fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-21 18:00:13 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
mesa/src/intel/compiler
History
Lionel Landwerlin 9471ffa70a intel/fs: fix scheduling of HALT instructions 
With the following test :

dEQP-VK.spirv_assembly.instruction.terminate_invocation.terminate.no_out_of_bounds_load

There is a :

shader_start:
   ...                                 <- no control flow
   g0 = some_alu
   g1 = fbl
   g2 = broadcast g3, g1
   g4 = get_buffer_size g2
   ...                                 <- no control flow
   halt                                <- on some lanes
   g5 = send <surface>, g4

eliminate_find_live_channel will remove the fbl/broadcast because it
assumes lane0 is active at get_buffer_size :

shader_start:
   ...                                 <- no control flow
   g0 = some_alu
   g4 = get_buffer_size g0
   ...                                 <- no control flow
   halt                                <- on some lanes
   g5 = send <surface>, g4

But then the instruction scheduler will move the get_buffer_size after
the halt :

shader_start:
   ...                                 <- no control flow
   halt                                <- on some lanes
   g0 = some_alu
   g4 = get_buffer_size g0
   g5 = send <surface>, g4

get_buffer_size pulls the surface index from lane0 in g0 which could
have been turned off by the halt and we end up accessing an invalid
surface handle.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20765>
2023-05-05 00:43:25 +03:00
..
brw_cfg.cpp intel/fs: Add physical fall-through CFG edge for unconditional BREAK instruction. 2021-12-21 00:43:29 +00:00
brw_cfg.h intel/compiler: Add cfg_t::adjust_block_ips() method 2021-07-14 09:56:59 -07:00
brw_clip.h
brw_clip_line.c intel/compiler: Split 3DPRIM_* defines out to a separate header. 2022-06-30 23:46:35 +00:00
brw_clip_point.c
brw_clip_tri.c intel/compiler: Split 3DPRIM_* defines out to a separate header. 2022-06-30 23:46:35 +00:00
brw_clip_unfilled.c intel/compiler: Split 3DPRIM_* defines out to a separate header. 2022-06-30 23:46:35 +00:00
brw_clip_util.c intel: move away from booleans to identify platforms 2021-11-08 16:48:06 +00:00
brw_compile_clip.c intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_compile_ff_gs.c intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_compile_sf.c intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_compiler.c nir: intel/compiler: Move ufind_msb lowering to NIR 2023-03-10 15:27:17 +00:00
brw_compiler.h intel/compiler: make uses_pos_offset a tri-state 2023-05-03 10:03:57 +00:00
brw_dead_control_flow.cpp
brw_dead_control_flow.h
brw_debug_recompile.c intel/compiler: Delete sampler key handling for planar format stuff 2022-12-09 10:18:25 +00:00
brw_disasm.c intel/disasm/gfx12+: Fix print out of non-existing condmod field with 64-bit immediate. 2023-01-19 06:14:03 +00:00
brw_disasm_info.c intel/eu: Handle compaction when inserting validation errors 2022-07-28 21:31:45 +00:00
brw_disasm_info.h intel/eu: Handle compaction when inserting validation errors 2022-07-28 21:31:45 +00:00
brw_eu.c intel/compiler: export brw_num_sources_from_inst 2022-12-10 03:59:19 +00:00
brw_eu.h intel/compiler: Use SHADER_OPCODE_SEND for PI messages 2023-02-06 09:12:17 +00:00
brw_eu_compact.c intel/compiler: don't allocate compaction arrays on the stack 2022-10-28 07:10:58 +00:00
brw_eu_defines.h intel/fs: drop FS_OPCODE_UNIFORM_PULL_CONSTANT_LOAD_GFX7 2023-01-26 11:26:53 +00:00
brw_eu_emit.c intel/compiler: use intel_needs_workaround for Wa_14012437816 2023-04-13 07:33:50 +00:00
brw_eu_util.c intel: Rename genx keyword to gfxx in source files 2021-04-02 18:33:07 +00:00
brw_eu_validate.c intel/eu/validate: Check predication and cmod for SEL, CMP, and CMPN 2023-01-09 19:15:19 +00:00
brw_fs.cpp intel/compiler: make uses_pos_offset a tri-state 2023-05-03 10:03:57 +00:00
brw_fs.h intel/fs: fix subgroup invocation read bounds checking 2023-03-14 12:15:48 +00:00
brw_fs_bank_conflicts.cpp intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_fs_builder.h intel/fs: Make bld.F16TO32 actually emit F16TO32 not F32TO16 2023-03-17 09:01:18 +00:00
brw_fs_cmod_propagation.cpp intel/fs: avoid cmod optimization on instruction with different write_mask 2023-01-24 07:35:42 +00:00
brw_fs_combine_constants.cpp intel/fs: Rework the loop of opt_combine_constants that collects constants 2023-04-03 21:50:06 +00:00
brw_fs_copy_propagation.cpp intel/fs: Use specialized version of regions_overlap in opt_copy_propagation 2023-04-06 19:07:50 +00:00
brw_fs_cse.cpp intel/compiler: Implement nir_intrinsic_last_invocation 2022-03-26 00:28:19 +00:00
brw_fs_dead_code_eliminate.cpp intel/compiler: Eliminate SHADER_OPCODE_UNTYPED_ATOMIC_FLOAT 2023-01-19 08:42:22 +00:00
brw_fs_generator.cpp intel/compiler: report max dispatch width statistic 2023-03-21 11:53:04 +00:00
brw_fs_live_variables.cpp intel/fs: White space fixes 2023-04-06 19:07:50 +00:00
brw_fs_live_variables.h intel: Rename gen_device prefix to intel_device 2021-04-20 20:06:33 +00:00
brw_fs_lower_pack.cpp intel/fs: Move packHalf2x16 handling to lower_pack() 2023-03-09 23:26:17 +00:00
brw_fs_lower_regioning.cpp intel/compiler/gfx12.5+: Lower 64-bit cluster_broadcast with 32-bit ops 2023-04-20 11:41:10 -07:00
brw_fs_nir.cpp intel/compiler: UNDEF SubgroupInvocation's register 2023-05-04 18:17:26 +00:00
brw_fs_reg_allocate.cpp intel/fs: put scratch surface in the surface state heap 2022-11-19 14:58:58 +00:00
brw_fs_register_coalesce.cpp intel/fs: Fix register coalesce in presence of force_writemask_all copy source writes. 2023-03-17 03:05:24 -07:00
brw_fs_saturate_propagation.cpp brw: fix saturate propagation region overlap range 2022-12-09 00:39:05 +00:00
brw_fs_scoreboard.cpp Revert "intel/fs: Fix inferred_sync_pipe for F16TO32 opcodes" 2023-03-09 23:26:17 +00:00
brw_fs_sel_peephole.cpp intel/fs: sel.cond writes the flags on Gfx4 and Gfx5 2021-08-11 13:09:20 -07:00
brw_fs_thread_payload.cpp intel/compiler: remove unused field from fs_thread_payload 2023-02-23 08:04:24 +00:00
brw_fs_validate.cpp intel/fs: add MOV source count validation 2023-03-14 10:38:50 +00:00
brw_fs_visitor.cpp intel/fs: fix subgroup invocation read bounds checking 2023-03-14 12:15:48 +00:00
brw_gfx_ver_enum.h intel/compiler: Fix brw_gfx_ver_enum.h to be a proper header file 2022-06-30 23:46:35 +00:00
brw_inst.h intel/eu/gfx12+: Implement decoding of 64-bit immediates. 2023-01-19 06:14:03 +00:00
brw_interpolation_map.c intel: Rename genx keyword to gfxx in source files 2021-04-02 18:33:07 +00:00
brw_ir.h intel/compiler: Remove one overload of backend_instruction::insert_before 2023-04-06 19:07:50 +00:00
brw_ir_allocator.h
brw_ir_analysis.h
brw_ir_fs.h intel/compiler: Micro optimize regions_overlap 2023-04-06 19:07:50 +00:00
brw_ir_performance.cpp intel/compiler: Use SHADER_OPCODE_SEND for PI messages 2023-02-06 09:12:17 +00:00
brw_ir_performance.h
brw_ir_vec4.h intel: fix typos found by codespell 2022-06-27 10:20:55 +00:00
brw_isa_info.h intel/compiler: Remove use of thread_local for opcode tables 2022-06-30 23:46:35 +00:00
brw_kernel.c intel: Always call nir_lower_frexp. 2023-04-06 02:32:01 +00:00
brw_kernel.h intel/compiler: fix singleton pointer coverity warning 2022-04-19 12:36:10 +03:00
brw_lower_logical_sends.cpp intel/fs: factor out lsc surface descriptor settings 2023-04-05 12:32:56 +00:00
brw_mesh.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
brw_nir.c intel/compiler: Use NIR_PASS instead of NIR_PASS_V 2023-04-06 19:07:50 +00:00
brw_nir.h intel/nir: add options to storage image lowering 2023-04-18 08:38:55 +00:00
brw_nir_analyze_boolean_resolves.c intel: Drop some author comments and update Faith's name 2023-03-26 00:16:25 +00:00
brw_nir_analyze_ubo_ranges.c intel/compiler: Fix missing tie-breaker in brw_nir_analyze_ubo_ranges() ordering code 2022-11-14 19:41:35 +00:00
brw_nir_attribute_workarounds.c intel/compiler: Use named NIR intrinsic const index accessors 2022-08-16 05:44:30 +00:00
brw_nir_blockify_uniform_loads.c intel/fs: optimize uniform SSBO & shared loads 2023-04-05 12:32:56 +00:00
brw_nir_clamp_image_1d_2d_array_sizes.c intel/compiler: use nir_shader_instructions_pass in brw_nir_clamp_image_1d_2d_array_sizes 2021-10-05 10:02:54 +00:00
brw_nir_clamp_per_vertex_loads.c intel/fs: clamp per vertex input accesses to patchControlPoints 2022-12-07 08:16:03 +00:00
brw_nir_lower_alpha_to_coverage.c intel/fs: make alpha_to_coverage a tristate 2023-02-06 09:12:18 +00:00
brw_nir_lower_conversions.c intel/fs: Use nir_type_convert instead of nir_type_conversion_op 2022-12-14 06:23:21 +00:00
brw_nir_lower_cs_intrinsics.c intel/compiler: optimize away local_inv_index and local_inv_id if workgroup size is 1 2022-12-13 13:00:49 +00:00
brw_nir_lower_intersection_shader.c intel/rt: Handle halts in any-hit shaders properly 2022-08-05 11:51:31 +00:00
brw_nir_lower_ray_queries.c intel/nir/rt: wire position fetch intrinsic 2023-05-04 11:25:41 +00:00
brw_nir_lower_rt_intrinsics.c intel/nir/rt: wire position fetch intrinsic 2023-05-04 11:25:41 +00:00
brw_nir_lower_shader_calls.c intel: Fixes -Werror,-Wbitwise-instead-of-logical for clang-15 in brw_nir_lower_shader_calls.c 2022-11-17 23:17:40 +00:00
brw_nir_lower_shading_rate_output.c intel: fix typos found by codespell 2022-06-27 10:20:55 +00:00
brw_nir_lower_storage_image.c intel/nir: add options to storage image lowering 2023-04-18 08:38:55 +00:00
brw_nir_opt_peephole_ffma.c nir: Combine if_uses with instruction uses 2023-04-07 23:48:03 +00:00
brw_nir_opt_peephole_imul32x16.c intel/compiler: Fix signed integer range analysis of imax and imin 2022-11-09 21:34:26 +00:00
brw_nir_rt.c anv: use shader_info->var_copies_lowered 2023-02-06 22:11:34 +00:00
brw_nir_rt.h anv: support VK_PIPELINE_CREATE_RAY_TRACING_SKIP_* 2022-10-20 00:03:55 +00:00
brw_nir_rt_builder.h intel/nir/rt: wire position fetch intrinsic 2023-05-04 11:25:41 +00:00
brw_nir_tcs_workarounds.c intel/compiler: use nir_metadata_none instead of its value 2021-10-05 10:02:54 +00:00
brw_nir_trig_workarounds.py driconf: Add a limit_trig_input_range option 2022-05-13 06:47:53 +00:00
brw_packed_float.c
brw_predicated_break.cpp intel/compiler: Don't predicate a WHILE if there is a CONT 2021-12-08 14:56:32 -08:00
brw_prim.h intel/compiler: Split 3DPRIM_* defines out to a separate header. 2022-06-30 23:46:35 +00:00
brw_private.h intel/compiler: Use SIMD selection helpers in compile_single_bs() 2022-11-15 04:55:18 +00:00
brw_reg.h intel/compiler: Add a few more brw_ud* helpers 2022-09-13 01:44:24 +00:00
brw_reg_type.c intel: Rename gen_device prefix to intel_device 2021-04-20 20:06:33 +00:00
brw_reg_type.h intel/compiler: Move type_is_unsigned_int to brw_reg_type.h 2021-08-30 14:00:14 -07:00
brw_rt.h intel/rt: Fix L3 bank performance bottlenecks due to SW stack stride alignment. 2023-02-26 11:48:33 -08:00
brw_schedule_instructions.cpp intel/fs: fix scheduling of HALT instructions 2023-05-05 00:43:25 +03:00
brw_shader.cpp intel/compiler: Micro optimize inst_is_in_block 2023-04-06 19:07:50 +00:00
brw_shader.h intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_simd_selection.cpp intel/compiler: fine-grained control of dispatch widths 2023-01-27 11:00:41 +00:00
brw_vec4.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
brw_vec4.h i965/vec4: Implement uclz in the vec4 backend 2023-03-17 09:01:18 +00:00
brw_vec4_builder.h intel: Rename Genx keyword to Gfxx 2021-04-02 18:33:07 +00:00
brw_vec4_cmod_propagation.cpp intel: fixes -Werror,-Wunused-but-set-variable for clang-15 2022-11-17 23:17:40 +00:00
brw_vec4_copy_propagation.cpp intel/compiler: Introduce a new brw_isa_info structure 2022-06-30 23:46:35 +00:00
brw_vec4_cse.cpp intel/compiler: Rename vec4 state URB opcodes to have VEC4_ prefix 2022-07-08 19:45:34 +00:00
brw_vec4_dead_code_eliminate.cpp intel/vec4: sel.cond writes the flags on Gfx4 and Gfx5 2021-08-11 13:09:32 -07:00
brw_vec4_generator.cpp intel/compiler: report max dispatch width statistic 2023-03-21 11:53:04 +00:00
brw_vec4_gs_nir.cpp intel/compiler: Use named NIR intrinsic const index accessors 2022-08-16 05:44:30 +00:00
brw_vec4_gs_visitor.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
brw_vec4_gs_visitor.h intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
brw_vec4_live_variables.cpp intel/vec4: sel.cond writes the flags on Gfx4 and Gfx5 2021-08-11 13:09:32 -07:00
brw_vec4_live_variables.h intel/vec4: sel.cond writes the flags on Gfx4 and Gfx5 2021-08-11 13:09:32 -07:00
brw_vec4_nir.cpp i965/vec4: Implement uclz in the vec4 backend 2023-03-17 09:01:18 +00:00
brw_vec4_reg_allocate.cpp intel/compiler: Don't create vec4 reg-set for gen8+ 2022-07-14 17:49:01 +00:00
brw_vec4_surface_builder.cpp intel: move away from booleans to identify platforms 2021-11-08 16:48:06 +00:00
brw_vec4_surface_builder.h
brw_vec4_tcs.cpp intel/fs: fix per vertex input clamping 2023-04-27 20:29:16 +00:00
brw_vec4_tcs.h intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
brw_vec4_tes.cpp intel/compiler: Rename vec4 state URB opcodes to have VEC4_ prefix 2022-07-08 19:45:34 +00:00
brw_vec4_tes.h intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
brw_vec4_visitor.cpp intel/vec4: force exec_all on float control instruction 2023-04-14 10:54:01 +00:00
brw_vec4_vs.h intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
brw_vec4_vs_visitor.cpp intel/compiler: Rename vec4 state URB opcodes to have VEC4_ prefix 2022-07-08 19:45:34 +00:00
brw_vue_map.c intel/compiler: Store the number of position slots in the VUE map 2022-08-31 02:00:18 +00:00
gfx6_gs_visitor.cpp intel/compiler: Rename vec4 state URB opcodes to have VEC4_ prefix 2022-07-08 19:45:34 +00:00
gfx6_gs_visitor.h intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
intel_clc.c intel/compiler: Fix dynarray usage in intel_clc 2022-11-14 19:15:05 +00:00
meson.build intel/fs: optimize uniform SSBO & shared loads 2023-04-05 12:32:56 +00:00
test_eu_compact.cpp intel/compiler: Fixes [-Wdeprecated-declarations] in test_eu_compact.cpp 2022-08-23 15:19:16 +00:00
test_eu_validate.cpp intel/eu/validate: Validate integer multiplication source size restrictions 2022-11-09 21:34:26 +00:00
test_fs_cmod_propagation.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
test_fs_copy_propagation.cpp intel/fs: Don't copy propagate from saturate to sel 2023-03-29 23:48:19 +00:00
test_fs_saturate_propagation.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
test_fs_scoreboard.cpp intel/fs: report max register pressure in shader stats 2023-03-08 13:37:07 +00:00
test_simd_selection.cpp intel/compiler: fine-grained control of dispatch widths 2023-01-27 11:00:41 +00:00
test_vec4_cmod_propagation.cpp intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
test_vec4_copy_propagation.cpp intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
test_vec4_dead_code_eliminate.cpp intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
test_vec4_register_coalesce.cpp intel/fs,vec4: Drop support for shader time 2021-12-10 21:20:47 +00:00
test_vf_float_conversions.cpp