summaryrefslogtreecommitdiff
path: root/src/compiler/nir/nir_opcodes.py
AgeCommit message (Expand)AuthorFilesLines
2019-11-20nir: Add a 8-bit bool typeNeil Roberts1-2/+11
2019-11-20nir: Add a 16-bit bool typeNeil Roberts1-1/+10
2019-11-20nir/opcodes: Add a helper function to generate reduce opcodesNeil Roberts1-17/+15
2019-11-20nir/opcodes: Add a helper function to generate the comparison binopsNeil Roberts1-20/+14
2019-10-18nir: add amul instructionRob Clark1-0/+12
2019-10-18nir: Add a new ALU nir_op_imul24Rob Clark1-0/+3
2019-10-18nir: Add a new ALU nir_op_imad24_ir3Eduardo Lima Mitev1-0/+7
2019-09-18nir/opcodes: Clear variable names confusionAndres Gomez1-10/+15
2019-09-17nir: fix fmin/fmax support for doublesSamuel Iglesias Gonsálvez1-2/+2
2019-09-17nir: fix denorms in unpack_half_1x16()Samuel Iglesias Gonsálvez1-1/+10
2019-09-17nir/opcodes: make sure f2f16_rtz and f2f16_rtne behavior is not overriden by ...Samuel Iglesias Gonsálvez1-1/+20
2019-09-17nir: mind rounding mode on fadd, fsub, fmul and fma opcodesSamuel Iglesias Gonsálvez1-4/+45
2019-09-17nir: add support for round to zero rounding mode to nir_op_f2f32Samuel Iglesias Gonsálvez1-0/+10
2019-07-31nir/algebraic: add new fsum ops and fdot loweringErico Nunes1-0/+2
2019-07-01nir: Add urol and uror opcodesSagar Ghuge1-0/+11
2019-06-26nir: remove fnot/fxor/fand/for opcodesJonathan Marek1-14/+0
2019-06-24nir: introduce lowering of bitfield_insert to bfm and a new opcode bitfield_s...Daniel Schürmann1-0/+3
2019-06-24nir: define behavior of nir_op_bfm and nir_op_u/ibfe according to SM5 spec.Daniel Schürmann1-16/+12
2019-06-07nir/opcodes: Add new 'umul_low' and 'imadsh_mix16' opcodesEduardo Lima Mitev1-1/+14
2019-05-24nir: Drop imov/fmov in favor of one mov instructionJason Ekstrand1-4/+1
2019-05-14nir: Mark ffma as 2src_commutativeIan Romanick1-15/+15
2019-05-14nir: Rename commutative to 2src_commutativeIan Romanick1-43/+48
2019-05-01nir: Saturating integer arithmetic is not associativeIan Romanick1-1/+1
2019-04-19nir_opcodes.py: Saturate to expression that doesn't overflowKristian H. Kristensen1-1/+1
2019-04-15nir,ac/nir: fix cube_face_coordRhys Perry1-6/+15
2019-03-22nir: use generic float types for frexp_exp and frexp_sigSamuel Pitoiset1-2/+2
2019-03-06compiler/nir: add an is_conversion field to nir_op_infoIago Toral Quiroga1-33/+43
2019-03-05nir/spirv: initial handling of OpenCL.std extension opcodesKarol Herbst1-0/+38
2019-03-04nir/glsl: Add another way of doing lower_imul64 for gen8+Sagar Ghuge1-0/+6
2019-02-25nir: Define shifts according to SM5 specification.Daniel Schürmann1-4/+6
2018-12-16nir: Add 1-bit Boolean opcodesJason Ekstrand1-2/+27
2018-12-16nir: Rename Boolean-related opcodes to include 32 in the nameJason Ekstrand1-17/+17
2018-12-13nir: Add a saturated unsigned integer add opcodeIan Romanick1-0/+2
2018-12-13nir: Allow [iu]mul_high on non-32-bit typesJason Ekstrand1-4/+39
2018-12-05nir: Make boolean conversions sized just like the othersJason Ekstrand1-12/+13
2018-12-05nir/opcodes: Rename tbool to tbool32Jason Ekstrand1-11/+11
2018-12-05nir/opcodes: Pull in the type helpers from constant_expressionsJason Ekstrand1-5/+29
2018-08-29nir/opcodes: Make unpack_half_2x16_split_* variable-widthJason Ekstrand1-4/+4
2018-07-24nir: rename f2f16_undef to f2f16Karol Herbst1-2/+2
2018-07-24python: Use range() instead of xrange()Mathieu Bridon1-2/+2
2018-05-03nir: add opcodes for 16-bit packing and unpackingIago Toral Quiroga1-0/+19
2018-04-14nir: subgroups instructions for 64bit ballot sizesDaniel Schürmann1-6/+6
2018-03-29nir: add support for min/max/median of 3 srcsDave Airlie1-0/+14
2018-03-22nir: add frexp_exp and frexp_sig opcodesTimothy Arceri1-0/+3
2018-03-07nir: add AMD_gcn_shader extended instructionsDaniel Schürmann1-0/+28
2018-02-28nir: fix interger divide by zero crash during constant foldingTimothy Arceri1-2/+2
2017-12-07nir/opcodes: Fix constant-folding of bitfield_insertJames Legg1-2/+2
2017-12-06nir: Handle fp16 rounding modes at nir_type_conversion_opJose Maria Casanova Crespo1-2/+9
2017-10-12nir/opcodes: Fix constant-folding of ufind_msbJason Ekstrand1-1/+1
2017-08-29nir: Remove series of unnecessary conversionsMatt Turner1-1/+1
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-25 20:45:41 +0000