summaryrefslogtreecommitdiffstats
path: root/src/amd/common/ac_llvm_build.c
Commit message (Expand)AuthorAgeFilesLines
* amd: remove support for LLVM 6.0Samuel Pitoiset2018-12-061-256/+14
* ac: avoid casting pointers on bcsel and storesDave Airlie2018-11-211-0/+9
* radv: Use structured intrinsics instead of indexing workaround for GFX9.Bas Nieuwenhuizen2018-11-191-0/+52
* ac: fix ac_build_fdiv for f64Marek Olšák2018-10-291-1/+2
* ac: Introduce ac_build_expand()Connor Abbott2018-10-221-14/+26
* ac: add helpers for fast integer division by a constantMarek Olšák2018-10-161-0/+61
* radv: emit the GLC bit for SSBO loads/stores when neededSamuel Pitoiset2018-10-121-2/+3
* ac: add ac_build_roundMarek Olšák2018-10-061-2/+17
* ac: simplify LLVM alloca helpersMarek Olšák2018-10-061-7/+4
* ac: define all address spaces properlyMarek Olšák2018-10-061-5/+5
* ac: add 16-bit support to ac_build_bitfield_reverse()Samuel Pitoiset2018-09-171-0/+5
* ac: add 16-bit support to ac_build_bit_count()Samuel Pitoiset2018-09-171-0/+5
* ac: add 16-bit support to ac_find_lsb()Samuel Pitoiset2018-09-171-2/+13
* ac: add 16-bit support to ac_build_umsb()Samuel Pitoiset2018-09-171-2/+16
* ac: add 16-bit support to ac_build_isign()Samuel Pitoiset2018-09-171-5/+16
* ac: add 16-bit constant values for zero and oneSamuel Pitoiset2018-09-171-0/+2
* ac: add ac_build_bifield_reverse() helperSamuel Pitoiset2018-09-171-0/+22
* ac: add ac_build_bit_count() helperSamuel Pitoiset2018-09-171-0/+28
* radeonsi: fix GPU hangs with bindless textures and LLVM 7.0Marek Olšák2018-09-101-5/+47
* ac: use iN_0/1 constantsMarek Olšák2018-09-101-12/+11
* ac: revert new LLVM 7.0 behavior for fdivMarek Olšák2018-09-101-1/+8
* ac,radeonsi: use ac_build_fmadMarek Olšák2018-08-211-2/+1
* ac: add imad & fmad helpersMarek Olšák2018-08-211-0/+14
* ac: add ac_build_s_barrierMarek Olšák2018-08-211-0/+6
* amd: remove support for LLVM 5.0Marek Olšák2018-08-031-104/+25
* ac: add support for 16bit UBO loadsDaniel Schürmann2018-07-231-0/+25
* ac: add 16bit conversion operationsDaniel Schürmann2018-07-231-5/+8
* ac: fold LLVMContext creation into ac_llvm_context_initMarek Olšák2018-07-041-3/+3
* ac: handle undefined EQAA samples in ac_apply_fmask_to_sampleMarek Olšák2018-06-131-2/+4
* ac: fix possible truncation of intrinsic nameTimothy Arceri2018-06-081-1/+1
* amd/common: Fix number of coords for getlod.Bas Nieuwenhuizen2018-06-071-3/+18
* amd/common: use the dimension-aware image intrinsics on LLVM 7+Nicolai Hähnle2018-06-041-24/+165
* ac: Use DPP for build_ddxy where possible.Bas Nieuwenhuizen2018-05-231-1/+15
* amd: remove support for LLVM 4.0Marek Olšák2018-05-171-179/+103
* ac/llvm: use amdgcn.tbuffer.store instead of SI.tbuffer.store intrinsicDave Airlie2018-05-171-32/+60
* amd/common: use llvm.amdgcn.wqm for explicit derivativesNicolai Hähnle2018-05-041-0/+7
* ac: fix the number of coordinates for ac_image_get_lod and arraysSamuel Pitoiset2018-04-231-0/+14
* ac/nir: use ac_build_image_opcode for image intrinsicsNicolai Hähnle2018-04-201-22/+0
* radeonsi: generate image load/store/atomic ops using ac_build_image_opcodeNicolai Hähnle2018-04-201-27/+78
* amd/common: pass address components individually to ac_build_image_intrinsicNicolai Hähnle2018-04-201-12/+89
* amd/common: pass new enum ac_image_dim to ac_build_image_opcodeNicolai Hähnle2018-04-201-2/+8
* ac: add LLVM build functions for subgroup instrinsicsDaniel Schürmann2018-04-141-0/+456
* ac: make ballot and umsb capable of 64bit inputsDaniel Schürmann2018-04-141-9/+25
* radeonsi: move FMASK shader logic to shared codeMarek Olšák2018-04-021-0/+56
* ac/nir: Add workaround for GFX9 buffer views.Bas Nieuwenhuizen2018-03-291-0/+24
* ac/nir: move unpack_param() to ac_llvm_build.cSamuel Pitoiset2018-03-131-0/+16
* ac/nir: move trim_vector to ac_llvm_build.cSamuel Pitoiset2018-03-131-0/+19
* ac/nir: move cast_ptr() to ac_llvm_build.cSamuel Pitoiset2018-03-131-0/+8
* ac/nir: move ac_build_alloca() to ac_llvm_build.cSamuel Pitoiset2018-03-131-0/+33
* ac: add if/loop build helpersTimothy Arceri2018-03-081-0/+189