summaryrefslogtreecommitdiff
AgeCommit message (Expand)AuthorFilesLines
2019-04-18intel/compiler: Improve fix_3src_operand()for-rafaelMatt Turner1-5/+18
2019-04-18intel/compiler: Add unit tests for sat prop for different exec sizesMatt Turner1-0/+68
2019-04-18intel/compiler: Use SIMD16 instructions in fs saturate prop unit testMatt Turner1-2/+2
2019-04-18intel/fs: Remove fs_generator::generate_linterp from gen11+.Rafael Antognolli1-43/+5
2019-04-18intel/fs: Add a lowering pass for linear interpolation.Rafael Antognolli2-0/+48
2019-04-18intel/fs: Only convert to scalar on fs_generator.Rafael Antognolli4-5/+5
2019-04-18intel/fs: Only propagate saturation if exec_size is the same.Rafael Antognolli1-1/+2
2019-04-18anv/device: expose VK_KHR_shader_float16_int8 in gen8+Iago Toral Quiroga2-0/+10
2019-04-18anv/pipeline: support Float16 and Int8 SPIR-V capabilities in gen8+Iago Toral Quiroga1-0/+2
2019-04-18compiler/spirv: move the check for Int8 capabilityIago Toral Quiroga1-4/+3
2019-04-18intel/compiler: validate region restrictions for mixed float modeIago Toral Quiroga2-0/+880
2019-04-18intel/compiler: validate conversions between 64-bit and 8-bit typesIago Toral Quiroga2-0/+105
2019-04-18intel/compiler: validate region restrictions for half-float conversionsIago Toral Quiroga2-1/+270
2019-04-18intel/compiler: also set F execution type for mixed float mode in BDWIago Toral Quiroga1-16/+20
2019-04-18intel/compiler: implement SIMD16 restrictions for mixed-float instructionsIago Toral Quiroga1-0/+72
2019-04-18intel/compiler: skip MAD algebraic optimization for half-float or mixed modeIago Toral Quiroga1-0/+4
2019-04-18intel/compiler: remove inexact algebraic optimizations from the backendIago Toral Quiroga1-38/+1
2019-04-18intel/compiler: fix cmod propagation for non 32-bit typesIago Toral Quiroga1-4/+9
2019-04-18intel/compiler: add a brw_reg_type_is_integer helperIago Toral Quiroga1-0/+18
2019-04-18intel/compiler: implement is_zero, is_one, is_negative_one for 8-bit/16-bitIago Toral Quiroga1-0/+26
2019-04-18intel/compiler: generalize the combine constants passIago Toral Quiroga1-22/+212
2019-04-18intel/eu: force stride of 2 on NULL register for Byte instructionsIago Toral Quiroga1-0/+11
2019-04-18intel/compiler: ask for an integer type if requesting an 8-bit typeIago Toral Quiroga1-2/+3
2019-04-18intel/compiler: rework conversion opcodesIago Toral Quiroga1-19/+22
2019-04-18intel/compiler: activate 16-bit bit-size lowerings also for 8-bitIago Toral Quiroga1-1/+1
2019-04-18intel/compiler: split is_partial_write() into two variantsIago Toral Quiroga11-30/+54
2019-04-18intel/compiler: workaround for SIMD8 half-float MAD in gen8Iago Toral Quiroga1-11/+28
2019-04-18intel/compiler: fix ddy for half-float in BroadwellIago Toral Quiroga1-2/+15
2019-04-18intel/compiler: fix ddx and ddy for 16-bit floatIago Toral Quiroga1-19/+18
2019-04-18intel/compiler: set correct precision fields for 3-source float instructionsIago Toral Quiroga1-0/+16
2019-04-18intel/compiler: allow half-float on 3-source instructions since gen8Iago Toral Quiroga1-1/+2
2019-04-18intel/compiler: don't compact 3-src instructions with Src1Type or Src2Type bitsIago Toral Quiroga1-1/+4
2019-04-18intel/compiler: add new half-float register type for 3-src instructionsIago Toral Quiroga1-0/+4
2019-04-18intel/compiler: add instruction setters for Src1Type and Src2Type.Iago Toral Quiroga1-0/+2
2019-04-18intel/compiler: drop unnecessary temporary from 32-bit fsign implementationIago Toral Quiroga1-3/+2
2019-04-18intel/compiler: implement 16-bit fsignIago Toral Quiroga1-1/+16
2019-04-18intel/compiler: handle extended math restrictions for half-floatIago Toral Quiroga3-12/+34
2019-04-18intel/compiler: lower some 16-bit float operations to 32-bitIago Toral Quiroga1-0/+5
2019-04-18intel/compiler: assert restrictions on conversions to half-floatIago Toral Quiroga1-2/+3
2019-04-18intel/compiler: handle b2i/b2f with other integer conversion opcodesIago Toral Quiroga1-8/+8
2019-04-18intel/compiler: split float to 64-bit opcodes from int to 64-bitIago Toral Quiroga1-0/+7
2019-04-18intel/compiler: add a NIR pass to lower conversionsIago Toral Quiroga5-0/+175
2019-04-17Add no_aos_sampling GALLIVM_PERF optionDominik Drees3-4/+11
2019-04-17ac: use struct/raw store intrinsics for 8-bit/16-bit int with LLVM 9+Samuel Pitoiset1-14/+34
2019-04-17ac: use struct/raw load intrinsics for 8-bit/16-bit int with LLVM 9+Samuel Pitoiset1-12/+38
2019-04-17ac: add support for more types with struct/raw LLVM intrinsicsSamuel Pitoiset1-20/+26
2019-04-17radv: add VK_KHR_shader_atomic_int64 but disable it for nowSamuel Pitoiset3-0/+12
2019-04-17ac/nir: add 64-bit SSBO atomic operations supportSamuel Pitoiset1-3/+7
2019-04-17ac/nir: use new LLVM 8 intrinsics for SSBO atomics except cmpswapSamuel Pitoiset1-13/+18
2019-04-17gallivm: fix saturated signed add / sub with llvm 9Roland Scheidegger1-0/+14
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-14 02:38:10 +0000