Lines Matching full:broadcom
269 - broadcom(cle,clif,common,simulator): add 7.1 version on the list of versions to build
270 - broadcom/cle: update the packet definitions for new generation v71
271 - broadcom/common: add some common v71 helpers
272 - broadcom/qpu: add comments on waddr not used on V3D 7.x
273 - broadcom/qpu: set V3D 7.x names for some waddr aliasing
274 - broadcom/compiler: rename small_imm to small_imm_b
275 - broadcom/compiler: add small_imm a/c/d on v3d_qpu_sig
276 - broadcom/qpu: add v71 signal map
277 - broadcom/qpu: define v3d_qpu_input, use on v3d_qpu_alu_instr
278 - broadcom/qpu: add raddr on v3d_qpu_input
279 - broadcom/qpu: defining shift/mask for raddr_c/d
280 - broadcom/commmon: add has_accumulators field on v3d_device_info
281 - broadcom/qpu: add qpu_writes_rf0_implicitly helper
282 - broadcom/qpu: add pack/unpack support for v71
283 - broadcom/compiler: phys index depends on hw version
284 - broadcom/compiler: don't favor/select accum registers for hw not supporting it
285 - broadcom/vir: implement is_no_op_mov for v71
286 - broadcom/compiler: update vir_to_qpu::set_src for v71
287 - broadcom/qpu_schedule: add process_raddr_deps
288 - broadcom/qpu: update disasm_raddr for v71
289 - broadcom/qpu: return false on qpu_writes_accumulatorXX helpers for v71
290 - broadcom/compiler: add support for varyings on nir to vir generation for v71
291 - broadcom/compiler: payload_w is loaded on rf3 for v71
292 - broadcom/qpu_schedule: update write deps for v71
293 - broadcom/compiler: update register classes to not include accumulators on v71
294 - broadcom/qpu: implement switch rules for fmin/fmax fadd/faddnf for v71
295 - broadcom/compiler: update one TMUWT restriction for v71
296 - broadcom/compiler: update ldunif/ldvary comment for v71
297 - broadcom/compiler: update payload registers handling when computing live intervals
298 - broadcom/qpu: new packing/conversion v71 instructions
471 - vc4,broadcom/compiler: Drop write_mask handling
590 - broadcom/compiler: Use nir_trim_vector explicitly
1868 - ci: move broadcom files rules to src/broadcom/ci/gitlab-ci.yml
1893 - broadcom/ci: reduce vc4-rpi3-gl timeout to 30min (instead of 1h)
1894 - broadcom/ci: reduce v3d-rpi4-gl timeout to 30min (instead of 1h)
1895 - broadcom/ci: reduce v3d-rpi4-traces timeout to 30min (instead of 1h)
1896 - broadcom/ci: reduce v3dv-rpi4-vk timeout to 30min (instead of 1h)
2107 - broadcom/compiler: Convert to new-style NIR registers
2752 - broadcom: Stop using nir_dest directly
3225 - broadcom/compiler: stop asserting on Vulkan environment
3226 - broadcom/compiler: use NIR's lowering for dispatch base
3227 - broadcom/compiler: move uniform offset lowering from compiler to GL driver
3228 - broadcom/compiler: move vulkan's point coord lowering to the driver
3230 - broadcom/compiler: always clamp results from logic ops
3231 - broadcom/compiler: drop execution environment from the shader key
3236 - squash! v3dv,broadcom/compiler: don't abuse sampler index
3248 - broadcom/compiler: add a couple of shader key helpers
3253 - broadcom/simulator: reset CFG7 for compute dispatch in v71
3254 - broadcom/common: retrieve V3D revision number
3255 - broadcom/compiler: update node/temp translation for v71
3256 - broadcom/compiler: implement "reads/writes too soon" checks for v71
3257 - broadcom/compiler: implement read stall check for v71
3258 - broadcom/compiler: add a v3d71_qpu_writes_waddr_explicitly helper
3259 - broadcom/compiler: prevent rf2-3 usage in thread end delay slots for v71
3260 - broadcom/qpu: add new ADD opcodes for FMOV/MOV in v71
3261 - broadcom/qpu: fix packing/unpacking of fmov variants for v71
3262 - broadcom/compiler: make vir_write_rX return false on platforms without accums
3263 - broadcom/compiler: rename vir_writes_rX to vir_writes_rX_implicitly
3264 - broadcom/compiler: only handle accumulator classes if present
3265 - broadcom/compiler: don't assign rf0 to temps across implicit rf0 writes
3266 - broadcom/compiler: CS payload registers have changed in v71
3267 - broadcom/compiler: don't schedule rf0 writes right after ldvary
3268 - broadcom/compiler: allow instruction merges in v71
3269 - broadcom/qpu: add MOV integer packing/unpacking variants
3270 - broadcom/qpu: fail packing on unhandled mul pack/unpack
3271 - broadcom/compiler: generalize check for shaders using pixel center W
3272 - broadcom/compiler: v71 isn't affected by double-rounding of viewport X,Y coords
3273 - broadcom/compiler: update peripheral access restrictions for v71
3274 - broadcom/qpu: add packing for fmov on ADD alu
3275 - broadcom/compiler: handle rf0 flops storage restriction in v71
3276 - broadcom/compiler: enable ldvary pipelining on v71
3277 - broadcom/compiler: try to use ldunif(a) instead of ldunif(a)rf in v71
3278 - broadcom/compiler: don't assign rf0 to temps that conflict with ldvary
3279 - broadcom/compiler: convert mul to add when needed to allow merge
3280 - broadcom/compiler: implement small immediates for v71
3281 - broadcom/compiler: update thread end restrictions for v7.x
3282 - broadcom/compiler: update ldvary thread switch delay slot restriction for v7.x
3283 - broadcom/compiler: lift restriction for branch + msfign after setmsf for v7.x
3284 - broadcom/compiler: start allocating from RF 4 in V7.x
3285 - broadcom/compiler: validate restrictions after TLB Z write
3286 - broadcom/compiler: lift restriction on vpmwt in last instruction for V3D 7.x
3287 - broadcom/compiler: fix up copy propagation for v71
3288 - broadcom/compiler: don't allocate spill base to rf0 in V3D 7.x
3289 - broadcom/compiler: improve allocation for final program instructions
3290 - broadcom/compiler: don't assign registers to unused nodes/temps
3291 - broadcom/compiler: only assign rf0 as last resort in V3D 7.x
3301 - broadcom/compiler: update thread end restrictions validation for v71
3610 - broadcom/ci: update expected results
3614 - broadcom: add performance counters for V3D 7.x
3615 - broadcom/simulator: add per-hw version calls
6127 - broadcom/qpu: Remove duplicate variable opcode