| /xsrc/external/mit/MesaLib/dist/src/amd/registers/ |
| H A D | gfx10.json | 1044 "chips": ["gfx10"], 1050 "chips": ["gfx10"], 1056 "chips": ["gfx10"], 1062 "chips": ["gfx10"], 1068 "chips": ["gfx10"], 1074 "chips": ["gfx10"], 1080 "chips": ["gfx10"], 1086 "chips": ["gfx10"], 1091 "chips": ["gfx10"], 1097 "chips": ["gfx10"], [all...] |
| H A D | pkt3.json | 132 "chips": ["gfx9", "gfx10", "gfx103"], 144 "chips": ["gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 150 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 168 "chips": ["gfx9", "gfx10", "gfx103"], 174 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 180 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 198 "chips": ["gfx9", "gfx10", "gfx103"], 204 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 209 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx103"], 214 "chips": ["gfx6", "gfx7", "gfx8", "gfx81", "gfx9", "gfx10", "gfx10 [all...] |
| H A D | gfx10-rsrc.json | 198 "chips": ["gfx10", "gfx103"], 203 "chips": ["gfx10", "gfx103"], 209 "chips": ["gfx10", "gfx103"], 214 "chips": ["gfx10"], 226 "chips": ["gfx10", "gfx103"], 232 "chips": ["gfx10", "gfx103"], 237 "chips": ["gfx10", "gfx103"], 243 "chips": ["gfx10", "gfx103"], 249 "chips": ["gfx10", "gfx103"], 255 "chips": ["gfx10"], [all...] |
| /xsrc/external/mit/MesaLib/dist/src/amd/compiler/ |
| H A D | aco_opcodes.py | 379 for (gfx6, gfx7, gfx8, gfx9, gfx10, name, cls) in default_class(SOP2, InstrClass.Salu): 380 opcode(name, gfx7, gfx9, gfx10, Format.SOP2, cls) 415 for (gfx6, gfx7, gfx8, gfx9, gfx10, name, cls) in default_class(SOPK, InstrClass.Salu): 416 opcode(name, gfx7, gfx9, gfx10, Format.SOPK, cls) 493 for (gfx6, gfx7, gfx8, gfx9, gfx10, name, cls) in default_class(SOP1, InstrClass.Salu): 494 opcode(name, gfx7, gfx9, gfx10, Format.SOP1, cls) 521 for (gfx6, gfx7, gfx8, gfx9, gfx10, name) in SOPC: 522 opcode(name, gfx7, gfx9, gfx10, Format.SOPC, InstrClass.Salu) 568 for (gfx6, gfx7, gfx8, gfx9, gfx10, name, cls) in default_class(SOPP, InstrClass.Salu): 569 opcode(name, gfx7, gfx9, gfx10, Forma [all...] |
| /xsrc/external/mit/MesaLib/dist/docs/relnotes/ |
| H A D | 19.2.0.rst | 322 - radeonsi/gfx10: fix the legacy pipeline by storing as_ngg in the 325 - radeonsi/gfx10: fix tessellation for the legacy pipeline 326 - radeonsi/gfx10: fix the PRIMITIVES_GENERATED query if using legacy 328 - radeonsi/gfx10: create the GS copy shader if using legacy streamout 329 - radeonsi/gfx10: add as_ngg variant for VS as ES to select Wave32/64 330 - radeonsi/gfx10: fix InstanceID for legacy VS+GS 331 - radeonsi/gfx10: don't initialize VGT_INSTANCE_STEP_RATE_0 332 - radeonsi/gfx10: always use the legacy pipeline for streamout 333 - radeonsi/gfx10: finish up Navi14, add PCI ID 334 - radeonsi/gfx10 [all...] |
| H A D | 20.2.4.rst | 108 - radeonsi: disable WGP mode on gfx10.3 to prevent hangs 112 - radeonsi/gfx10: flush gfx cs on ngg -> legacy transition
|
| H A D | 19.2.7.rst | 72 - radv/gfx10: fix implementation of exclusive scans
|
| H A D | 19.2.1.rst | 122 - radeonsi/gfx10: fix L2 cache rinse programming 126 - radeonsi/gfx10: fix corruption for chips with harvested TCCs
|
| H A D | 21.1.4.rst | 155 - aco/gfx10: NGG zero output workaround for conservative rasterization. 156 - aco/gfx10: Emit barrier at the start of NGG VS and TES.
|
| H A D | 19.3.0.rst | 2321 - radeonsi/gfx10: fix the legacy pipeline by storing as_ngg in the 2324 - radeonsi/gfx10: fix tessellation for the legacy pipeline 2325 - radeonsi/gfx10: fix the PRIMITIVES_GENERATED query if using legacy 2327 - radeonsi/gfx10: create the GS copy shader if using legacy streamout 2328 - radeonsi/gfx10: add as_ngg variant for VS as ES to select Wave32/64 2329 - radeonsi/gfx10: fix InstanceID for legacy VS+GS 2330 - radeonsi/gfx10: don't initialize VGT_INSTANCE_STEP_RATE_0 2331 - radeonsi/gfx10: always use the legacy pipeline for streamout 2332 - radeonsi/gfx10: finish up Navi14, add PCI ID 2333 - radeonsi/gfx10 [all...] |
| H A D | 19.2.5.rst | 102 - radeonsi: disable sdma for gfx10
|
| H A D | 20.1.5.rst | 114 - radeonsi/gfx10: set the correct value for OFFCHIP_BUFFERING
|
| H A D | 19.3.3.rst | 149 - ac/gpu_info: always use distributed tessellation on gfx10 202 - aco/gfx10: Fix VcmpxExecWARHazard mitigation.
|
| H A D | 20.0.3.rst | 158 - radv/gfx10: fix required subgroup size with 160 - radv/gfx10: fix required ballot size with
|
| H A D | 20.2.5.rst | 109 - ac: fix min/max_good_num_cu_per_sa on gfx10.3 with disabled SEs 110 - radeonsi: disable SDMA on gfx6-7 and gfx10.3 to decrease CPU overhead
|
| H A D | 20.0.0.rst | 2289 - radeonsi/gfx10: simplify some duplicated NGG GS code 2290 - radeonsi/gfx10: fix the vertex order for triangle strips emitted by a 2311 - radeonsi/gfx10: disable vertex grouping 2312 - radeonsi/gfx10: simplify the tess_turns_off_ngg condition 2321 - radeonsi/gfx10: don't insert NGG streamout atomics if they are never 2327 - radeonsi/gfx10: fix ngg_get_ordered_id 2330 - radeonsi/gfx10: don't declare any LDS for NGG if it's not used 2331 - radeonsi/gfx10: enable NGG passthrough for eligible shaders 2332 - radeonsi/gfx10: improve performance for TES using PrimID but not 2338 gfx10 [all...] |
| H A D | 19.2.3.rst | 133 - radv/gfx10: fix 3D images
|
| H A D | 19.3.2.rst | 126 - radv/gfx10: fix the out-of-bounds check for vertex descriptors
|
| H A D | 20.0.2.rst | 34 - [RadeonSI][gfx10/navi] Kerbal Space Program crash: si_draw_vbo:
|
| H A D | 20.1.6.rst | 122 - radv/gfx10: add missing initialization of registers
|
| H A D | 20.2.2.rst | 94 - Revert "radeonsi/gfx10: disable vertex grouping"
|
| H A D | 21.1.2.rst | 133 - radeonsi: add a gfx10 hw bug workaround with the barrier before gs_alloc_req
|
| H A D | 21.1.3.rst | 115 - radeonsi: add a gfx10 bug workaround for NOT_EOP
|
| H A D | 21.3.4.rst | 143 - radeonsi/gfx10: fix si_texture_get_offset for mipmapped tex
|
| H A D | 20.1.0.rst | 197 - [RadeonSI][gfx10/navi] Kerbal Space Program crash: si_draw_vbo: 3045 - radeonsi/gfx10: cache metadata in L2 on small chips 3046 - radeonsi: set better tessellation tunables on gfx9 and gfx10 3049 - ac: disable late alloc on small gfx10 chips 3115 - radeonsi/gfx10: don't use NGG culling if compute-based culling is 3117 - radeonsi/gfx10: fix ds.ordered.add intrinsic for compute-based 3119 - radeonsi/gfx10: user correct ACQUIRE_MEM packet for compute-based 3121 - radeonsi/gfx10: fix the wave size for compute-based culling 3122 - radeonsi/gfx10: fix descriptors and compute registers for 3142 - ac: out-of-order rasterization is not supported on gfx10 [all...] |