* 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
* Shebang Fix
Per George's "I'd merge a PR replacing the 4 python3.7 with python3" on Discord. George updated Python to 3.8.2 for webcam tools, which broke manager from launching. Instead of chasing the exact version, it seems more reasonable to fall back to 3.
* More Python3.7's
George Hotz
HaraldSchafer
Andre Volmensky
Chris Souers
Willem Melching
Paweł Goliński
Bruce Wayne
Adeeb
Jason Young
xps-genesis
Chris McCammon
Dean Lee
Erich Moraga
Adeeb Shihadeh
George Hotz
robbederks
William