summaryrefslogtreecommitdiffstats
path: root/src/mesa
Commit message (Collapse)AuthorAgeFilesLines
* i965: Lower min/max after optimization on Gen4/5.Matt Turner2016-02-178-44/+88
| | | | | | | | | | | | | | | | | | | Gen4/5's SEL instruction cannot use conditional modifiers, so min/max are implemented as CMP + SEL. Handling that after optimization lets us CSE more. On Ironlake: total instructions in shared programs: 6426035 -> 6422753 (-0.05%) instructions in affected programs: 326604 -> 323322 (-1.00%) helped: 1411 total cycles in shared programs: 129184700 -> 129101586 (-0.06%) cycles in affected programs: 18950290 -> 18867176 (-0.44%) helped: 2419 HURT: 328 Reviewed-by: Francisco Jerez <[email protected]>
* i965/vec4: Initialize force_writemask_all in vec4_builder().Matt Turner2016-02-171-1/+2
| | | | Reviewed-by: Francisco Jerez <[email protected]>
* st/mesa: fix up result_src.type when doing i2u/u2i conversionsIlia Mirkin2016-02-171-0/+1
| | | | | | | | | | | | Even though it's a no-op, it's important to keep track of the type so that we can pick the properly-signed op later on. This fixes dEQP-GLES3.functional.shaders.precision.uint.highp_div_fragment, which ended up using IDIV instead of UDIV. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]> Cc: [email protected]
* st/mesa: use cso_set_viewport_dims() in try_pbo_upload_common()Brian Paul2016-02-171-12/+1
| | | | | | | Note that this results in a different transformation for the viewport's Z axis (depth range), but that doesn't matter for this case. Reviewed-by: Roland Scheidegger <[email protected]>
* i965/gen7: Use predicated rendering for indirect computeJordan Justen2016-02-172-14/+83
| | | | | | | | | | | | | | | | | | | | | | | | | | | On gen7 (Ivy Bridge, Haswell), we will get a GPU hang if an indirect dispatch is used, but one of the dimensions is 0. Therefore we use predicated rendering on the GPGPU_WALKER command to handle this case. Fixes piglit test: spec/arb_compute_shader/zero-dispatch-size From the ARB_compute_shader spec, under DispatchCompute: "If the work group count in any dimension is zero, no work groups are dispatched." And then for DispatchComputeIndirect: ... "is equivalent (assuming no errors are generated) to calling DispatchCompute with <num_groups_x>, <num_groups_y> and <num_groups_z>" ... Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94100 Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]> Tested-by: Ilia Mirkin <[email protected]>
* st/mesa: add missing ETC2 entries to format_mapRob Clark2016-02-161-0/+42
| | | | | | | | Noticed by Ilia when I was trying to figure out why some app was failing to use ETC2. Signed-off-by: Rob Clark <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* st/mesa: do not init limits when compute shaders are not supportedSamuel Pitoiset2016-02-161-0/+8
| | | | | | | | | | | | | | | | | When the number of uniform blocks is less than 12, ARB_uniform_buffer_object can't be enabled and the maximum GL version is not even 3.1... This fixes a regression introduced in 7c79c1e (st/mesa: add compute shader state) if the maximum number of uniform blocks allowed for compute shaders is less than 12. This happens on Kepler but this might also affect other Gallium drivers. Signed-off-by: Samuel Pitoiset <[email protected]> Reported-by: Tobias Klausmann <[email protected]> Tested-by: Tobias Klausmann <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Tobias Klausmann <[email protected]>
* mesa: Don't call driver when there is no compute workJordan Justen2016-02-161-0/+3
| | | | | | | | | | The ARB_compute_shader spec says: "If the work group count in any dimension is zero, no work groups are dispatched." Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
* i965: Set compute shader shared memory max to 64kJordan Justen2016-02-161-1/+1
| | | | | | | | | | | | | | | | | | | | See Ivy Bridge PRM, Volume 2, Part 2, 1.8.4 INTERFACE_DESCRIPTOR_DATA: DWORD 5, bits 20:16: "This field indicates how much shared local memory the thread group requires. The amount is specified in 4k blocks, but only powers of 2 are allowed: 0, 4k, 8k, 16k, 32k and 64k per half-slice." For Haswell, see Volume 2d, INTERFACE_DESCRIPTOR_DATA: DWORD 5, bits 20:16: With text identical to the Ivy Bridge PRM. For Broadwell, see Volume 2d, INTERFACE_DESCRIPTOR_DATA: DWORD 6, bits 20:16: With text identical to the Ivy Bridge PRM. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* st/mesa: use new CSO_BITS_ALL_SHADERSBrian Paul2016-02-164-24/+9
| | | | Reviewed-by: Marek Olšák <[email protected]>
* st/mesa: simplify st->ctx, ctx->st usage in a various placesBrian Paul2016-02-166-18/+17
|
* st/mesa: use _mesa_geometric_width/height() in glDrawPixels codeBrian Paul2016-02-161-10/+9
| | | | Reviewed-by: Ilia Mirkin <[email protected]>
* st/mesa: rename attr variable in st_DrawTex()Brian Paul2016-02-161-10/+10
| | | | | | | Rename to 'tex_attr' to be a bit more clear. Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: use 'cso' instead of 'st->cso_context' in st_DrawTex()Brian Paul2016-02-161-1/+1
| | | | | Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: fix whitespace and add comment in st_DrawTex()Brian Paul2016-02-161-3/+3
| | | | | Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: used _mesa_num_tex_faces() in st_finalize_texture()Brian Paul2016-02-161-1/+1
| | | | | Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: use cso_save/restore_state() in st_cb_texture.cBrian Paul2016-02-161-33/+22
| | | | | | This simplifies the error handling code too. Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: use new cso_save/restore_state() functionsBrian Paul2016-02-164-101/+55
| | | | Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: use new cso_set_viewport_dims() helperBrian Paul2016-02-163-36/+7
| | | | Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: use 'cso' local var instead of st->cso_contextBrian Paul2016-02-163-90/+89
| | | | | | Just a little cleaner. Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: consolidate quad drawing codeBrian Paul2016-02-165-238/+136
| | | | | | | The glClear, glBitmap and glDrawPixels code now use a new st_draw_quad() helper function. Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: overhaul vertex setup for clearing, glDrawPixels, glBitmapBrian Paul2016-02-165-161/+193
| | | | | | | | | | | | Define a new st_util_vertex structure which is a bit smaller (9 floats versus the previous 12 floats per vertex). Clean up the glClear, glDrawPixels and glBitmap code that sets up the vertex data and does the drawing so it's all very similar. This can lead to more consolidation. v2: add assertion that vertex buffer slot == 0 to catch possible future change in cso_get_aux_vertex_buffer_slot() behavior. Reviewed-by: Jose Fonseca <[email protected]>
* st/mesa: include u_draw.h, not u_draw_quad.h in st_draw.cBrian Paul2016-02-161-1/+1
| | | | Reviewed-by: Jose Fonseca <[email protected]>
* i965: Expose logic telling if non-msrt mcs is supportedTopi Pohjolainen2016-02-162-4/+13
| | | | | | | | | Alos use the opportunity to mark inputs constant. (Context has to be given as read-write to intel_miptree_supports_non_msrt_fast_clear() to support debug output). Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965/gen9: Refactor msrt mcs initializationTopi Pohjolainen2016-02-161-14/+22
| | | | | | | | This will be re-used to initialize auxiliary buffers in lossless compression case. Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965: Add a few assertions on lossless compressionTopi Pohjolainen2016-02-162-0/+9
| | | | | | | | | v2 (Ben): Use combination of msaa_layout and number of samples instead of introducing explicit type for lossless compression (intel_miptree_is_lossless_compressed()). Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965: Add a flag telling color resolve pass to ignore CCS_ETopi Pohjolainen2016-02-163-2/+27
| | | | | | | | | v2 (Ben): Use combination of msaa_layout and number of samples instead of introducing explicit type for lossless compression (intel_miptree_is_lossless_compressed()). Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965: Add resolve option for lossless compressionTopi Pohjolainen2016-02-162-1/+5
| | | | | | | | | v2 (Ben): Use combination of msaa_layout and number of samples instead of introducing explicit type for lossless compression (intel_miptree_is_lossless_compressed()). Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965: Allow fast clear to be used with lossless compressionTopi Pohjolainen2016-02-162-2/+6
| | | | | | | | | | | | v2 (Ben): Use combination of msaa_layout and number of samples instead of introducing explicit type for lossless compression. v3 (Ben): Squash with "i965: Resolve color buffer also in lossless compression case" and clarify simple non-compressed fast clear case. Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* i965: Add helper for detecting lossless compressionTopi Pohjolainen2016-02-162-0/+30
| | | | | Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Ben Widawsky <[email protected]>
* Revert "i965: Restore vbo after color resolve during brw_try_draw_prims()"Topi Pohjolainen2016-02-161-9/+0
| | | | | | | | | | | | | This got pushed accidentally in the first place but wasn't reverted as it didn't regress piglit but instead fixed one newly introduced test exercising a corner in case in i965 driver. However, saving and restoring vertex buffer context is complicated and requires more thought. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94150 Signed-off-by: Topi Pohjolainen <[email protected]> Reviewed-by: Tapani Palli <[email protected]>
* st/mesa: count shader images in MaxCombinedShaderOutputResourcesNicolai Hähnle2016-02-151-0/+1
| | | | Reviewed-by: Ilia Mirkin <[email protected]>
* st/mesa: enable GL image extensions when backend supports themIlia Mirkin2016-02-151-0/+17
| | | | | | | | | | This enables ARB_shader_image_load_store and ARB_shader_image_size when the backend claims support for these. It will also implicitly enable the image component of ARB_shader_texture_image_samples. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* st/mesa: convert GLSL image intrinsics into TGSIIlia Mirkin2016-02-152-4/+211
| | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* st/mesa: allow st_format.h to be included from C++ filesIlia Mirkin2016-02-151-0/+8
| | | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* st/mesa: set pipe_image_view layers correctly for 3D texturesNicolai Hähnle2016-02-151-7/+17
| | | | Reviewed-by: Ilia Mirkin <[email protected]>
* st/mesa: call st_finalize_texture from image atomsNicolai Hähnle2016-02-151-1/+5
| | | | Reviewed-by: Ilia Mirkin <[email protected]>
* st/mesa: add an image atom for shader imagesIlia Mirkin2016-02-156-0/+237
| | | | | | Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
* st/mesa: empty buffer binding if the buffer's not really thereIlia Mirkin2016-02-151-3/+5
| | | | | | | | This can happen with 0-sized buffers. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]>
* mesa: need to check resource and set length even if bufSize is 0Ilia Mirkin2016-02-151-4/+0
| | | | | | | | | | | | | | This fixes a number of dEQP tests, such as: dEQP-GLES31.functional.program_interface_query.buffer_limited_query.resource_query It was expecting the length to be set even in the bufSize == 0 case. Also _mesa_get_program_resourceiv does some error checking on the resource which should probably happen even in the bufSize == 0 case as well although there's no dEQP test for that. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* i965/bxt: Production thread countsBen Widawsky2016-02-151-10/+9
| | | | | | | | v2: Forgot to squash in the comment removal Signed-off-by: Ben Widawsky <[email protected]> Reviewed-by: Mark Janes <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* i965: Fix gl_DrawID in the vec4 backend.Kenneth Graunke2016-02-141-5/+5
| | | | | | | | | | | | brw_draw_upload.c uploads VertexID/InstanceID first, then DrawID. So we need to assign the attribute mapping in that order as well. Fixes the following Pigit tests with the vec4 backend: - arb_shader_draw_parameters-drawid vertexid - arb_shader_draw_parameters-drawid-indirect basevertex Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]>
* mesa: move assertion in _mesa_cube_face_target()Brian Paul2016-02-141-3/+5
| | | | | | | Fixes piglit arb_texture_view-sampling-2d-array-as-2d-layer regression. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94134 Reviewed-by: Jose Fonseca <[email protected]>
* mesa: default FixedSampleLocations to true when using a dummy imageIlia Mirkin2016-02-131-0/+1
| | | | | | | | | | | | GL_ARB_texture_multisample and GLES 3.1 expect the initial value to be GL_TRUE. This fixes dEQP-GLES31.functional.state_query.texture_level.texture_2d_multisample_array.fixed_sample_locations_integer and a few related tests. Signed-off-by: Ilia Mirkin <[email protected]> Reviewed-by: Chris Forbes <[email protected]>
* glsl/types: Add support for function typesJason Ekstrand2016-02-135-0/+6
| | | | | | | | SPIR-V has a concept of a function type that's used fairly heavily. We could special-case function types in SPIR-V -> NIR but it's easier if we just add support to glsl_types. Reviewed-by: Jordan Justen <[email protected]>
* glsl/types: Rename sampler_type to sampled_typeJason Ekstrand2016-02-131-1/+1
| | | | | | | | It's a bit more descriptive since it is the base type that you get when you sample from it. Also, the next commit adds a bare "sampler" type and we need glsl_type::sampler_type available for a public static member. Reviewed-by: Jordan Justen <[email protected]>
* i965: Reupload push and pull constants when we get new shader image unit state.Francisco Jerez2016-02-131-0/+5
| | | | | | | | | | | Fixes several of the "dEQP-GLES31.functional.image_load_store*load_store*single_layer" dEQP tests that use image formats we implement using untyped surface messages. Cc: [email protected] Tested-by: Ilia Mirkin <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965: fix MAX_COMPUTE_SHARED_SIZE constant valueSamuel Pitoiset2016-02-131-0/+1
| | | | | | | | | | | | MAX_COMPUTE_SHARED_SIZE should be set to 32768. This fixes a regression introduced in be27f77 (mesa: do not use a constant for MAX_COMPUTE_SHARED_SIZE). Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94139 Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* st/mesa: fix pipe_grid_info initializerSamuel Pitoiset2016-02-131-1/+1
| | | | | | | Fixes MSVC build error which doesn't allow empty initializers. Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Roland Scheidegger <[email protected]>
* st/mesa: implement limits for ARB_compute_shaderSamuel Pitoiset2016-02-131-2/+31
| | | | | | | | | | | | | | | | | | | | | According to the spec, this also increases the following minimum values: - MAX_COMBINED_TEXTURE_IMAGE_UNITS 96 (6*16), was 80 - MAX_UNIFORM_BUFFER_BINDINGS 72 (6*12), was 60 ARB_compute_shader is not enabled by default because images support is still not implemented yet. If you want to use it you need to set MESA_EXTENSION_OVERRIDE=GL_ARB_compute_shader. Changes from v2: - make use of the new PIPE_CAP_SHADER_SUPPORTED_IRS cap instead of enabling the extension when PIPE_CAP_COMPUTE is enabled. - query for PIPE_CAP_COMPUTE first - s/shader_supported_irs/compute_supported_irs/ - disable ARB_compute_shader and add a comment which explains why Signed-off-by: Samuel Pitoiset <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Reviewed-by: Ilia Mirkin <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-20 22:10:21 +0000