) can render directly to memory, bypassing tiling. Although it can't do this if blend, depth, and a few other features of the pipeline are enabled. This direct memory mode can be faster for some sorts of operations, such as simple blits. In particular, this significantly speeds up XA by avoiding to pull the entire dest pixmap into GMEM, render tiles, and write it all back out again. This should also speed up resource copy-region and blit. Signed-off-by: Rob Clark <[email protected]>
* freedreno: add a3xx supportRob Clark2013-06-0835-3/+8955
| | | | | | | | | | | | | | | | | | | | The adreno a3xx GPU is found in newer snapdragon devices, such as the nexus4. The a3xx is GLESv3 and OpenCL capable, although that is not enabled yet in gallium. Compared to a2xx, it introduces an entirely new unified shader ISA, and re-shuffles all or nearly all of the registers. The good news is that (for the most part) the registers are more orthogonal, not combining unrelated state in a single register. And that there is a lot more flexibility, so we don't need to patch and re-emit the shader like we did on a2xx. The shader compiler is currently quite dumb, there would be a lot of room for improvement with an optimizing pass. Despite that, with the a320 in my nexus4 it seems to be ~2-3x faster compared to the a220 in my HP touchpad. Signed-off-by: Rob Clark <[email protected]>
* freedreno: prepare for a3xxRob Clark2013-06-0849-2008/+2798
| | | | | | | | Split the parts that are specific to adreno a2xx series GPUs from the parts that will be in common with a3xx, so that a3xx support can be added more cleanly. Signed-off-by: Rob Clark <[email protected]>
* llvmpipe: move create_surface/destroy_surface functions to lp_surface.cRoland Scheidegger2013-06-072-59/+59
| | | | | | | Believe it or not but these two are actually the first two functions which really belong in this file nowadays. Reviewed-by: Brian Paul <[email protected]>
* llvmpipe: add support for layered renderingRoland Scheidegger2013-06-0715-110/+195
| | | | | | | | | | | | | | | | Mostly just make sure the layer parameter gets passed through to the right places (and get clamped, can do this at setup time), fix up clears to clear all layers and disable opaque optimization. Luckily don't need to touch the jitted code. (Clears invoked via pipe's clear_render_target method will not work however since the pipe_util_clear function used for it doesn't handle clearing multiple layers yet.) v2: per Brian's suggestion, prettify var initialization and add some comments, add assertion for impossible layer specification for surface. Reviewed-by: Brian Paul <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* ilo: fix textureSize() for single-layered array texturesChia-I Wu2013-06-081-2/+18
| | | | | We returned 0 instead of 1 for the number of layers when the array texutre is single-layered. This fixed it on GEN7+.
* tgsi: replace tgsi_file_names tgsi_file_names[] with tgsi_file_name() functionBrian Paul2013-06-072-4/+4
| | | | | | | | | This change came from the discovery that the STATIC_ASSERT to check that the number of register file strings didn't actually work. Similar changes could be made for the other string arrays in tgsi_string.c Reviewed-by: Jose Fonseca <[email protected]>
* ilo: advertise PIPE_CAP_CUBE_MAP_ARRAYChia-I Wu2013-06-071-2/+1
| | | | | It was supported but not advertised. Also remove TODO tag for PIPE_CAP_MIN_MAP_BUFFER_ALIGNMENT, as it is not a TODO.
* ilo: add support for TEX2/TXB2/TXL2 in fsChia-I Wu2013-06-071-3/+3
| | | | They were already supported, just being rejected in the TGSI translator.
* ilo: use slab allocator for transfersChia-I Wu2013-06-074-28/+39
| | | | | Slab allocator is perfect for transfer. Improved OpenArena performance by 1% with several casual runs.
* ilo: clean up states upon context destroyChia-I Wu2013-06-071-0/+38
| | | | We need to unreference resources that we referenced.
* ilo: unmap cp bo before destroying itChia-I Wu2013-06-071-1/+6
| | | | | The BOs are mapped in their entire life times for the chipsets we support so do not forget to unmap it.
* ilo: enable bo reuseChia-I Wu2013-06-071-0/+2
| | | | This magical line of code must have got lost at some point in the history...
* ilo: construct 3DSTATE_SF in create_rasterizer_state()Chia-I Wu2013-06-077-164/+194
| | | | Add ilo_rasterizer_sf and initialize it in create_rasterizer_state().
* ilo: construct 3DSTATE_CLIP in create_rasterizer_state()Chia-I Wu2013-06-075-50/+86
| | | | Add ilo_rasterizer_clip and initialize it in create_rasterizer_state().
* ilo: use emit_SURFACE_STATE() for render targetsChia-I Wu2013-06-079-127/+52
| | | | | | Introduce ilo_surface_cso and initialize it in create_surface(). With the change, we can emit SURFACE_STATE directly from the CSO and remove emit_surf_SURFACE_STATE(). We do not deal with depth/stencil surfaces yet.
* ilo: use emit_SURFACE_STATE() for constant buffersChia-I Wu2013-06-079-70/+26
| | | | | | Introduce ilo_cbuf_cso and initialize it in set_constant_buffer(). As ilo_view_surface is embedded in ilo_cbuf_cso, switch to emit_SURFACE_STATE() for constant buffers and remove emit_cbuf_SURFACE_STATE().
* ilo: add emit_SURFACE_STATE() for sampler viewsChia-I Wu2013-06-0710-99/+69
| | | | | | Introduce ilo_view_cso and initialize it in create_sampler_view(). Add emit_SURFACE_STATE() to GPE, which can emit SURFACE_STATE from ilo_view_surface.
* ilo: add ilo_view_surface for SURFACE_STATEChia-I Wu2013-06-073-125/+268
| | | | Define struct ilo_view_surface for SURFACE_STATE construction and emission.
* ilo: convert generic depth-stencil-alpha pipe state to ilo pipe stateCourtney Goeltzenleuchter2013-06-076-21/+51
| | | | | | | | | Moving the work to create time reduces the work at emit time. Saves time overall as create work is only done once. Fix compiler warning in gen7_pipeline_sol. [olv: remember pipe_alpha_state instead of pipe_depth_stencil_alpha_state in ilo_dsa_state]
* ilo: introduce vertex element CSOChia-I Wu2013-06-076-119/+227
| | | | | | | Introduce ilo_ve_cso and initialize it in create_vertex_elements_state(). This commit goes a step further by setting up mappings from HW VB to PIPE VB, which we failed to do previously. That allows us to support instanced rendering.
* ilo: simplify emit_3DSTATE_DEPTH_BUFFER()Chia-I Wu2013-06-076-63/+19
| | | | | | Remove hiz and dsa from the parameters. We would know whether HiZ buffer exists from ilo_texture once it is supported. DSA state should not affect 3DSTATE_DEPTH_BUFFER.
* ilo: introduce blend CSOChia-I Wu2013-06-076-97/+183
| | | | | Introduce ilo_blend_cso and initialize it in create_blend_state(). This saves us from having to construct hardware blend states in draw_vbo().
* ilo: introduce sampler CSOChia-I Wu2013-06-078-371/+447
| | | | | | Introduce ilo_sampler_cso and initialize it in create_sampler_state(). This saves us from having to perform CPU-intensive calculations to construct hardware sampler states in draw_vbo().
* ilo: construct SCISSOR_RECT in set_scissor_states()Chia-I Wu2013-06-077-26/+92
| | | | | | This allows us to memcpy() the state in draw_vbo(). Add ilo_init_states() and ilo_cleanup_states() that are called when contexts are created and destroyed respectively, and properly set the initial scissor state in ilo_init_states().
* ilo: introduce viewport CSOChia-I Wu2013-06-078-197/+197
| | | | | | Introduce ilo_viewport_cso and initialize it in set_viewport_states(). This saves us from having to perform CPU-intensive calculations to construct hardware viewport states in draw_vbo().
* ilo: switch to ilo states for shaders and resourcesChia-I Wu2013-06-077-114/+114
| | | | | | | | | | | | Define and use struct ilo_sampler_state; struct ilo_view_state; struct ilo_cbuf_state; struct ilo_resource_state; struct ilo_global_binding; in ilo_context.
* ilo: switch to ilo states for CC stageChia-I Wu2013-06-079-107/+119
| | | | | | | | | | Define and use struct ilo_dsa_state; struct ilo_blend_state; struct ilo_fb_state; in ilo_context.
* ilo: switch to ilo states for WM stageChia-I Wu2013-06-077-26/+33
| | | | | | | | Define and use struct ilo_rasterizer_state; in ilo_context.
* ilo: switch to ilo states for CLIP and SF stagesChia-I Wu2013-06-076-19/+49
| | | | | | | | | Define and use struct ilo_viewport_state; struct ilo_scissor_state; in ilo_context.
* ilo: switch to ilo states for SOL stageChia-I Wu2013-06-077-30/+29
| | | | | | | | Define and use struct ilo_so_state; in ilo_context.
* ilo: switch to ilo states for VF stageChia-I Wu2013-06-077-53/+55
| | | | | | | | | | Define and use struct ilo_vb_state; struct ilo_ve_state; struct ilo_ib_state; in ilo_context.
* ilo: move hardware limits to ilo_gpe.hChia-I Wu2013-06-072-22/+56
|
* llvmpipe: bump 3d and cube map limits to 2048 and 8192 respectivelyRoland Scheidegger2013-06-061-2/+2
| | | | | | | These should just work, required by d3d10. Too large resources will get thrown out separately anyway. Reviewed-by: Brian Paul <[email protected]>
* llvmpipe: improve alignment calculation for fetching/storing pixelsRoland Scheidegger2013-06-051-12/+21
| | | | | | | | | | | | | | | | This was always doing per-pixel alignment which isn't necessary, except for the buffer case (due to the per-element offset). The disabled code for calculating it was incorrect because it assumed that always the full block would be fetched, which may not be the case, so fix this up. The original code failed for instance for r10g10b10a2 the alignment would have been calculated as 4 (block_width) * 4 (bytes) so 16, but the actual fetch may have only fetched 2 values at a time, hence only alignment 8 - it is unclear what exactly would happen in this case (alignment larger than size to fetch). So just use the (already calculated) fetch size instead and get alignment from that which should always work, no matter if fetching 1,2 or 4 pixels. Reviewed-by: Jose Fonseca <[email protected]>
* llvmpipe: reduce alignment requirement for 1d resources from 4x4 to 4x1Roland Scheidegger2013-06-059-44/+158
| | | | | | | | | | | | | | | | | | | | | | | | | | | | For rendering to buffers, we cannot have any y alignment. So make sure that tile clear commands only clear up to the fb width/height, not more (do this for all resources actually as clearing more seems pointless for other resources too). For the jit fs function, skip execution of the lower half of the fragment shader for the 4x4 stamp completely, for depth/stencil only load/store the values from the first row (replace other row with undef). For the blend function, also only load half the values from fs output, replace the rest with undefs so that everything still operates on the full 4x4 block to keep code the same between 4x1 and 4x4 (except for load/store of course which also needs to skip (store) or replace these values with undefs (load))., at the cost of slightly less optimal code being produced in some cases. Also reduce 1d and 1d array alignment too, because they can be handled the same as buffers so don't need to waste memory. v2: don't try to run special blend code for 4x1, (very) slightly less complexity if we just use the same code as for 4x4 which may or may not make it easier to optimize in the future (as we care a lot more about 4x4 performance than 1d). v2: don't use undef values for unused fs src outputs with llvm 3.1 as it apparently can trigger a bug in llvm. Reviewed-by: Jose Fonseca <[email protected]>
* llvmpipe: cleanup of generate_unswizzled_blendRoland Scheidegger2013-06-051-22/+37
| | | | | | | | | | | | | Some parameters were used inconsistently, for instance not using block_width/block_height/block_size for deferring number of pixels but rather relying on guesses from the number of fragment shaders etc, so fix this up (no actual change in behavior since the block size stays fixed). (Though most of the code would work with different block_height, with three exceptions, one being the hacked r11g11b10 conversions and twiddle code which only work with block_height 2 not 1, and the last one being blend vector type not being 128bit wide.) Reviewed-by: Jose Fonseca <[email protected]>