aboutsummaryrefslogtreecommitdiffstats
path: root/src/compiler
Commit message (Expand)AuthorAgeFilesLines
* glsl: Restore the IsES flag on the shader when reading from cache.Eric Anholt2020-03-221-0/+2
* nir/gather_info: handle emit_vertex_with_counterRhys Perry2020-03-191-0/+1
* nir: fix clip/cull_distance_array_size in nir_lower_clip_cull_distance_arraysMarek Olšák2020-03-191-1/+10
* soft-fp64: Split a block that was missing a cast on a comparisonIan Romanick2020-03-181-13/+15
* soft-fp64/fadd: Common code optimization for differing sign caseIan Romanick2020-03-181-21/+11
* soft-fp64/fadd: Move common code out of both branches of an if-statementIan Romanick2020-03-181-22/+11
* soft-fp64/fadd: Use absolute value of expDiffIan Romanick2020-03-181-3/+4
* soft-fp64/fadd: Rename aFrac and bFrac variablesIan Romanick2020-03-181-6/+21
* soft-fp64/fadd: Combine an if-statement into the preceeding else-clauseIan Romanick2020-03-181-4/+2
* soft-fp64/fadd: Reformat after previous commitIan Romanick2020-03-181-19/+21
* soft-fp64/fadd: Delete a redundant condition checkIan Romanick2020-03-181-1/+1
* soft-fp64/fadd: Just let the subtraction happen when the result will be zeroIan Romanick2020-03-181-4/+5
* soft-fp64/fadd: Pick zero or non-zero result based on subtraction resultIan Romanick2020-03-181-6/+1
* soft-fp64/fadd: Massively split the live range of zFrac0 and zFrac1Ian Romanick2020-03-181-3/+12
* soft-fp64/fadd: Instead of tracking "b < a", track sign of the differenceIan Romanick2020-03-181-5/+5
* soft-fp64: Optimize __fmin64 and __fmax64 by using different evaluation order...Ian Romanick2020-03-181-8/+16
* soft-fp64/ffloor: Simplify the >= 0 comparisonIan Romanick2020-03-181-1/+13
* soft-fp64: Relax the way NaN is propagatedIan Romanick2020-03-181-2/+19
* soft-fp64/fsat: Micro-optimize x >= 1 testIan Romanick2020-03-181-1/+19
* soft-fp64/fsat: Micro-optimize x < 0 testIan Romanick2020-03-181-1/+3
* soft-fp64/fsat: Correctly handle NaNIan Romanick2020-03-181-2/+3
* soft-fp64/flt: Perform checks in a different orderIan Romanick2020-03-182-16/+67
* soft-fp64/fneg: Don't treat NaN speciallyIan Romanick2020-03-181-4/+1
* soft-fp64: Store sign value as 0 or 0x80000000Ian Romanick2020-03-181-16/+16
* soft-fp64: Pick a single idiom for treating sign value as a BooleanIan Romanick2020-03-181-10/+10
* soft-fp64: Simplify __countLeadingZeros32 functionIan Romanick2020-03-181-3/+1
* soft-fp64: Don't open-code umulExtendedIan Romanick2020-03-181-32/+8
* soft-fp64/b2f: Reimplement using bitwise logic opsIan Romanick2020-03-181-1/+1
* 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
* meson: Avoid duplicate symbols.Jose Fonseca2020-03-162-4/+13
* nir/glsl: gather bitmask of images used by programTapani Pälli2020-03-162-0/+21
* glsl: do not crash if string literal is used outside of #include/#lineDanylo Piliaiev2020-03-131-0/+1
* glsl/tests: Fix waiting for disk_cache_put() to finish.Eric Anholt2020-03-121-42/+11
* glsl/tests: Catch mkdir errors to help explain when they happen.Eric Anholt2020-03-121-2/+14
* nir: Add pass to combine adjacent scoped memory barriersCaio Marcelo de Oliveira Filho2020-03-124-0/+95
* nir: Reorder nir_scopes so wider scope has larger numeric valueCaio Marcelo de Oliveira Filho2020-03-121-4/+4
* nir: Don't skip a bit in nir_memory_semanticsCaio Marcelo de Oliveira Filho2020-03-121-2/+2
* nir/algebraic: coalesce fmod loweringJuan A. Suarez Romero2020-03-121-2/+1
* nir/lower_double_ops: relax lower mod()Juan A. Suarez Romero2020-03-121-9/+22
* nir: Add ability to lower non-const quad broadcasts to const ones.Timur Kristóf2020-03-122-1/+42
* glsl/list: use uintptr_t for exec_node_data()'s subtractionRhys Perry2020-03-121-1/+1
* nir/print: show variable precisionRob Clark2020-03-101-0/+10
* glsl/opt_minmax: Add support for float16Neil Roberts2020-03-091-0/+19
* glsl/lower_instructions: Handle fp16 for FDIV_TO_MUL_RCPKristian H. Kristensen2020-03-091-4/+5
* glsl/lower_instructions: Handle fp16 for MOD_TO_FLOORHyunjun Ko2020-03-091-1/+1
* glsl/lower_instructions: Use float16 constants when appropriateNeil Roberts2020-03-091-5/+31
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-25 07:04:39 +0000