aboutsummaryrefslogtreecommitdiffstats
path: root/src/compiler/nir/nir_opt_algebraic.py
Commit message (Expand)AuthorAgeFilesLines
* nir: Add b2b opcodesJason Ekstrand2020-03-301-1/+1
* nir/algebraic: add fexp2(fmul(flog2(a), 0.5) -> fsqrt(a) optimizationSamuel Pitoiset2020-03-301-0/+1
* soft-fp64/flt: Perform checks in a different orderIan Romanick2020-03-181-0/+11
* nir/algebraic: Simplify a contradiction that can occur in __flt64_nonnanIan Romanick2020-03-181-0/+1
* nir/algebraic: Constant reassociation for bitwise operations tooIan Romanick2020-03-181-0/+3
* nir/algebraic: Generalize some and-of-shift-right patterns [v2]Ian Romanick2020-03-181-2/+19
* nir/algebraic: optimize ior(ine(a, 0), ine(b, 0)) to ine(ior(a, b), 0)Ian Romanick2020-03-181-1/+5
* nir/algebraic: Simplify logic to detect sign of an integerIan Romanick2020-03-181-0/+15
* nir/algebraic: coalesce fmod loweringJuan A. Suarez Romero2020-03-121-2/+1
* nir: Flush to zero with OOB low exponents in ldexpJason Ekstrand2020-03-041-14/+41
* nir: Add optimization for doing removing f16/f32 conversionsHyunjun Ko2020-02-241-0/+7
* nir/opcodes: Add nir_op_f2fmpNeil Roberts2020-02-241-0/+5
* Revert "nir: Add a couple trivial abs optimizations"Erik Faye-Lund2020-02-131-2/+0
* nir: do not use De Morgan's Law rules for flt and fgeSamuel Pitoiset2020-02-111-1/+1
* nir/algebraic: add some half packing optimizationsRhys Perry2020-01-291-0/+9
* nir/algebraic: add patterns for a >> #b << #bRhys Perry2020-01-291-0/+16
* nir/algebraic: Optimize some 64-bit integer comparisons involving zeroIan Romanick2020-01-231-0/+18
* nir/algebraic: Add lowering for 64-bit iadd_sat and isub_satIan Romanick2020-01-231-0/+50
* nir/algebraic: Add lowering for 64-bit uadd_satIan Romanick2020-01-231-0/+1
* nir/algebraic: Add lowering for 64-bit usub_satIan Romanick2020-01-231-0/+1
* nir/algebraic: Add lowering for 64-bit hadd and rhaddIan Romanick2020-01-231-0/+5
* nir/algebraic: Add lowering for uabs_usub and uabs_isubIan Romanick2020-01-231-0/+3
* nir/algebraic: sqrt(x)*sqrt(x) -> fabs(x)Elie Tournier2020-01-151-0/+1
* nir/algebraic: i2f(f2i()) -> trunc()Elie Tournier2020-01-151-0/+5
* nir/algebraic: a & ~(a >> 31) -> imax(a, 0)Rhys Perry2020-01-141-0/+1
* nir: add option to lower half packing opcodesJonathan Marek2019-12-161-0/+12
* nir/algebraic: Rearrange bcsel sequences generated by nir_opt_peephole_selectIan Romanick2019-12-021-0/+53
* nir/algebraic: Simplify some Inf and NaN avoidance codeIan Romanick2019-12-021-0/+9
* nir/algebraic: Mark other comparison exact when removing a == aIan Romanick2019-11-041-2/+2
* nir/algebraic: Add the ability to mark a replacement as exactIan Romanick2019-11-041-0/+3
* nir: add nir_lower_amul passRob Clark2019-10-181-3/+3
* nir: add address calc related opt rulesRob Clark2019-10-181-0/+16
* nir: add amul instructionRob Clark2019-10-181-0/+5
* nir: Remove unnecessary subtraction optimizationsDaniel Schürmann2019-09-301-10/+0
* nir: recombine nir_op_*sub when lower_sub = falseDaniel Schürmann2019-09-301-8/+13
* nir/algebraic: Additional D3D Boolean optimizationIan Romanick2019-09-191-0/+1
* nir/algebraic: Do not apply late DPH optimization in vertex processing stagesIan Romanick2019-09-191-3/+12
* nir/algebraic: mark float optimizations returning one parameter as inexactAndres Gomez2019-09-171-8/+8
* nir/algebraic: Clean up value range analysis-based optimizationsIan Romanick2019-08-291-8/+18
* nir/algebraic: Mark some value range analysis-based optimizations impreciseIan Romanick2019-08-291-9/+13
* nir/algrbraic: Don't optimize open-coded bitfield reverse when lowering is en...Ian Romanick2019-08-281-1/+1
* nir/algebraic: some subtraction optimizationsDaniel Schürmann2019-08-211-0/+3
* nir/algebraic: add a few masking-before-unpack optimizationsRhys Perry2019-08-161-1/+9
* nir/algebraic: Reassociate shift-by-constant of shift-by-constantIan Romanick2019-08-141-1/+25
* nir/algebraic: Reassociate add-and-shift to be shift-and-addIan Romanick2019-08-141-0/+5
* nir/algebraic: Use value range analysis to eliminate useless unary opsIan Romanick2019-08-051-2/+8
* nir/algebraic: Use value range analysis to convert fmin to fsatIan Romanick2019-08-051-1/+1
* nir/algebraic: Use value range analysis to eliminate tautological comparesIan Romanick2019-08-051-21/+21
* nir/algebraic: Use value range analysis to eliminate tautological compares no...Ian Romanick2019-08-051-0/+28
* nir/algebraic: Simplify some comparisons like a+constant < constantIan Romanick2019-08-051-0/+8
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-13 12:03:27 +0000