aboutsummaryrefslogtreecommitdiffstats
path: root/src/intel/compiler
Commit message (Expand)AuthorAgeFilesLines
* util: Remove tmp argument from BITSET_FOREACH_SET macroMatt Turner2020-01-231-6/+3
* i965: Enable INTEL_shader_integer_functions2 on Gen8+Ian Romanick2020-01-231-0/+2
* intel/fs: Implement support for NIR opcodes for INTEL_shader_integer_functions2Ian Romanick2020-01-231-0/+67
* intel/fs: Add SHADER_OPCODE_[IU]SUB_SAT pseudo-opsIan Romanick2020-01-233-0/+101
* intel/fs: Don't lower integer multiplies that don't need loweringIan Romanick2020-01-231-0/+11
* intel/compiler: Move Gen4/5 rounding to visitorMatt Turner2020-01-224-37/+28
* intel/compiler: Return early if read() failedEmmanuel Gil Peyrot2020-01-221-1/+4
* intel/compiler: Fix array bounds warning on GCC 10.Timur Kristóf2020-01-221-0/+2
* intel/compiler: Test compaction on Gen <= 12Matt Turner2020-01-221-1/+1
* intel/compiler: Validate fuzzed instructionsMatt Turner2020-01-223-1/+7
* intel/compiler: Add unit tests for new EU validation checksMatt Turner2020-01-221-0/+396
* intel/compiler: Validate some instruction word encodingsMatt Turner2020-01-221-10/+84
* intel/compiler: Factor out brw_validate_instruction()Matt Turner2020-01-221-26/+35
* intel/compiler: Handle invalid compacted immediatesMatt Turner2020-01-221-1/+15
* intel/compiler: Handle invalid inputs to brw_reg_type_to_*()Matt Turner2020-01-221-0/+6
* intel/compiler: Split hw_type tablesMatt Turner2020-01-221-23/+116
* intel/compiler: Add a INVALID_{,HW_}REG_TYPE macrosMatt Turner2020-01-223-5/+8
* intel/compiler: Add NF some more placesMatt Turner2020-01-222-0/+5
* intel/compiler: Limit compaction unit tests to specific gensMatt Turner2020-01-221-9/+18
* intel/compiler: Don't disassemble align1 3-src operands on Gen < 10Matt Turner2020-01-221-0/+12
* intel/compiler: Split has_64bit_types into float/intMatt Turner2020-01-225-20/+69
* intel/compiler: Extract GEN_* macros into separate fileMatt Turner2020-01-222-37/+63
* intel/compiler: Use ARRAY_SIZE()Matt Turner2020-01-221-22/+22
* intel/fs: Don't emit control barrier if only one thread is usedCaio Marcelo de Oliveira Filho2020-01-211-0/+9
* intel/fs: Don't emit fence for shared memory if only one thread is usedCaio Marcelo de Oliveira Filho2020-01-211-13/+23
* intel/fs: Add workgroup_size() helperCaio Marcelo de Oliveira Filho2020-01-212-0/+10
* intel/fs: Add FS_OPCODE_SCHEDULING_FENCECaio Marcelo de Oliveira Filho2020-01-213-0/+13
* intel/fs: Switch to standard vector layout for barycentrics at optimization t...Francisco Jerez2020-01-174-58/+30
* intel/fs: Introduce barycentric layout lowering pass.Francisco Jerez2020-01-173-9/+73
* intel/fs: Split fetch_payload_reg() into separate helper for barycentrics.Francisco Jerez2020-01-172-12/+30
* intel/fs/gen6: Use SEL instead of bashing thread payload for unlit centroid w...Francisco Jerez2020-01-171-5/+8
* intel/fs/gen6: Generalize aligned_pairs_class to SIMD16 aligned barycentrics.Francisco Jerez2020-01-172-31/+46
* intel/fs/gen6: Constrain barycentric source of LINTERP during bank conflict m...Francisco Jerez2020-01-171-0/+8
* intel/fs/gen4-6: Allocate registers from aligned_pairs_class based on LINTERP...Francisco Jerez2020-01-171-19/+20
* intel/fs: Allow limited copy propagation of a LOAD_PAYLOAD into another.Francisco Jerez2020-01-171-1/+15
* intel/fs: Add support for copy-propagating a block of multiple FIXED_GRFs.Francisco Jerez2020-01-171-5/+7
* intel/fs: Add partial support for copy-propagating FIXED_GRFs.Francisco Jerez2020-01-171-14/+75
* intel/fs: Extend copy propagation dataflow analysis to copies with FIXED_GRF ...Francisco Jerez2020-01-171-5/+6
* intel/fs: Rework fs_inst::is_copy_payload() into multiple classification help...Francisco Jerez2020-01-174-31/+101
* intel/fs: Generalize fs_reg::is_contiguous() to register files other than VGRF.Francisco Jerez2020-01-171-1/+16
* intel/fs: Try to vectorize header setup in lower_load_payload().Francisco Jerez2020-01-171-8/+16
* intel/compiler: Fix illegal mutation in get_nir_image_intrinsic_imageKenneth Graunke2020-01-151-3/+6
* anv,nir: Lower quad_broadcast with dynamic index in NIRJason Ekstrand2020-01-151-0/+1
* i965: Reuse the new core glsl_count_dword_slots().Eric Anholt2020-01-142-54/+2
* intel/fs: Only use SLM fence in compute shadersCaio Marcelo de Oliveira Filho2020-01-141-0/+3
* nir/lower_gs_intrinsics: add option for per-stream countsRhys Perry2020-01-141-1/+1
* nir/lower_atomics_to_ssbo: Also lower barriersJason Ekstrand2020-01-131-1/+0
* nir: Rename nir_intrinsic_barrier to control_barrierJason Ekstrand2020-01-132-3/+3
* intel/nir: Stop adding redundant barriersJason Ekstrand2020-01-131-14/+0
* nir: Add a new memory_barrier_tcs_patch intrinsicJason Ekstrand2020-01-132-0/+6
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 07:42:31 +0000