summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* i965: Add untyped surface write opcode.Francisco Jerez2015-05-049-0/+81
| | | | | Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965: Reorder sources of the untyped atomic opcode.Francisco Jerez2015-05-044-6/+6
| | | | | | | | | | | | This is consistent with the untyped surface read opcode. From now on all typed and untyped surface access opcodes will follow the same pattern: src[0] will be the message payload, src[1] will be the surface index and src[2] will be a control immediate (atomic operation for atomic opcodes and number of vector components for surface read and write opcodes). Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965: Pass the number of components as a source of the untyped surface read ↵Francisco Jerez2015-05-044-6/+10
| | | | | | | opcode. Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965/vec4: Add support for untyped surface message sends from GRF.Francisco Jerez2015-05-043-16/+14
| | | | | | | | | This doesn't actually enable untyped surface message sends from GRF yet, the upcoming atomic counter and image intrinsic lowering code will. Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965: Don't request untyped atomic writeback message if the destination is null.Francisco Jerez2015-05-042-2/+3
| | | | | Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965: Simplify generator code for untyped surface messages.Francisco Jerez2015-05-044-87/+18
| | | | | | | | | The generate_untyped_*() methods do nothing useful other than calling the corresponding function from brw_eu_emit.c. The calls to brw_mark_surface_used() will go away too in a future commit. Reviewed-by: Topi Pohjolainen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965: Fix the untyped surface opcodes to deal with indirect surface access.Francisco Jerez2015-05-044-82/+99
| | | | | | | | | | | | Change brw_untyped_atomic() and brw_untyped_surface_read() to take the surface index as a register instead of a constant and to use brw_send_indirect_message() to emit the indirect variant of send with a dynamically calculated message descriptor. This will be required to support variable indexing of image arrays for ARB_shader_image_load_store. Acked-by: Kenneth Graunke <[email protected]> Reviewed-by: Topi Pohjolainen <[email protected]>
* ilo: use ilo_image exclusively in coreChia-I Wu2015-05-024-139/+149
| | | | | Initialize ilo_view_surface and ilo_zs_surface from ilo_image instead of ilo_texture.
* ilo: add ilo_image_can_enable_aux()Chia-I Wu2015-05-029-50/+27
| | | | It replaces ilo_texture_can_enable_hiz().
* ilo: make ilo_image more self-containedChia-I Wu2015-05-022-9/+21
| | | | Add depth0, sample_count, and scanout to ilo_image.
* ilo: add ilo_image_init_for_imported()Chia-I Wu2015-05-023-60/+66
| | | | | It replaces ilo_image_update_for_imported_bo() and enables more error checkings for imported textures.
* ilo: prepare for image init for imported boChia-I Wu2015-05-021-120/+129
| | | | Refactoring in prepraration for ilo_image_init_for_imported().
* ilo: constify ilo_image_paramsChia-I Wu2015-05-021-11/+11
| | | | Make ilo_image_params const in functions that do not modify it.
* ilo: improve readability of ilo_imageChia-I Wu2015-05-026-111/+127
| | | | Improve docs, rename struct fields, and reorder walk types. No real changes.
* ilo: move command builder to coreChia-I Wu2015-05-0223-61/+74
|
* ilo: move ilo_state_3d* to coreChia-I Wu2015-05-029-276/+274
| | | | ilo state structs (struct ilo_xxx_state) are moved as well.
* ilo: add ilo_buffer.h to coreChia-I Wu2015-05-025-90/+138
| | | | Rename the original ilo_buffer to ilo_buffer_resource to avoid name conflict.
* ilo: move BOs from ilo_texture to ilo_imageChia-I Wu2015-05-027-39/+63
| | | | We want to work with ilo_image instead of ilo_texture in core.
* ilo: move ilo_layout.[ch] to core as ilo_image.[ch]Chia-I Wu2015-05-0211-487/+489
| | | | Move files and s/layout/image/.
* ilo: add ilo_format.[ch] to coreChia-I Wu2015-05-028-169/+184
| | | | The original ilo_format.[ch] are removed.
* ilo: add ilo_fence.h to coreChia-I Wu2015-05-025-58/+113
| | | | Implement pipe_fence_handle on top of ilo_fence.
* ilo: add ilo_dev_init() to coreChia-I Wu2015-05-024-146/+195
| | | | Move init_dev() from ilo_screen.c to core.
* ilo: rename ilo_dev_info to ilo_devChia-I Wu2015-05-0225-141/+141
| | | | With intel_winsys being embedded in it, drop the "_info" suffix.
* ilo: move intel_winsys to ilo_dev_infoChia-I Wu2015-05-025-13/+15
| | | | We want to use ilo_dev_info instead of ilo_screen in core.
* ilo: add ilo_dev.h to coreChia-I Wu2015-05-023-38/+73
| | | | Move what are remaining in ilo_common.h (that is, ilo_dev_*) to ilo_dev.h.
* ilo: add ilo_debug.[ch] to coreChia-I Wu2015-05-025-85/+158
| | | | | They consist of the debug helpers that used to live in ilo_common.h and ilo_screen.c.
* ilo: add ilo_core.h to coreChia-I Wu2015-05-023-14/+48
| | | | | ilo_core.h includes the common gallium headers that were included in ilo_common.h.
* ilo: move intel_winsys.h to coreChia-I Wu2015-05-0220-19/+19
| | | | | Add a new subdirectory and start moving files that do not depend on ilo_screen/ilo_context to it.
* i965: Upload atomic buffer state for compute shadersJordan Justen2015-05-024-1/+29
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Emit MEDIA_STATE_FLUSH after WALKERJordan Justen2015-05-022-0/+6
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Implement brw_emit_gpgpu_walkerJordan Justen2015-05-022-1/+51
| | | | | | | | | | | | | Tested on Ivybridge, Haswell and Broadwell. v2: * Use SET_FIELD. (Ken) * Use simd_size / 16 to support SIMD8/16/32. Ken suggested that we might be able to do it arithmetically rather than just supporting SIMD8 and SIMD16 with a conditional. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/state: Emit pipeline select when changing pipelinesJordan Justen2015-05-024-6/+36
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965: Implement DispatchCompute() back-endPaul Berry2015-05-024-0/+127
| | | | | | | brw_emit_gpgpu_walker will be implemented in a subsequent patch. Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* main/cs: Implement front end code for glDispatchCompute().Paul Berry2015-05-021-1/+19
| | | | | Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* mesa/cs: Add DispatchCompute() to driver function table.Paul Berry2015-05-021-0/+7
| | | | | Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Emit state base addressJordan Justen2015-05-022-1/+3
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/fs: Add CS shader time supportJordan Justen2015-05-024-2/+33
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Upload brw_cs_stateJordan Justen2015-05-024-0/+109
| | | | | | | | v3: * Add defines. Misc cleanup suggestions. (Ken) Signed-off-by: Jordan Justen <[email protected]> Acked-by: Kenneth Graunke <[email protected]>
* i965/cs: Support CS program precompileJordan Justen2015-05-024-0/+41
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965: Add brw_setup_tex_for_precompile. Use in VS, GS & FS.Jordan Justen2015-05-023-24/+24
| | | | | | Suggested-by: Kristian Høgsberg <[email protected]> Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Emit compute shader code and upload programsJordan Justen2015-05-023-0/+212
| | | | | | | | | | | | v2: * Don't bother checking for 'gen > 5' (krh) * Populate sampler data in key (krh) v3: * Drop no8 support, and simplify code in several places (Ken) Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Set invocation counts based on max_cs_threadsJordan Justen2015-05-021-0/+24
| | | | | | | | | | | | | | For ES, we set the max counts based on SIMD8, which is currently accurate. For desktop GL, we set the max counts based on SIMD16, which can fail in some cases where a SIMD16 program is not currently supported. Therefore, this value is not currently accurate, but will work fine in many cases, and lets us run more test cases. Eventually we want to always be able to generate a SIMD16 program. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Add max_cs_threadsJordan Justen2015-05-024-1/+14
| | | | | | | | Add values for gen7 & gen8. These are the number threads in a subslice. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965: Remove comment about chv device numbers being preliminaryJordan Justen2015-05-021-3/+0
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/fs: Support compute programs in fs_visitorJordan Justen2015-05-024-3/+93
| | | | | | | | | | v2: * Clean out some unneeded code copied from run_fs (krh) * Always use NIR * Split shader time out into a separate commit Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cache: Add support for CS in program state cacheJordan Justen2015-05-024-0/+54
| | | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Add brw_cs_prog_data, brw_cs_prog_key and brw_context::cs.Paul Berry2015-05-022-0/+62
| | | | | | | | | | | | [email protected]: * Added brw_cs_prog_key structure * Added brw_cs_prog_data::dispatch_grf_start_reg_16 * Added brw_cs_prog_data::local_size * Added brw_cs_prog_data::simd_size Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kristian Høgsberg <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Add generator support for CS_OPCODE_CS_TERMINATEJordan Justen2015-05-022-0/+36
| | | | | | | | | | v2: * Don't rely on brw_eu* to generate the send instruction. We now generate the send here, and drop the "i965/cs: Add support for the SEND message that terminates a CS thread" brw_eu* patch. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/cs: Mark g0 as used by CS_OPCODE_CS_TERMINATEJordan Justen2015-05-021-0/+4
| | | | | Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* i965/fs: Add emit_cs_terminate to emit CS_OPCODE_CS_TERMINATEJordan Justen2015-05-022-0/+23
| | | | | | | | | | | | v2: * Do more work at the visitor level. g0 is loaded and sent to the generator now. v3: * Use Ken's comment explaining g0 usage Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-18 03:24:03 +0000