* hyundai fw query
* Change query
* this works
* That is not engine
* hyundai fw query
* Change query
* this works
* That is not engine
* Skip FW query in test_car_models
* Those routes don't fingerprint properly after speedup
* only send toyota queries to subaddresses
Co-authored-by: openpilot laptop <laptop@comma.ai>
* bigmodel
* more debug print
* debugging bigmodel
* remove the tanh, debugging
* print images/buffers
* disassemble the command queues
* decompiler
* dump the shaders
* full disasm
* support patching kernel and fixing convolution_horizontal_reduced_reads_1x1
* microbenchmark
* 42 GFLOPS, 1 GB/s
* gemm benchmark
* 75 GFLOPS vs 42 GFLOPS
* 115 GFLOPS
* oops, never mind
* gemm image is slow
* this is pretty hopeless
* gemm image gets 62 GFLOPS
* this is addictive and still a waste of time
* cleanup cleanup
* that hook was dumb
* tabbing
* more tabbing
Co-authored-by: Comma Device <device@comma.ai>
* way cleaner take 2
* cleanup
* be more relaxed
* just let it be
* don't drive backwards or upside down
* do this more
* vNED sometyimes invalid
* use reasonble stds
* stability in nonlinear zone
* previous metrics were without publishing
* thneed runs the model
* thneed is doing the hooking
* set kernel args
* thneeding the bufferS
* print the images well
* thneeds with better buffers
* includes
* disasm adreno
* parse packets
* disasm works
* disasm better
* more thneeding
* much thneeding
* much more thneeding
* thneed works i think
* thneed is patient
* thneed works
* 7.7%
* gpuobj sync
* yay, it mallocs now
* cleaning it up, Thneed
* sync objs and set power
* thneed needs inputs and outputs
* thneed in modeld
* special modeld runs
* can't thneed the DSP
* test is weird
* thneed modeld uses 6.4% CPU
* add thneed to release
* move to debug
* delete some junk from the pr
* always track the timestamp
* timestamp hacks in thneed
* create a new command queue
* fix timestamp
* pretty much back to what we had, you can't use SNPE with thneed
* improve thneed test
* disable save log
Co-authored-by: Comma Device <device@comma.ai>
* add rednose
* update rednose
* This compiles
* Add rednose to release
* cleanup
* Extract generated dir as argument
* Add constants.py to release
* Add rednose to dockerfile
* Fix that
Previous commit moved G80 from G90 grouping to Hyundai Genesis grouping.
Bug found as minSteerSpeed is 0 for G80 but 60 for Hyundai Genesis.
Taking @pd0wm recommendation and ungrouping G80 to its own.
* it's a class
* more refactor
* remove that
* car interface should create that
* that too
* not a dict
* don't create permanent events every iteration
* break up long lines
* fix honda
* small optimization
* less long lines
* dict is faster
* latcontrol less args
* longcontrol less args
* update profiling script
* few optimizations
* create events together
* clean up
* more clean up
* remove comment
* clean up
* simplify state transition
* more clean up
* update comments
Willem Melching
Adeeb Shihadeh
VirtuallyChris
George Hotz
Hylke Jellema
eFini
Comma Device
Erich Moraga
HaraldSchafer
Andre Volmensky
Chris Souers
Paweł Goliński
Bruce Wayne
Adeeb
Jason Young
xps-genesis
Dean Lee