summaryrefslogtreecommitdiffstats
path: root/src/glsl/nir/nir_opcodes.py
Commit message (Expand)AuthorAgeFilesLines
* Merge remote-tracking branch 'mattst88/nir-lower-pack-unpack' into vulkanJason Ekstrand2016-01-251-10/+29
|\
| * nir: Add lowering support for packing opcodes.Matt Turner2016-01-251-0/+10
| * nir: Add opcodes to extract bytes or words.Matt Turner2016-01-251-0/+9
| * nir: Make argument order of unop_convert match binop_convert.Matt Turner2016-01-251-10/+10
* | nir/opcodes: Properly flush denormals in fquantize2f16Jason Ekstrand2016-01-221-1/+1
* | Merge remote-tracking branch 'mesa-public/master' into vulkanJason Ekstrand2016-01-141-12/+47
|\|
| * nir: Lower bitfield_extract.Matt Turner2016-01-141-0/+31
| * nir: Handle <bits>=32 case in bitfield_insert lowering.Matt Turner2016-01-141-0/+1
| * nir: Change bfm's semantics to match Intel/AMD/SM5.Matt Turner2016-01-131-3/+6
| * glsl: Fix undefined shifts.Matt Turner2016-01-131-3/+3
| * glsl, nir: Make ir_triop_bitfield_extract a vectorized operation.Kenneth Graunke2016-01-131-4/+4
| * glsl, nir: Make ir_quadop_bitfield_insert a vectorized operation.Kenneth Graunke2016-01-131-2/+2
| * nir: Fix constant evaluation of bfm.Matt Turner2016-01-131-1/+1
* | nir: Add more modulus and remainder opcodesJason Ekstrand2016-01-131-1/+15
* | nir: Add a fquantize2f16 opcodeJason Ekstrand2016-01-121-0/+1
|/
* nir/opcodes: Fix up uadd_carry and usub_borrowJason Ekstrand2016-01-071-2/+2
* nir: Delete bany, ball, fany, fall.Matt Turner2015-12-181-7/+0
* nir: s/nir_type_unsigned/nir_type_uintJason Ekstrand2015-11-231-39/+39
* nir: fix constant folding of bfiConnor Abbott2015-11-191-2/+2
* nir: Add opcodes for saturated vector math.Eric Anholt2015-10-231-0/+45
* nir: Add fdph and fdph_replicated opcodesJason Ekstrand2015-09-221-0/+5
* nir: Add a fdot instruction that replicates the result to a vec4Jason Ekstrand2015-09-151-0/+3
* nir: Avoid double promotion.Matt Turner2015-07-291-2/+2
* nir: Delete all traces of nir_op_flogIan Romanick2015-05-081-1/+0
* nir: Delete all traces of nir_op_fexpIan Romanick2015-05-081-1/+0
* nir: Remove fsin_reduced/fcos_reduced.Matt Turner2015-04-061-2/+0
* nir: fix typo for f2b/i2b/b2i expressions (v2)Rob Clark2015-04-051-3/+3
* mesa: Replace _mesa_round_to_even() with _mesa_roundeven().Matt Turner2015-03-181-1/+1
* nir/opcodes: Use a return type of tfloat for ldexpJason Ekstrand2015-01-281-1/+1
* Revert "nir/opcodes: Use fpclassify() instead of isnormal() for ldexp"Jason Ekstrand2015-01-281-1/+1
* nir/opcodes: Use fpclassify() instead of isnormal() for ldexpJason Ekstrand2015-01-281-1/+1
* nir/opcodes: Don't go through doubles when constant-folding iabsJason Ekstrand2015-01-261-1/+1
* nir/opcodes: Simplify and fix the unpack_half_*_split_* constant expressionsJason Ekstrand2015-01-261-6/+4
* nir: add new constant folding infrastructureJason Ekstrand2015-01-241-184/+396
* nir: use Python to autogenerate opcode informationConnor Abbott2015-01-241-0/+381
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 06:15:03 +0000